From 2d43955cece38b8a6cd6c8ef8d4b49eb2f2ca56a Mon Sep 17 00:00:00 2001 From: Scott Linder Date: Wed, 25 May 2022 17:17:53 +0000 Subject: [PATCH] [AMDGPU][NFC] Refactor AMDGPUCallingConv.td Rename CalleeSavedRegs defs to avoid being overly specific: * CSR_AMDGPU_AGPRs_32_255 => CSR_AMDGPU_AGPRs * CSR_AMDGPU_SGPRs_30_31 + CSR_AMDGPU_SGPRs_32_105 => CSR_AMDGPU_SGPRs * CSR_AMDGPU_SI_Gfx_SGPRs_4_29 + CSR_AMDGPU_SI_Gfx_SGPRs_64_105 => CSR_AMDGPU_SI_Gfx_SGPRs * CSR_AMDGPU_HighRegs => CSR_AMDGPU * CSR_AMDGPU_HighRegs_With_AGPRs => CSR_AMDGPU_GFX90AInsts * CSR_AMDGPU_SI_Gfx_With_AGPRs => CSR_AMDGPU_SI_Gfx_GFX90AInsts Introduce a class RegMask to mark the cases where we use the CalleeSavedRegs class purely as an expedient way to produce a mask. Update the names of these masks to not mention "CSR". Other targets also seem to do this, so a reasonable alternative is to actually update table-gen to include a new class to do this explicitly, but the current approach seems harmless so I opted to just make it more explicit. Reviewed By: arsenm, sebastian-ne Differential Revision: https://reviews.llvm.org/D109008 --- llvm/lib/Target/AMDGPU/AMDGPUCallingConv.td | 70 +++++----- llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp | 20 +-- .../AMDGPU/GlobalISel/dropped_debug_info_assert.ll | 2 +- .../AMDGPU/GlobalISel/irtranslator-assert-align.ll | 8 +- .../irtranslator-call-abi-attribute-hints.ll | 12 +- .../GlobalISel/irtranslator-call-implicit-args.ll | 40 +++--- .../GlobalISel/irtranslator-call-return-values.ll | 90 ++++++------- .../AMDGPU/GlobalISel/irtranslator-call-sret.ll | 2 +- .../CodeGen/AMDGPU/GlobalISel/irtranslator-call.ll | 144 ++++++++++----------- .../GlobalISel/irtranslator-indirect-call.ll | 2 +- .../AMDGPU/GlobalISel/irtranslator-sibling-call.ll | 46 +++---- .../AMDGPU/GlobalISel/irtranslator-tail-call.ll | 2 +- .../GlobalISel/localizer-wrong-insert-point.mir | 4 +- .../CodeGen/AMDGPU/accvgpr-spill-scc-clobber.mir | 60 ++++----- llvm/test/CodeGen/AMDGPU/agpr-copy-no-vgprs.mir | 12 +- .../CodeGen/AMDGPU/agpr-copy-sgpr-no-vgprs.mir | 12 +- .../CodeGen/AMDGPU/av_spill_cross_bb_usage.mir | 4 +- llvm/test/CodeGen/AMDGPU/call-waw-waitcnt.mir | 4 +- llvm/test/CodeGen/AMDGPU/collapse-endcf2.mir | 4 +- .../CodeGen/AMDGPU/debug-value-scheduler-crash.mir | 4 +- .../AMDGPU/fold-operands-remove-m0-redef.mir | 4 +- .../AMDGPU/greedy-alloc-fail-sgpr1024-spill.mir | 8 +- .../AMDGPU/limit-soft-clause-reg-pressure.mir | 4 +- .../CodeGen/AMDGPU/pei-scavenge-vgpr-spill.mir | 8 +- llvm/test/CodeGen/AMDGPU/sched-crash-dbg-value.mir | 2 +- .../AMDGPU/sgpr-spill-to-vmem-scc-clobber.mir | 24 ++-- .../CodeGen/AMDGPU/sgpr-spill-wrong-stack-id.mir | 12 +- llvm/test/CodeGen/AMDGPU/splitkit-copy-bundle.mir | 6 +- .../CodeGen/AMDGPU/verify-gfx90a-aligned-vgprs.mir | 2 +- .../test/CodeGen/AMDGPU/vgpr-spill-scc-clobber.mir | 80 ++++++------ .../AMDGPU/virtregrewrite-undef-identity-copy.mir | 8 +- llvm/test/CodeGen/MIR/AMDGPU/stack-id-assert.mir | 2 +- 32 files changed, 349 insertions(+), 353 deletions(-) diff --git a/llvm/lib/Target/AMDGPU/AMDGPUCallingConv.td b/llvm/lib/Target/AMDGPU/AMDGPUCallingConv.td index dec2277..b6c6607 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUCallingConv.td +++ b/llvm/lib/Target/AMDGPU/AMDGPUCallingConv.td @@ -148,57 +148,32 @@ def CSR_AMDGPU_VGPRs : CalleeSavedRegs< (sequence "VGPR%u", 248, 255)) >; -def CSR_AMDGPU_AGPRs_32_255 : CalleeSavedRegs< +def CSR_AMDGPU_AGPRs : CalleeSavedRegs< (sequence "AGPR%u", 32, 255) >; -def CSR_AMDGPU_SGPRs_30_31 : CalleeSavedRegs< - (sequence "SGPR%u", 30, 31) +def CSR_AMDGPU_SGPRs : CalleeSavedRegs< + (sequence "SGPR%u", 30, 105) >; -def CSR_AMDGPU_SGPRs_32_105 : CalleeSavedRegs< - (sequence "SGPR%u", 32, 105) +def CSR_AMDGPU_SI_Gfx_SGPRs : CalleeSavedRegs< + (add (sequence "SGPR%u", 4, 31), (sequence "SGPR%u", 64, 105)) >; -def CSR_AMDGPU_SI_Gfx_SGPRs_4_29 : CalleeSavedRegs< - (sequence "SGPR%u", 4, 29) +def CSR_AMDGPU : CalleeSavedRegs< + (add CSR_AMDGPU_VGPRs, CSR_AMDGPU_SGPRs) >; -def CSR_AMDGPU_SI_Gfx_SGPRs_64_105 : CalleeSavedRegs< - (sequence "SGPR%u", 64, 105) ->; - -// Just to get the regmask, not for calling convention purposes. -def CSR_AMDGPU_AllVGPRs : CalleeSavedRegs< - (sequence "VGPR%u", 0, 255) ->; - -def CSR_AMDGPU_AllAGPRs : CalleeSavedRegs< - (sequence "AGPR%u", 0, 255) ->; -def CSR_AMDGPU_AllVectorRegs : CalleeSavedRegs< - (add CSR_AMDGPU_AllVGPRs, CSR_AMDGPU_AllAGPRs) ->; - -// Just to get the regmask, not for calling convention purposes. -def CSR_AMDGPU_AllAllocatableSRegs : CalleeSavedRegs< - (add (sequence "SGPR%u", 0, 105), VCC_LO, VCC_HI) ->; - -def CSR_AMDGPU_HighRegs : CalleeSavedRegs< - (add CSR_AMDGPU_VGPRs, CSR_AMDGPU_SGPRs_30_31, CSR_AMDGPU_SGPRs_32_105) ->; - -def CSR_AMDGPU_HighRegs_With_AGPRs : CalleeSavedRegs< - (add CSR_AMDGPU_HighRegs, CSR_AMDGPU_AGPRs_32_255) +def CSR_AMDGPU_GFX90AInsts : CalleeSavedRegs< + (add CSR_AMDGPU, CSR_AMDGPU_AGPRs) >; def CSR_AMDGPU_SI_Gfx : CalleeSavedRegs< - (add CSR_AMDGPU_VGPRs, CSR_AMDGPU_SI_Gfx_SGPRs_4_29, CSR_AMDGPU_SGPRs_30_31, CSR_AMDGPU_SI_Gfx_SGPRs_64_105) + (add CSR_AMDGPU_VGPRs, CSR_AMDGPU_SI_Gfx_SGPRs) >; -def CSR_AMDGPU_SI_Gfx_With_AGPRs : CalleeSavedRegs< - (add CSR_AMDGPU_SI_Gfx, CSR_AMDGPU_AGPRs_32_255) +def CSR_AMDGPU_SI_Gfx_GFX90AInsts : CalleeSavedRegs< + (add CSR_AMDGPU_SI_Gfx, CSR_AMDGPU_AGPRs) >; def CSR_AMDGPU_NoRegs : CalleeSavedRegs<(add)>; @@ -237,3 +212,24 @@ def CC_AMDGPU : CallingConv<[ "AMDGPUSubtarget::SOUTHERN_ISLANDS && State.getCallingConv() == CallingConv::C", CCDelegateTo> ]>; + +// Trivial class to denote when a def is used only to get a RegMask, i.e. +// SaveList is ignored and the def is not used as part of any calling +// convention. +class RegMask : CalleeSavedRegs; + +def AMDGPU_AllVGPRs : RegMask< + (sequence "VGPR%u", 0, 255) +>; + +def AMDGPU_AllAGPRs : RegMask< + (sequence "AGPR%u", 0, 255) +>; + +def AMDGPU_AllVectorRegs : RegMask< + (add AMDGPU_AllVGPRs, AMDGPU_AllAGPRs) +>; + +def AMDGPU_AllAllocatableSRegs : RegMask< + (add (sequence "SGPR%u", 0, 105), VCC_LO, VCC_HI) +>; diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp index 4490e66..3303577 100644 --- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp +++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp @@ -394,10 +394,10 @@ const MCPhysReg *SIRegisterInfo::getCalleeSavedRegs( case CallingConv::C: case CallingConv::Fast: case CallingConv::Cold: - return ST.hasGFX90AInsts() ? CSR_AMDGPU_HighRegs_With_AGPRs_SaveList - : CSR_AMDGPU_HighRegs_SaveList; + return ST.hasGFX90AInsts() ? CSR_AMDGPU_GFX90AInsts_SaveList + : CSR_AMDGPU_SaveList; case CallingConv::AMDGPU_Gfx: - return ST.hasGFX90AInsts() ? CSR_AMDGPU_SI_Gfx_With_AGPRs_SaveList + return ST.hasGFX90AInsts() ? CSR_AMDGPU_SI_Gfx_GFX90AInsts_SaveList : CSR_AMDGPU_SI_Gfx_SaveList; default: { // Dummy to not crash RegisterClassInfo. @@ -418,10 +418,10 @@ const uint32_t *SIRegisterInfo::getCallPreservedMask(const MachineFunction &MF, case CallingConv::C: case CallingConv::Fast: case CallingConv::Cold: - return ST.hasGFX90AInsts() ? CSR_AMDGPU_HighRegs_With_AGPRs_RegMask - : CSR_AMDGPU_HighRegs_RegMask; + return ST.hasGFX90AInsts() ? CSR_AMDGPU_GFX90AInsts_RegMask + : CSR_AMDGPU_RegMask; case CallingConv::AMDGPU_Gfx: - return ST.hasGFX90AInsts() ? CSR_AMDGPU_SI_Gfx_With_AGPRs_RegMask + return ST.hasGFX90AInsts() ? CSR_AMDGPU_SI_Gfx_GFX90AInsts_RegMask : CSR_AMDGPU_SI_Gfx_RegMask; default: return nullptr; @@ -511,19 +511,19 @@ bool SIRegisterInfo::hasBasePointer(const MachineFunction &MF) const { Register SIRegisterInfo::getBaseRegister() const { return AMDGPU::SGPR34; } const uint32_t *SIRegisterInfo::getAllVGPRRegMask() const { - return CSR_AMDGPU_AllVGPRs_RegMask; + return AMDGPU_AllVGPRs_RegMask; } const uint32_t *SIRegisterInfo::getAllAGPRRegMask() const { - return CSR_AMDGPU_AllAGPRs_RegMask; + return AMDGPU_AllAGPRs_RegMask; } const uint32_t *SIRegisterInfo::getAllVectorRegMask() const { - return CSR_AMDGPU_AllVectorRegs_RegMask; + return AMDGPU_AllVectorRegs_RegMask; } const uint32_t *SIRegisterInfo::getAllAllocatableSRegMask() const { - return CSR_AMDGPU_AllAllocatableSRegs_RegMask; + return AMDGPU_AllAllocatableSRegs_RegMask; } unsigned SIRegisterInfo::getSubRegFromChannel(unsigned Channel, diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll index f9fe75c..34007a7 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll @@ -45,7 +45,7 @@ define amdgpu_kernel void @call_debug_loc() { ; CHECK-NEXT: $vgpr31 = COPY [[V_OR3_B32_e64_]], debug-location !6 ; CHECK-NEXT: [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee + 4, target-flags(amdgpu-gotprel32-hi) @callee + 12, implicit-def $scc, debug-location !6 ; CHECK-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0, debug-location !6 :: (dereferenceable invariant load (p0) from got, addrspace 4) - ; CHECK-NEXT: $sgpr30_sgpr31 = SI_CALL [[S_LOAD_DWORDX2_IMM]], @callee, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, debug-location !6 + ; CHECK-NEXT: $sgpr30_sgpr31 = SI_CALL [[S_LOAD_DWORDX2_IMM]], @callee, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, debug-location !6 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc, debug-location !6 ; CHECK-NEXT: S_ENDPGM 0 entry: diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-assert-align.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-assert-align.ll index 640314d..001589c 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-assert-align.ll +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-assert-align.ll @@ -54,7 +54,7 @@ define void @call_result_align_1() { ; CHECK-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @returns_ptr, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @returns_ptr, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr0 ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY $vgpr1 ; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY17]](s32), [[COPY18]](s32) @@ -100,7 +100,7 @@ define void @call_result_align_8() { ; CHECK-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @returns_ptr, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @returns_ptr, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr0 ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY $vgpr1 ; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY17]](s32), [[COPY18]](s32) @@ -147,7 +147,7 @@ define void @declaration_result_align_8() { ; CHECK-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @returns_ptr_align8, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @returns_ptr_align8, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; CHECK-NEXT: [[COPY17:%[0-9]+]]:_(s32) = COPY $vgpr0 ; CHECK-NEXT: [[COPY18:%[0-9]+]]:_(s32) = COPY $vgpr1 ; CHECK-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY17]](s32), [[COPY18]](s32) @@ -192,7 +192,7 @@ define i8 addrspace(1)* @tail_call_assert_align() { ; CHECK-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; CHECK-NEXT: SI_TCRETURN [[GV]](p0), @returns_ptr_align8, 0, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: SI_TCRETURN [[GV]](p0), @returns_ptr_align8, 0, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 entry: %call = tail call i8 addrspace(1)* @returns_ptr_align8() ret i8 addrspace(1)* %call diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-abi-attribute-hints.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-abi-attribute-hints.ll index 7015bd8..7ea2422 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-abi-attribute-hints.ll +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-abi-attribute-hints.ll @@ -38,7 +38,7 @@ define amdgpu_kernel void @kernel_call_no_workitem_ids() { ; CHECK-NEXT: $sgpr12 = COPY [[COPY11]](s32) ; CHECK-NEXT: $sgpr13 = COPY [[COPY12]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY13]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @extern, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @extern, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @extern() "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" @@ -81,7 +81,7 @@ define amdgpu_kernel void @kernel_call_no_workgroup_ids() { ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[PTR_ADD]](p4) ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY10]](s64) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @extern, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @extern, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @extern() "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" @@ -115,7 +115,7 @@ define amdgpu_kernel void @kernel_call_no_other_sgprs() { ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY8]](<4 x s32>) ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[PTR_ADD]](p4) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @extern, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr8_sgpr9, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @extern, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr8_sgpr9, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @extern() "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" @@ -152,7 +152,7 @@ define void @func_call_no_workitem_ids() { ; CHECK-NEXT: $sgpr12 = COPY [[COPY11]](s32) ; CHECK-NEXT: $sgpr13 = COPY [[COPY12]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY13]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @extern, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @extern, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: SI_RETURN call void @extern() "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" @@ -183,7 +183,7 @@ define void @func_call_no_workgroup_ids() { ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY7]](p4) ; CHECK-NEXT: $sgpr10_sgpr11 = COPY [[COPY8]](s64) ; CHECK-NEXT: $vgpr31 = COPY [[COPY9]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @extern, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @extern, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: SI_RETURN call void @extern() "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" @@ -205,7 +205,7 @@ define void @func_call_no_other_sgprs() { ; CHECK-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY4]](<4 x s32>) ; CHECK-NEXT: $sgpr8_sgpr9 = COPY [[COPY2]](p4) ; CHECK-NEXT: $vgpr31 = COPY [[COPY3]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @extern, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr8_sgpr9, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @extern, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr8_sgpr9, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: SI_RETURN call void @extern() "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-implicit-args.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-implicit-args.ll index c04b66d..0447b6cd 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-implicit-args.ll +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-implicit-args.ll @@ -56,7 +56,7 @@ define amdgpu_kernel void @test_call_external_void_func_i32([17 x i8]) #0 { ; GFX900-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GFX900-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GFX900-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX900-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX900-NEXT: S_ENDPGM 0 ; GFX908-LABEL: name: test_call_external_void_func_i32 @@ -106,7 +106,7 @@ define amdgpu_kernel void @test_call_external_void_func_i32([17 x i8]) #0 { ; GFX908-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GFX908-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GFX908-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX908-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX908-NEXT: S_ENDPGM 0 call void @external_void_func_i32(i32 42) @@ -148,7 +148,7 @@ define void @test_func_call_external_void_func_i32() #0 { ; GFX900-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; GFX900-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; GFX900-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX900-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX900-NEXT: SI_RETURN ; GFX908-LABEL: name: test_func_call_external_void_func_i32 @@ -185,7 +185,7 @@ define void @test_func_call_external_void_func_i32() #0 { ; GFX908-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; GFX908-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; GFX908-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX908-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX908-NEXT: SI_RETURN call void @external_void_func_i32(i32 99) @@ -278,7 +278,7 @@ define amdgpu_kernel void @test_call_external_void_func_v32i32([17 x i8]) #0 { ; GFX900-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GFX900-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GFX900-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX900-NEXT: ADJCALLSTACKDOWN 0, 4, implicit-def $scc ; GFX900-NEXT: S_ENDPGM 0 ; GFX908-LABEL: name: test_call_external_void_func_v32i32 @@ -364,7 +364,7 @@ define amdgpu_kernel void @test_call_external_void_func_v32i32([17 x i8]) #0 { ; GFX908-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GFX908-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GFX908-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX908-NEXT: ADJCALLSTACKDOWN 0, 4, implicit-def $scc ; GFX908-NEXT: S_ENDPGM 0 call void @external_void_func_v32i32(<32 x i32> zeroinitializer) @@ -493,7 +493,7 @@ define void @test_func_call_external_void_func_v32i32([17 x i8]) #0 { ; GFX900-NEXT: $sgpr13 = COPY [[COPY30]](s32) ; GFX900-NEXT: $sgpr14 = COPY [[COPY31]](s32) ; GFX900-NEXT: $vgpr31 = COPY [[COPY32]](s32) - ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX900-NEXT: ADJCALLSTACKDOWN 0, 4, implicit-def $scc ; GFX900-NEXT: SI_RETURN ; GFX908-LABEL: name: test_func_call_external_void_func_v32i32 @@ -617,7 +617,7 @@ define void @test_func_call_external_void_func_v32i32([17 x i8]) #0 { ; GFX908-NEXT: $sgpr13 = COPY [[COPY30]](s32) ; GFX908-NEXT: $sgpr14 = COPY [[COPY31]](s32) ; GFX908-NEXT: $vgpr31 = COPY [[COPY32]](s32) - ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX908-NEXT: ADJCALLSTACKDOWN 0, 4, implicit-def $scc ; GFX908-NEXT: SI_RETURN call void @external_void_func_v32i32(<32 x i32> zeroinitializer) @@ -661,7 +661,7 @@ define amdgpu_kernel void @test_only_workitem_id_x() #0 !reqd_work_group_size !0 ; GFX900-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; GFX900-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; GFX900-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX900-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX900-NEXT: S_ENDPGM 0 ; GFX908-LABEL: name: test_only_workitem_id_x @@ -700,7 +700,7 @@ define amdgpu_kernel void @test_only_workitem_id_x() #0 !reqd_work_group_size !0 ; GFX908-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; GFX908-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; GFX908-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX908-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX908-NEXT: S_ENDPGM 0 call void @external_void_func_i32(i32 42) @@ -748,7 +748,7 @@ define amdgpu_kernel void @test_only_workitem_id_y() #0 !reqd_work_group_size !1 ; GFX900-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; GFX900-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; GFX900-NEXT: $vgpr31 = COPY [[OR]](s32) - ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX900-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX900-NEXT: S_ENDPGM 0 ; GFX908-LABEL: name: test_only_workitem_id_y @@ -791,7 +791,7 @@ define amdgpu_kernel void @test_only_workitem_id_y() #0 !reqd_work_group_size !1 ; GFX908-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; GFX908-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; GFX908-NEXT: $vgpr31 = COPY [[OR]](s32) - ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX908-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX908-NEXT: S_ENDPGM 0 call void @external_void_func_i32(i32 42) @@ -839,7 +839,7 @@ define amdgpu_kernel void @test_only_workitem_id_z() #0 !reqd_work_group_size !2 ; GFX900-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; GFX900-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; GFX900-NEXT: $vgpr31 = COPY [[OR]](s32) - ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX900-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX900-NEXT: S_ENDPGM 0 ; GFX908-LABEL: name: test_only_workitem_id_z @@ -882,7 +882,7 @@ define amdgpu_kernel void @test_only_workitem_id_z() #0 !reqd_work_group_size !2 ; GFX908-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; GFX908-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; GFX908-NEXT: $vgpr31 = COPY [[OR]](s32) - ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX908-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX908-NEXT: S_ENDPGM 0 call void @external_void_func_i32(i32 42) @@ -931,7 +931,7 @@ define amdgpu_kernel void @test_only_workitem_id_xy() #0 !reqd_work_group_size ! ; GFX900-NEXT: $sgpr13 = COPY [[COPY14]](s32) ; GFX900-NEXT: $sgpr14 = COPY [[COPY15]](s32) ; GFX900-NEXT: $vgpr31 = COPY [[OR]](s32) - ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX900-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX900-NEXT: S_ENDPGM 0 ; GFX908-LABEL: name: test_only_workitem_id_xy @@ -975,7 +975,7 @@ define amdgpu_kernel void @test_only_workitem_id_xy() #0 !reqd_work_group_size ! ; GFX908-NEXT: $sgpr13 = COPY [[COPY14]](s32) ; GFX908-NEXT: $sgpr14 = COPY [[COPY15]](s32) ; GFX908-NEXT: $vgpr31 = COPY [[OR]](s32) - ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX908-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX908-NEXT: S_ENDPGM 0 call void @external_void_func_i32(i32 42) @@ -1028,7 +1028,7 @@ define amdgpu_kernel void @test_only_workitem_id_yz() #0 !reqd_work_group_size ! ; GFX900-NEXT: $sgpr13 = COPY [[COPY14]](s32) ; GFX900-NEXT: $sgpr14 = COPY [[COPY15]](s32) ; GFX900-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX900-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX900-NEXT: S_ENDPGM 0 ; GFX908-LABEL: name: test_only_workitem_id_yz @@ -1076,7 +1076,7 @@ define amdgpu_kernel void @test_only_workitem_id_yz() #0 !reqd_work_group_size ! ; GFX908-NEXT: $sgpr13 = COPY [[COPY14]](s32) ; GFX908-NEXT: $sgpr14 = COPY [[COPY15]](s32) ; GFX908-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX908-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX908-NEXT: S_ENDPGM 0 call void @external_void_func_i32(i32 42) @@ -1125,7 +1125,7 @@ define amdgpu_kernel void @test_only_workitem_id_xz() #0 !reqd_work_group_size ! ; GFX900-NEXT: $sgpr13 = COPY [[COPY14]](s32) ; GFX900-NEXT: $sgpr14 = COPY [[COPY15]](s32) ; GFX900-NEXT: $vgpr31 = COPY [[OR]](s32) - ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX900-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX900-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX900-NEXT: S_ENDPGM 0 ; GFX908-LABEL: name: test_only_workitem_id_xz @@ -1169,7 +1169,7 @@ define amdgpu_kernel void @test_only_workitem_id_xz() #0 !reqd_work_group_size ! ; GFX908-NEXT: $sgpr13 = COPY [[COPY14]](s32) ; GFX908-NEXT: $sgpr14 = COPY [[COPY15]](s32) ; GFX908-NEXT: $vgpr31 = COPY [[OR]](s32) - ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GFX908-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GFX908-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GFX908-NEXT: S_ENDPGM 0 call void @external_void_func_i32(i32 42) diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-return-values.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-return-values.ll index cdc7568..346f427 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-return-values.ll +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-return-values.ll @@ -116,7 +116,7 @@ define amdgpu_kernel void @test_call_external_i32_func_i32_imm(i32 addrspace(1)* ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i32_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i32_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GCN-NEXT: G_STORE [[COPY21]](s32), [[LOAD]](p1) :: (volatile store (s32) into %ir.out.load, addrspace 1) @@ -196,7 +196,7 @@ define amdgpu_kernel void @test_call_external_i1_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i1_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i1_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[TRUNC:%[0-9]+]]:_(s1) = G_TRUNC [[COPY21]](s32) ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc @@ -272,7 +272,7 @@ define amdgpu_kernel void @test_call_external_i1_zeroext_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i1_zeroext_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i1_zeroext_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[TRUNC:%[0-9]+]]:_(s1) = G_TRUNC [[COPY21]](s32) ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc @@ -331,7 +331,7 @@ define amdgpu_kernel void @test_call_external_i1_signext_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i1_signext_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i1_signext_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[TRUNC:%[0-9]+]]:_(s1) = G_TRUNC [[COPY21]](s32) ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc @@ -390,7 +390,7 @@ define amdgpu_kernel void @test_call_external_i8_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i8_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i8_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY21]](s32) ; GCN-NEXT: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[TRUNC]](s16) @@ -468,7 +468,7 @@ define amdgpu_kernel void @test_call_external_i8_zeroext_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i8_zeroext_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i8_zeroext_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY21]](s32) ; GCN-NEXT: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[TRUNC]](s16) @@ -528,7 +528,7 @@ define amdgpu_kernel void @test_call_external_i8_signext_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i8_signext_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i8_signext_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY21]](s32) ; GCN-NEXT: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[TRUNC]](s16) @@ -588,7 +588,7 @@ define amdgpu_kernel void @test_call_external_i16_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i16_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i16_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY21]](s32) ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc @@ -645,7 +645,7 @@ define amdgpu_kernel void @test_call_external_i16_zeroext_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i16_zeroext_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i16_zeroext_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY21]](s32) ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc @@ -704,7 +704,7 @@ define amdgpu_kernel void @test_call_external_i16_signext_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i16_signext_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i16_signext_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY21]](s32) ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc @@ -763,7 +763,7 @@ define amdgpu_kernel void @test_call_external_i32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i32_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i32_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GCN-NEXT: G_STORE [[COPY21]](s32), [[DEF]](p1) :: (volatile store (s32) into `i32 addrspace(1)* undef`, addrspace 1) @@ -837,7 +837,7 @@ define amdgpu_kernel void @test_call_external_i48_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i48_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i48_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY21]](s32), [[COPY22]](s32) @@ -896,7 +896,7 @@ define amdgpu_kernel void @test_call_external_i48_zeroext_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i48_zeroext_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i48_zeroext_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY21]](s32), [[COPY22]](s32) @@ -957,7 +957,7 @@ define amdgpu_kernel void @test_call_external_i48_signext_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i48_signext_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i48_signext_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY21]](s32), [[COPY22]](s32) @@ -1018,7 +1018,7 @@ define amdgpu_kernel void @test_call_external_i64_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i64_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i64_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY21]](s32), [[COPY22]](s32) @@ -1076,7 +1076,7 @@ define amdgpu_kernel void @test_call_external_p1_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_p1_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_p1_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY21]](s32), [[COPY22]](s32) @@ -1134,7 +1134,7 @@ define amdgpu_kernel void @test_call_external_v2p1_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v2p1_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v2p1_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[COPY23:%[0-9]+]]:_(s32) = COPY $vgpr2 @@ -1196,7 +1196,7 @@ define amdgpu_kernel void @test_call_external_p3_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_p3_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_p3_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(p3) = COPY $vgpr0 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GCN-NEXT: G_STORE [[COPY21]](p3), [[DEF]](p3) :: (volatile store (p3) into `i8 addrspace(3)* addrspace(3)* undef`, addrspace 3) @@ -1252,7 +1252,7 @@ define amdgpu_kernel void @test_call_external_v2p3_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v2p3_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v2p3_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(p3) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(p3) = COPY $vgpr1 ; GCN-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x p3>) = G_BUILD_VECTOR [[COPY21]](p3), [[COPY22]](p3) @@ -1310,7 +1310,7 @@ define amdgpu_kernel void @test_call_external_f16_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_f16_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_f16_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY21]](s32) ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc @@ -1367,7 +1367,7 @@ define amdgpu_kernel void @test_call_external_f32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_f32_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_f32_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GCN-NEXT: G_STORE [[COPY21]](s32), [[DEF]](p1) :: (volatile store (s32) into `float addrspace(1)* undef`, addrspace 1) @@ -1423,7 +1423,7 @@ define amdgpu_kernel void @test_call_external_f64_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_f64_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_f64_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[COPY21]](s32), [[COPY22]](s32) @@ -1481,7 +1481,7 @@ define amdgpu_kernel void @test_call_external_v2f64_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v2f64_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v2f64_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[COPY23:%[0-9]+]]:_(s32) = COPY $vgpr2 @@ -1543,7 +1543,7 @@ define amdgpu_kernel void @test_call_external_v2i32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v2i32_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v2i32_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[COPY21]](s32), [[COPY22]](s32) @@ -1601,7 +1601,7 @@ define amdgpu_kernel void @test_call_external_v3i32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v3i32_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v3i32_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[COPY23:%[0-9]+]]:_(s32) = COPY $vgpr2 @@ -1660,7 +1660,7 @@ define amdgpu_kernel void @test_call_external_v4i32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v4i32_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v4i32_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[COPY23:%[0-9]+]]:_(s32) = COPY $vgpr2 @@ -1720,7 +1720,7 @@ define amdgpu_kernel void @test_call_external_v5i32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v5i32_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v5i32_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[COPY23:%[0-9]+]]:_(s32) = COPY $vgpr2 @@ -1781,7 +1781,7 @@ define amdgpu_kernel void @test_call_external_v8i32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v8i32_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4, implicit-def $vgpr5, implicit-def $vgpr6, implicit-def $vgpr7 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v8i32_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4, implicit-def $vgpr5, implicit-def $vgpr6, implicit-def $vgpr7 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[COPY23:%[0-9]+]]:_(s32) = COPY $vgpr2 @@ -1845,7 +1845,7 @@ define amdgpu_kernel void @test_call_external_v16i32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v16i32_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4, implicit-def $vgpr5, implicit-def $vgpr6, implicit-def $vgpr7, implicit-def $vgpr8, implicit-def $vgpr9, implicit-def $vgpr10, implicit-def $vgpr11, implicit-def $vgpr12, implicit-def $vgpr13, implicit-def $vgpr14, implicit-def $vgpr15 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v16i32_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4, implicit-def $vgpr5, implicit-def $vgpr6, implicit-def $vgpr7, implicit-def $vgpr8, implicit-def $vgpr9, implicit-def $vgpr10, implicit-def $vgpr11, implicit-def $vgpr12, implicit-def $vgpr13, implicit-def $vgpr14, implicit-def $vgpr15 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[COPY23:%[0-9]+]]:_(s32) = COPY $vgpr2 @@ -1917,7 +1917,7 @@ define amdgpu_kernel void @test_call_external_v32i32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v32i32_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4, implicit-def $vgpr5, implicit-def $vgpr6, implicit-def $vgpr7, implicit-def $vgpr8, implicit-def $vgpr9, implicit-def $vgpr10, implicit-def $vgpr11, implicit-def $vgpr12, implicit-def $vgpr13, implicit-def $vgpr14, implicit-def $vgpr15, implicit-def $vgpr16, implicit-def $vgpr17, implicit-def $vgpr18, implicit-def $vgpr19, implicit-def $vgpr20, implicit-def $vgpr21, implicit-def $vgpr22, implicit-def $vgpr23, implicit-def $vgpr24, implicit-def $vgpr25, implicit-def $vgpr26, implicit-def $vgpr27, implicit-def $vgpr28, implicit-def $vgpr29, implicit-def $vgpr30, implicit-def $vgpr31 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v32i32_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4, implicit-def $vgpr5, implicit-def $vgpr6, implicit-def $vgpr7, implicit-def $vgpr8, implicit-def $vgpr9, implicit-def $vgpr10, implicit-def $vgpr11, implicit-def $vgpr12, implicit-def $vgpr13, implicit-def $vgpr14, implicit-def $vgpr15, implicit-def $vgpr16, implicit-def $vgpr17, implicit-def $vgpr18, implicit-def $vgpr19, implicit-def $vgpr20, implicit-def $vgpr21, implicit-def $vgpr22, implicit-def $vgpr23, implicit-def $vgpr24, implicit-def $vgpr25, implicit-def $vgpr26, implicit-def $vgpr27, implicit-def $vgpr28, implicit-def $vgpr29, implicit-def $vgpr30, implicit-def $vgpr31 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[COPY23:%[0-9]+]]:_(s32) = COPY $vgpr2 @@ -2005,7 +2005,7 @@ define amdgpu_kernel void @test_call_external_v2i16_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v2i16_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v2i16_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GCN-NEXT: G_STORE [[COPY21]](<2 x s16>), [[DEF]](p1) :: (volatile store (<2 x s16>) into `<2 x i16> addrspace(1)* undef`, addrspace 1) @@ -2061,7 +2061,7 @@ define amdgpu_kernel void @test_call_external_v3i16_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v3i16_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v3i16_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1 ; GCN-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[COPY21]](<2 x s16>), [[COPY22]](<2 x s16>) @@ -2121,7 +2121,7 @@ define amdgpu_kernel void @test_call_external_v4i16_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v4i16_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v4i16_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1 ; GCN-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[COPY21]](<2 x s16>), [[COPY22]](<2 x s16>) @@ -2179,7 +2179,7 @@ define amdgpu_kernel void @test_call_external_v2f16_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v2f16_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v2f16_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GCN-NEXT: G_STORE [[COPY21]](<2 x s16>), [[DEF]](p1) :: (volatile store (<2 x s16>) into `<2 x half> addrspace(1)* undef`, addrspace 1) @@ -2235,7 +2235,7 @@ define amdgpu_kernel void @test_call_external_v3f16_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v3f16_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v3f16_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1 ; GCN-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[COPY21]](<2 x s16>), [[COPY22]](<2 x s16>) @@ -2295,7 +2295,7 @@ define amdgpu_kernel void @test_call_external_v4f16_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v4f16_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v4f16_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1 ; GCN-NEXT: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[COPY21]](<2 x s16>), [[COPY22]](<2 x s16>) @@ -2353,7 +2353,7 @@ define amdgpu_kernel void @test_call_external_v3f32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v3f32_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v3f32_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[COPY23:%[0-9]+]]:_(s32) = COPY $vgpr2 @@ -2412,7 +2412,7 @@ define amdgpu_kernel void @test_call_external_v5f32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v5f32_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v5f32_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[COPY23:%[0-9]+]]:_(s32) = COPY $vgpr2 @@ -2475,7 +2475,7 @@ define amdgpu_kernel void @test_call_external_i32_i64_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY16]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY17]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i32_i64_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i32_i64_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY23:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: [[COPY24:%[0-9]+]]:_(s32) = COPY $vgpr2 @@ -2564,7 +2564,7 @@ define amdgpu_kernel void @test_call_external_a2i32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_a2i32_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_a2i32_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[COPY22:%[0-9]+]]:_(s32) = COPY $vgpr1 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc @@ -2625,7 +2625,7 @@ define amdgpu_kernel void @test_call_external_a5i8_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_a5i8_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_a5i8_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $vgpr2, implicit-def $vgpr3, implicit-def $vgpr4 ; GCN-NEXT: [[COPY21:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY21]](s32) ; GCN-NEXT: [[TRUNC1:%[0-9]+]]:_(s8) = G_TRUNC [[TRUNC]](s16) @@ -2711,7 +2711,7 @@ define amdgpu_kernel void @test_call_external_v32i32_i32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY16]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY17]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v32i32_i32_func_void, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v32i32_i32_func_void, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GCN-NEXT: [[LOAD:%[0-9]+]]:_(<32 x s32>) = G_LOAD [[FRAME_INDEX]](p5) :: (load (<32 x s32>) from %stack.0, addrspace 5) ; GCN-NEXT: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 128 @@ -2777,7 +2777,7 @@ define amdgpu_kernel void @test_call_external_i32_v32i32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY16]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY17]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i32_v32i32_func_void, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_i32_v32i32_func_void, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GCN-NEXT: [[LOAD:%[0-9]+]]:_(s32) = G_LOAD [[FRAME_INDEX]](p5) :: (load (s32) from %stack.0, align 128, addrspace 5) ; GCN-NEXT: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 128 @@ -2842,7 +2842,7 @@ define amdgpu_kernel void @test_call_external_v33i32_func_void() #0 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v33i32_func_void, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v33i32_func_void, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GCN-NEXT: [[LOAD:%[0-9]+]]:_(<33 x s32>) = G_LOAD [[FRAME_INDEX]](p5) :: (load (<33 x s32>) from %stack.0, align 256, addrspace 5) ; GCN-NEXT: G_STORE [[LOAD]](<33 x s32>), [[DEF]](p1) :: (volatile store (<33 x s32>) into `<33 x i32> addrspace(1)* undef`, align 8, addrspace 1) @@ -2909,7 +2909,7 @@ define amdgpu_kernel void @test_call_external_v33i32_func_v33i32_i32(<33 x i32> ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v33i32_func_v33i32_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_v33i32_func_v33i32_i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GCN-NEXT: [[LOAD2:%[0-9]+]]:_(<33 x s32>) = G_LOAD [[FRAME_INDEX]](p5) :: (load (<33 x s32>) from %stack.0, align 256, addrspace 5) ; GCN-NEXT: G_STORE [[LOAD2]](<33 x s32>), [[DEF]](p1) :: (volatile store (<33 x s32>) into `<33 x i32> addrspace(1)* undef`, align 8, addrspace 1) diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-sret.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-sret.ll index 2b4bd48..f808695 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-sret.ll +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call-sret.ll @@ -65,7 +65,7 @@ define amdgpu_kernel void @test_call_external_void_func_sret_struct_i8_i32_byval ; GCN-NEXT: $sgpr13 = COPY [[COPY16]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY17]](s32) ; GCN-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_sret_struct_i8_i32_byval_struct_i8_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_sret_struct_i8_i32_byval_struct_i8_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 8, implicit-def $scc ; GCN-NEXT: [[PTR_ADD3:%[0-9]+]]:_(p5) = G_PTR_ADD [[FRAME_INDEX1]], [[C2]](s32) ; GCN-NEXT: [[LOAD:%[0-9]+]]:_(s8) = G_LOAD [[FRAME_INDEX1]](p5) :: (dereferenceable load (s8) from %ir.out.gep02, addrspace 5) diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call.ll index 8566590..9cfa25e 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call.ll +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-call.ll @@ -139,7 +139,7 @@ define amdgpu_kernel void @test_call_external_void_func_void() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_void() @@ -193,7 +193,7 @@ define void @test_func_call_external_void_func_void() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_void, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_void, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: SI_RETURN call void @external_void_func_void() @@ -247,7 +247,7 @@ define amdgpu_kernel void @test_call_external_void_func_empty_struct() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_empty_struct, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_empty_struct, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_empty_struct({} zeroinitializer, i32 23) @@ -301,7 +301,7 @@ define amdgpu_kernel void @test_call_external_void_func_empty_array() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_empty_array, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_empty_array, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_empty_array([0 x i8] zeroinitializer, i32 23) @@ -356,7 +356,7 @@ define amdgpu_kernel void @test_call_external_void_func_i1_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i1, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i1, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_i1(i1 true) @@ -413,7 +413,7 @@ define amdgpu_kernel void @test_call_external_void_func_i1_signext(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i1_signext, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i1_signext, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %var = load volatile i1, i1 addrspace(1)* undef @@ -471,7 +471,7 @@ define amdgpu_kernel void @test_call_external_void_func_i1_zeroext(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i1_zeroext, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i1_zeroext, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %var = load volatile i1, i1 addrspace(1)* undef @@ -529,7 +529,7 @@ define amdgpu_kernel void @test_call_external_void_func_i8_imm(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i8, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i8, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_i8(i8 123) @@ -587,7 +587,7 @@ define amdgpu_kernel void @test_call_external_void_func_i8_signext(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i8_signext, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i8_signext, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %var = load volatile i8, i8 addrspace(1)* undef @@ -646,7 +646,7 @@ define amdgpu_kernel void @test_call_external_void_func_i8_zeroext(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i8_zeroext, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i8_zeroext, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %var = load volatile i8, i8 addrspace(1)* undef @@ -702,7 +702,7 @@ define amdgpu_kernel void @test_call_external_void_func_i16_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i16, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i16, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_i16(i16 123) @@ -759,7 +759,7 @@ define amdgpu_kernel void @test_call_external_void_func_i16_signext(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i16_signext, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i16_signext, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %var = load volatile i16, i16 addrspace(1)* undef @@ -817,7 +817,7 @@ define amdgpu_kernel void @test_call_external_void_func_i16_zeroext(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i16_zeroext, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i16_zeroext, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %var = load volatile i16, i16 addrspace(1)* undef @@ -873,7 +873,7 @@ define amdgpu_kernel void @test_call_external_void_func_i32_imm(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_i32(i32 42) @@ -967,7 +967,7 @@ define amdgpu_kernel void @test_call_external_void_func_i64_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i64, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i64, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_i64(i64 123) @@ -1026,7 +1026,7 @@ define amdgpu_kernel void @test_call_external_void_func_v2i64() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2i64, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2i64, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <2 x i64>, <2 x i64> addrspace(1)* null @@ -1087,7 +1087,7 @@ define amdgpu_kernel void @test_call_external_void_func_v2i64_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2i64, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2i64, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v2i64(<2 x i64> ) @@ -1146,7 +1146,7 @@ define amdgpu_kernel void @test_call_external_void_func_i48(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i48, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i48, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %var = load volatile i48, i48 addrspace(1)* undef @@ -1206,7 +1206,7 @@ define amdgpu_kernel void @test_call_external_void_func_i48_signext(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i48_signext, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i48_signext, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %var = load volatile i48, i48 addrspace(1)* undef @@ -1266,7 +1266,7 @@ define amdgpu_kernel void @test_call_external_void_func_i48_zeroext(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i48_zeroext, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_i48_zeroext, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %var = load volatile i48, i48 addrspace(1)* undef @@ -1324,7 +1324,7 @@ define amdgpu_kernel void @test_call_external_void_func_p0_imm(i8* %arg) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_p0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_p0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_p0(i8* %arg) @@ -1383,7 +1383,7 @@ define amdgpu_kernel void @test_call_external_void_func_v2p0() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2p0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2p0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <2 x i8*>, <2 x i8*> addrspace(1)* null @@ -1449,7 +1449,7 @@ define amdgpu_kernel void @test_call_external_void_func_v3i64() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3i64, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3i64, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %load = load <2 x i64>, <2 x i64> addrspace(1)* null @@ -1519,7 +1519,7 @@ define amdgpu_kernel void @test_call_external_void_func_v4i64() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v4i64, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v4i64, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %load = load <2 x i64>, <2 x i64> addrspace(1)* null @@ -1576,7 +1576,7 @@ define amdgpu_kernel void @test_call_external_void_func_f16_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_f16, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_f16, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_f16(half 4.0) @@ -1630,7 +1630,7 @@ define amdgpu_kernel void @test_call_external_void_func_f32_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_f32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_f32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_f32(float 4.0) @@ -1688,7 +1688,7 @@ define amdgpu_kernel void @test_call_external_void_func_v2f32_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2f32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2f32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v2f32(<2 x float> ) @@ -1748,7 +1748,7 @@ define amdgpu_kernel void @test_call_external_void_func_v3f32_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3f32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3f32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v3f32(<3 x float> ) @@ -1812,7 +1812,7 @@ define amdgpu_kernel void @test_call_external_void_func_v5f32_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v5f32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v5f32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v5f32(<5 x float> ) @@ -1868,7 +1868,7 @@ define amdgpu_kernel void @test_call_external_void_func_f64_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_f64, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_f64, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_f64(double 4.0) @@ -1928,7 +1928,7 @@ define amdgpu_kernel void @test_call_external_void_func_v2f64_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2f64, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2f64, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v2f64(<2 x double> ) @@ -1991,7 +1991,7 @@ define amdgpu_kernel void @test_call_external_void_func_v3f64_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3f64, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3f64, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v3f64(<3 x double> ) @@ -2046,7 +2046,7 @@ define amdgpu_kernel void @test_call_external_void_func_v2i16() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2i16, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2i16, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <2 x i16>, <2 x i16> addrspace(1)* undef @@ -2107,7 +2107,7 @@ define amdgpu_kernel void @test_call_external_void_func_v3i16() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3i16, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3i16, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <3 x i16>, <3 x i16> addrspace(1)* undef @@ -2168,7 +2168,7 @@ define amdgpu_kernel void @test_call_external_void_func_v3f16() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3f16, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3f16, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <3 x half>, <3 x half> addrspace(1)* undef @@ -2226,7 +2226,7 @@ define amdgpu_kernel void @test_call_external_void_func_v4i16() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v4i16, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v4i16, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <4 x i16>, <4 x i16> addrspace(1)* undef @@ -2287,7 +2287,7 @@ define amdgpu_kernel void @test_call_external_void_func_v4i16_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v4i16, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v4i16, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v4i16(<4 x i16> ) @@ -2348,7 +2348,7 @@ define amdgpu_kernel void @test_call_external_void_func_v5i16() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v5i16, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v5i16, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <5 x i16>, <5 x i16> addrspace(1)* undef @@ -2411,7 +2411,7 @@ define amdgpu_kernel void @test_call_external_void_func_v7i16() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v7i16, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v7i16, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <7 x i16>, <7 x i16> addrspace(1)* undef @@ -2505,7 +2505,7 @@ define amdgpu_kernel void @test_call_external_void_func_v63i16() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v63i16, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v63i16, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 4, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <63 x i16>, <63 x i16> addrspace(1)* undef @@ -2602,7 +2602,7 @@ define amdgpu_kernel void @test_call_external_void_func_v65i16() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v65i16, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v65i16, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 8, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <65 x i16>, <65 x i16> addrspace(1)* undef @@ -2696,7 +2696,7 @@ define amdgpu_kernel void @test_call_external_void_func_v66i16() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v66i16, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v66i16, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 8, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <66 x i16>, <66 x i16> addrspace(1)* undef @@ -2752,7 +2752,7 @@ define amdgpu_kernel void @test_call_external_void_func_v2f16() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2f16, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2f16, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <2 x half>, <2 x half> addrspace(1)* undef @@ -2810,7 +2810,7 @@ define amdgpu_kernel void @test_call_external_void_func_v2i32() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <2 x i32>, <2 x i32> addrspace(1)* undef @@ -2869,7 +2869,7 @@ define amdgpu_kernel void @test_call_external_void_func_v2i32_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v2i32(<2 x i32> ) @@ -2930,7 +2930,7 @@ define amdgpu_kernel void @test_call_external_void_func_v3i32_imm(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v3i32(<3 x i32> ) @@ -2993,7 +2993,7 @@ define amdgpu_kernel void @test_call_external_void_func_v3i32_i32(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3i32_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3i32_i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v3i32_i32(<3 x i32> , i32 6) @@ -3052,7 +3052,7 @@ define amdgpu_kernel void @test_call_external_void_func_v4i32() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v4i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v4i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = load <4 x i32>, <4 x i32> addrspace(1)* undef @@ -3115,7 +3115,7 @@ define amdgpu_kernel void @test_call_external_void_func_v4i32_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v4i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v4i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v4i32(<4 x i32> ) @@ -3179,7 +3179,7 @@ define amdgpu_kernel void @test_call_external_void_func_v5i32_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v5i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v5i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v5i32(<5 x i32> ) @@ -3243,7 +3243,7 @@ define amdgpu_kernel void @test_call_external_void_func_v8i32() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v8i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v8i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %ptr = load <8 x i32> addrspace(1)*, <8 x i32> addrspace(1)* addrspace(4)* undef @@ -3315,7 +3315,7 @@ define amdgpu_kernel void @test_call_external_void_func_v8i32_imm() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v8i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v8i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void @external_void_func_v8i32(<8 x i32> ) @@ -3387,7 +3387,7 @@ define amdgpu_kernel void @test_call_external_void_func_v16i32() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v16i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v16i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %ptr = load <16 x i32> addrspace(1)*, <16 x i32> addrspace(1)* addrspace(4)* undef @@ -3480,7 +3480,7 @@ define amdgpu_kernel void @test_call_external_void_func_v32i32() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 4, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %ptr = load <32 x i32> addrspace(1)*, <32 x i32> addrspace(1)* addrspace(4)* undef @@ -3579,7 +3579,7 @@ define amdgpu_kernel void @test_call_external_void_func_v32i32_i32(i32) #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32_i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 8, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %ptr0 = load <32 x i32> addrspace(1)*, <32 x i32> addrspace(1)* addrspace(4)* undef @@ -3688,7 +3688,7 @@ define amdgpu_kernel void @test_call_external_void_func_v32i32_i8_i8_i16() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY16]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY17]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32_i8_i8_i16, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32_i8_i8_i16, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 16, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %ptr0 = load <32 x i32> addrspace(1)*, <32 x i32> addrspace(1)* addrspace(4)* undef @@ -3794,7 +3794,7 @@ define amdgpu_kernel void @test_call_external_void_func_v32i32_p3_p5() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY16]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY17]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32_p3_p5, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v32i32_p3_p5, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 12, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %ptr0 = load <32 x i32> addrspace(1)*, <32 x i32> addrspace(1)* addrspace(4)* undef @@ -3860,7 +3860,7 @@ define amdgpu_kernel void @test_call_external_void_func_struct_i8_i32() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_struct_i8_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_struct_i8_i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %ptr0 = load { i8, i32 } addrspace(1)*, { i8, i32 } addrspace(1)* addrspace(4)* undef @@ -3978,7 +3978,7 @@ define amdgpu_kernel void @test_call_external_void_func_byval_struct_i8_i32() #0 ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_byval_struct_i8_i32, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_byval_struct_i8_i32, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 8, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %val = alloca { i8, i32 }, align 4, addrspace(5) @@ -4038,7 +4038,7 @@ define void @call_byval_3ai32_byval_i8_align32([3 x i32] addrspace(5)* %incoming ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY17]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @void_func_byval_a3i32_byval_i8_align32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @void_func_byval_a3i32_byval_i8_align32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 36, implicit-def $scc ; CHECK-NEXT: SI_RETURN call void @void_func_byval_a3i32_byval_i8_align32([3 x i32] addrspace(5)* byval([3 x i32]) %incoming0, i8 addrspace(5)* align 32 %incoming1, i32 999) @@ -4088,7 +4088,7 @@ define void @call_byval_a4i64_align4_higher_source_align([4 x i64] addrspace(5)* ; CHECK-NEXT: $sgpr13 = COPY [[COPY14]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY15]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY16]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @void_func_byval_a4i64_align4, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @void_func_byval_a4i64_align4, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 32, implicit-def $scc ; CHECK-NEXT: SI_RETURN call void @void_func_byval_a4i64_align4([4 x i64] addrspace(5)* byval([4 x i64]) align 4 %incoming_high_align) @@ -4150,7 +4150,7 @@ define amdgpu_kernel void @test_call_external_void_func_v2i8() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2i8, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v2i8, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %ptr = load <2 x i8> addrspace(1)*, <2 x i8> addrspace(1)* addrspace(4)* undef @@ -4217,7 +4217,7 @@ define amdgpu_kernel void @test_call_external_void_func_v3i8() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3i8, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v3i8, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %ptr = load <3 x i8> addrspace(1)*, <3 x i8> addrspace(1)* addrspace(4)* undef @@ -4287,7 +4287,7 @@ define amdgpu_kernel void @test_call_external_void_func_v4i8() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v4i8, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v4i8, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %ptr = load <4 x i8> addrspace(1)*, <4 x i8> addrspace(1)* addrspace(4)* undef @@ -4369,7 +4369,7 @@ define amdgpu_kernel void @test_call_external_void_func_v8i8() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v8i8, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v8i8, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %ptr = load <8 x i8> addrspace(1)*, <8 x i8> addrspace(1)* addrspace(4)* undef @@ -4475,7 +4475,7 @@ define amdgpu_kernel void @test_call_external_void_func_v16i8() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v16i8, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_v16i8, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 %ptr = load <16 x i8> addrspace(1)*, <16 x i8> addrspace(1)* addrspace(4)* undef @@ -4577,7 +4577,7 @@ define amdgpu_kernel void @stack_passed_arg_alignment_v32i32_f64(<32 x i32> %val ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @stack_passed_f64_arg, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @stack_passed_f64_arg, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 12, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 entry: @@ -4705,7 +4705,7 @@ define void @stack_12xv3i32() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_12xv3i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_12xv3i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 20, implicit-def $scc ; CHECK-NEXT: SI_RETURN entry: @@ -4845,7 +4845,7 @@ define void @stack_12xv3f32() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_12xv3f32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_12xv3f32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 20, implicit-def $scc ; CHECK-NEXT: SI_RETURN entry: @@ -4989,7 +4989,7 @@ define void @stack_8xv5i32() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_8xv5i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_8xv5i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 36, implicit-def $scc ; CHECK-NEXT: SI_RETURN entry: @@ -5129,7 +5129,7 @@ define void @stack_8xv5f32() #0 { ; CHECK-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_8xv5f32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @external_void_func_8xv5f32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 36, implicit-def $scc ; CHECK-NEXT: SI_RETURN entry: @@ -5170,7 +5170,7 @@ define amdgpu_ps void @amdgpu_ps_call_default_cc() { ; CHECK-NEXT: $sgpr13 = COPY [[COPY2]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY3]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY4]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[C]](p0), 0, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[C]](p0), 0, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 main_body: diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-indirect-call.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-indirect-call.ll index f038325..a957ade 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-indirect-call.ll +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-indirect-call.ll @@ -47,7 +47,7 @@ define amdgpu_kernel void @test_indirect_call_sgpr_ptr(void()* %fptr) { ; CHECK-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[OR1]](s32) - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[LOAD]](p0), 0, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[LOAD]](p0), 0, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_ENDPGM 0 call void %fptr() diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-sibling-call.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-sibling-call.ll index b65d584..1be7d37 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-sibling-call.ll +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-sibling-call.ll @@ -51,7 +51,7 @@ define hidden fastcc i32 @sibling_call_i32_fastcc_i32_i32(i32 %a, i32 %b, i32 %c ; GCN-NEXT: $vgpr1 = COPY [[COPY1]](s32) ; GCN-NEXT: [[COPY3:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY3]](<4 x s32>) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3 entry: %ret = tail call fastcc i32 @i32_fastcc_i32_i32(i32 %a, i32 %b) ret i32 %ret @@ -75,7 +75,7 @@ define fastcc i32 @sibling_call_i32_fastcc_i32_i32_stack_object(i32 %a, i32 %b, ; GCN-NEXT: $vgpr1 = COPY [[COPY1]](s32) ; GCN-NEXT: [[COPY3:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY3]](<4 x s32>) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3 entry: %alloca = alloca [16 x i32], align 4, addrspace(5) %gep = getelementptr inbounds [16 x i32], [16 x i32] addrspace(5)* %alloca, i32 0, i32 5 @@ -102,7 +102,7 @@ define fastcc i32 @sibling_call_i32_fastcc_i32_i32_callee_stack_object(i32 %a, i ; GCN-NEXT: $vgpr1 = COPY [[COPY1]](s32) ; GCN-NEXT: [[COPY3:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY3]](<4 x s32>) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32_stack_object, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32_stack_object, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3 entry: %alloca = alloca [16 x i32], align 4, addrspace(5) %gep = getelementptr inbounds [16 x i32], [16 x i32] addrspace(5)* %alloca, i32 0, i32 5 @@ -124,7 +124,7 @@ define fastcc void @sibling_call_i32_fastcc_i32_i32_unused_result(i32 %a, i32 %b ; GCN-NEXT: $vgpr1 = COPY [[COPY1]](s32) ; GCN-NEXT: [[COPY3:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY3]](<4 x s32>) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3 entry: %ret = tail call fastcc i32 @i32_fastcc_i32_i32(i32 %a, i32 %b) ret void @@ -151,7 +151,7 @@ define amdgpu_kernel void @kernel_call_i32_fastcc_i32_i32_unused_result(i32 %a, ; GCN-NEXT: $vgpr1 = COPY [[EVEC1]](s32) ; GCN-NEXT: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $private_rsrc_reg ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY1]](<4 x s32>) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @i32_fastcc_i32_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @i32_fastcc_i32_i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def $vgpr0 ; GCN-NEXT: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GCN-NEXT: S_ENDPGM 0 @@ -197,7 +197,7 @@ define fastcc i32 @sibling_call_i32_fastcc_i32_byval_i32_byval_parent(i32 %a, i3 ; GCN-NEXT: $vgpr0 = COPY [[COPY]](s32) ; GCN-NEXT: [[COPY3:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY3]](<4 x s32>) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @i32_fastcc_i32_byval_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @i32_fastcc_i32_byval_i32, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def $vgpr0 ; GCN-NEXT: [[COPY4:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 4, implicit-def $scc ; GCN-NEXT: $vgpr0 = COPY [[COPY4]](s32) @@ -259,7 +259,7 @@ define fastcc i32 @sibling_call_i32_fastcc_i32_byval_i32(i32 %a, [32 x i32] %lar ; GCN-NEXT: $vgpr0 = COPY [[COPY]](s32) ; GCN-NEXT: [[COPY31:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY31]](<4 x s32>) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_byval_i32, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_byval_i32, 0, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3 entry: %ret = tail call fastcc i32 @i32_fastcc_i32_byval_i32(i32 %a, i32 addrspace(5)* byval(i32) inttoptr (i32 16 to i32 addrspace(5)*)) ret i32 %ret @@ -402,7 +402,7 @@ define fastcc i32 @sibling_call_i32_fastcc_i32_i32_a32i32(i32 %a, i32 %b, [32 x ; GCN-NEXT: $vgpr30 = COPY [[COPY30]](s32) ; GCN-NEXT: [[COPY31:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY31]](<4 x s32>) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32_a32i32, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32_a32i32, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3 entry: %ret = tail call fastcc i32 @i32_fastcc_i32_i32_a32i32(i32 %a, i32 %b, [32 x i32] %c) ret i32 %ret @@ -495,7 +495,7 @@ define fastcc i32 @sibling_call_i32_fastcc_i32_i32_a32i32_stack_object(i32 %a, i ; GCN-NEXT: $vgpr30 = COPY [[COPY30]](s32) ; GCN-NEXT: [[COPY31:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY31]](<4 x s32>) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32_a32i32, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32_a32i32, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3 entry: %alloca = alloca [16 x i32], align 4, addrspace(5) %gep = getelementptr inbounds [16 x i32], [16 x i32] addrspace(5)* %alloca, i32 0, i32 5 @@ -560,7 +560,7 @@ define fastcc i32 @no_sibling_call_callee_more_stack_space(i32 %a, i32 %b) #1 { ; GCN-NEXT: $vgpr30 = COPY [[C]](s32) ; GCN-NEXT: [[COPY2:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY2]](<4 x s32>) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @i32_fastcc_i32_i32_a32i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @i32_fastcc_i32_i32_a32i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def $vgpr0 ; GCN-NEXT: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 12, implicit-def $scc ; GCN-NEXT: $vgpr0 = COPY [[COPY3]](s32) @@ -585,7 +585,7 @@ define fastcc i32 @sibling_call_i32_fastcc_i32_i32_other_call(i32 %a, i32 %b, i3 ; GCN-NEXT: $vgpr1 = COPY [[COPY1]](s32) ; GCN-NEXT: [[COPY3:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY3]](<4 x s32>) - ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @i32_fastcc_i32_i32, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def $vgpr0 + ; GCN-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[GV]](p0), @i32_fastcc_i32_i32, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def $vgpr0 ; GCN-NEXT: [[COPY4:%[0-9]+]]:_(s32) = COPY $vgpr0 ; GCN-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; GCN-NEXT: [[GV1:%[0-9]+]]:sreg_64(p0) = G_GLOBAL_VALUE @sibling_call_i32_fastcc_i32_i32 @@ -594,7 +594,7 @@ define fastcc i32 @sibling_call_i32_fastcc_i32_i32_other_call(i32 %a, i32 %b, i3 ; GCN-NEXT: $vgpr2 = COPY [[COPY4]](s32) ; GCN-NEXT: [[COPY5:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY5]](<4 x s32>) - ; GCN-NEXT: SI_TCRETURN [[GV1]](p0), @sibling_call_i32_fastcc_i32_i32, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + ; GCN-NEXT: SI_TCRETURN [[GV1]](p0), @sibling_call_i32_fastcc_i32_i32, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $sgpr0_sgpr1_sgpr2_sgpr3 entry: %other.call = tail call fastcc i32 @i32_fastcc_i32_i32(i32 %a, i32 %b) %ret = tail call fastcc i32 @sibling_call_i32_fastcc_i32_i32(i32 %a, i32 %b, i32 %other.call) @@ -690,7 +690,7 @@ define fastcc i32 @sibling_call_stack_objecti32_fastcc_i32_i32_a32i32(i32 %a, i3 ; GCN-NEXT: $vgpr30 = COPY [[COPY30]](s32) ; GCN-NEXT: [[COPY31:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY31]](<4 x s32>) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32_a32i32, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32_a32i32, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3 entry: %alloca = alloca [16 x i32], align 4, addrspace(5) %gep = getelementptr inbounds [16 x i32], [16 x i32] addrspace(5)* %alloca, i32 0, i32 5 @@ -795,7 +795,7 @@ define fastcc i32 @sibling_call_stack_objecti32_fastcc_i32_i32_a32i32_larger_arg ; GCN-NEXT: $vgpr30 = COPY [[C1]](s32) ; GCN-NEXT: [[COPY31:%[0-9]+]]:_(<4 x s32>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 ; GCN-NEXT: $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY31]](<4 x s32>) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32_a32i32, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i32_fastcc_i32_i32_a32i32, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3 entry: %alloca = alloca [16 x i32], align 4, addrspace(5) %gep = getelementptr inbounds [16 x i32], [16 x i32] addrspace(5)* %alloca, i32 0, i32 5 @@ -958,7 +958,7 @@ define fastcc void @sibling_call_fastcc_multi_byval(i32 %a, [64 x i32]) #1 { ; GCN-NEXT: $sgpr13 = COPY [[COPY44]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY45]](s32) ; GCN-NEXT: $vgpr31 = COPY [[COPY46]](s32) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @void_fastcc_multi_byval, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @void_fastcc_multi_byval, 0, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 entry: %alloca0 = alloca [3 x i32], align 16, addrspace(5) %alloca1 = alloca [2 x i64], align 8, addrspace(5) @@ -1150,7 +1150,7 @@ define fastcc void @sibling_call_byval_and_stack_passed(i32 %stack.out.arg, [64 ; GCN-NEXT: $sgpr13 = COPY [[COPY44]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY45]](s32) ; GCN-NEXT: $vgpr31 = COPY [[COPY46]](s32) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @void_fastcc_byval_and_stack_passed, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @void_fastcc_byval_and_stack_passed, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $vgpr4, implicit $vgpr5, implicit $vgpr6, implicit $vgpr7, implicit $vgpr8, implicit $vgpr9, implicit $vgpr10, implicit $vgpr11, implicit $vgpr12, implicit $vgpr13, implicit $vgpr14, implicit $vgpr15, implicit $vgpr16, implicit $vgpr17, implicit $vgpr18, implicit $vgpr19, implicit $vgpr20, implicit $vgpr21, implicit $vgpr22, implicit $vgpr23, implicit $vgpr24, implicit $vgpr25, implicit $vgpr26, implicit $vgpr27, implicit $vgpr28, implicit $vgpr29, implicit $vgpr30, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 entry: %alloca = alloca [3 x i32], align 16, addrspace(5) store [3 x i32] [i32 9, i32 9, i32 9], [3 x i32] addrspace(5)* %alloca @@ -1198,7 +1198,7 @@ define hidden fastcc i64 @sibling_call_i64_fastcc_i64(i64 %a) #1 { ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[COPY17]](s32) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i64_fastcc_i64, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i64_fastcc_i64, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 entry: %ret = tail call fastcc i64 @i64_fastcc_i64(i64 %a) ret i64 %ret @@ -1244,7 +1244,7 @@ define hidden fastcc i8 addrspace(1)* @sibling_call_p1i8_fastcc_p1i8(i8 addrspac ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[COPY17]](s32) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @p1i8_fastcc_p1i8, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @p1i8_fastcc_p1i8, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 entry: %ret = tail call fastcc i8 addrspace(1)* @p1i8_fastcc_p1i8(i8 addrspace(1)* %a) ret i8 addrspace(1)* %ret @@ -1288,7 +1288,7 @@ define hidden fastcc i16 @sibling_call_i16_fastcc_i16(i16 %a) #1 { ; GCN-NEXT: $sgpr13 = COPY [[COPY14]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY15]](s32) ; GCN-NEXT: $vgpr31 = COPY [[COPY16]](s32) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i16_fastcc_i16, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @i16_fastcc_i16, 0, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 entry: %ret = tail call fastcc i16 @i16_fastcc_i16(i16 %a) ret i16 %ret @@ -1332,7 +1332,7 @@ define hidden fastcc half @sibling_call_f16_fastcc_f16(half %a) #1 { ; GCN-NEXT: $sgpr13 = COPY [[COPY14]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY15]](s32) ; GCN-NEXT: $vgpr31 = COPY [[COPY16]](s32) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @f16_fastcc_f16, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @f16_fastcc_f16, 0, csr_amdgpu, implicit $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 entry: %ret = tail call fastcc half @f16_fastcc_f16(half %a) ret half %ret @@ -1383,7 +1383,7 @@ define hidden fastcc <3 x i16> @sibling_call_v3i16_fastcc_v3i16(<3 x i16> %a) #1 ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[COPY17]](s32) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @v3i16_fastcc_v3i16, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @v3i16_fastcc_v3i16, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 entry: %ret = tail call fastcc <3 x i16> @v3i16_fastcc_v3i16(<3 x i16> %a) ret <3 x i16> %ret @@ -1429,7 +1429,7 @@ define hidden fastcc <4 x i16> @sibling_call_v4i16_fastcc_v4i16(<4 x i16> %a) #1 ; GCN-NEXT: $sgpr13 = COPY [[COPY15]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY16]](s32) ; GCN-NEXT: $vgpr31 = COPY [[COPY17]](s32) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @v4i16_fastcc_v4i16, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @v4i16_fastcc_v4i16, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 entry: %ret = tail call fastcc <4 x i16> @v4i16_fastcc_v4i16(<4 x i16> %a) ret <4 x i16> %ret @@ -1481,7 +1481,7 @@ define hidden fastcc <2 x i64> @sibling_call_v2i64_fastcc_v2i64(<2 x i64> %a) #1 ; GCN-NEXT: $sgpr13 = COPY [[COPY17]](s32) ; GCN-NEXT: $sgpr14 = COPY [[COPY18]](s32) ; GCN-NEXT: $vgpr31 = COPY [[COPY19]](s32) - ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @v2i64_fastcc_v2i64, 0, csr_amdgpu_highregs, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; GCN-NEXT: SI_TCRETURN [[GV]](p0), @v2i64_fastcc_v2i64, 0, csr_amdgpu, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit $vgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 entry: %ret = tail call fastcc <2 x i64> @v2i64_fastcc_v2i64(<2 x i64> %a) ret <2 x i64> %ret diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-tail-call.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-tail-call.ll index 87b53c6..12384542 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-tail-call.ll +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-tail-call.ll @@ -35,7 +35,7 @@ define void @tail_call_void_func_void() { ; CHECK-NEXT: $sgpr13 = COPY [[COPY13]](s32) ; CHECK-NEXT: $sgpr14 = COPY [[COPY14]](s32) ; CHECK-NEXT: $vgpr31 = COPY [[COPY15]](s32) - ; CHECK-NEXT: SI_TCRETURN [[GV]](p0), @external_void_func_void, 0, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 + ; CHECK-NEXT: SI_TCRETURN [[GV]](p0), @external_void_func_void, 0, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $vgpr31 tail call void @external_void_func_void() ret void } diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/localizer-wrong-insert-point.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/localizer-wrong-insert-point.mir index b186ce2..8622f9f 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/localizer-wrong-insert-point.mir +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/localizer-wrong-insert-point.mir @@ -16,7 +16,7 @@ body: | ; CHECK-NEXT: bb.1: ; CHECK-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc ; CHECK-NEXT: [[C1:%[0-9]+]]:_(p0) = G_CONSTANT i64 0 - ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[C1]](p0), 0, csr_amdgpu_highregs + ; CHECK-NEXT: $sgpr30_sgpr31 = G_SI_CALL [[C1]](p0), 0, csr_amdgpu ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc ; CHECK-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31 bb.0: @@ -25,7 +25,7 @@ body: | bb.1: ADJCALLSTACKUP 0, 0, implicit-def $scc - $sgpr30_sgpr31 = G_SI_CALL %0, 0, csr_amdgpu_highregs + $sgpr30_sgpr31 = G_SI_CALL %0, 0, csr_amdgpu ADJCALLSTACKDOWN 0, 0, implicit-def $scc S_SETPC_B64_return undef $sgpr30_sgpr31 diff --git a/llvm/test/CodeGen/AMDGPU/accvgpr-spill-scc-clobber.mir b/llvm/test/CodeGen/AMDGPU/accvgpr-spill-scc-clobber.mir index f92ad8c..fc63a80 100644 --- a/llvm/test/CodeGen/AMDGPU/accvgpr-spill-scc-clobber.mir +++ b/llvm/test/CodeGen/AMDGPU/accvgpr-spill-scc-clobber.mir @@ -36,7 +36,7 @@ body: | ; GFX908-NEXT: S_NOP 0 ; GFX908-NEXT: {{ $}} ; GFX908-NEXT: bb.2: - ; GFX908-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX908-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX90A-LABEL: name: agpr32_restore_clobber_scc ; GFX90A: bb.0: ; GFX90A-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -506,7 +506,7 @@ body: | ; GFX90A-NEXT: $agpr34 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec ; GFX90A-NEXT: $agpr33 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec ; GFX90A-NEXT: $agpr32 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec - ; GFX90A-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX90A-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX908-FLATSCR-LABEL: name: agpr32_restore_clobber_scc ; GFX908-FLATSCR: bb.0: ; GFX908-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -527,7 +527,7 @@ body: | ; GFX908-FLATSCR-NEXT: S_NOP 0 ; GFX908-FLATSCR-NEXT: {{ $}} ; GFX908-FLATSCR-NEXT: bb.2: - ; GFX908-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX908-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX90A-FLATSCR-LABEL: name: agpr32_restore_clobber_scc ; GFX90A-FLATSCR: bb.0: ; GFX90A-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -998,7 +998,7 @@ body: | ; GFX90A-FLATSCR-NEXT: $agpr34 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec ; GFX90A-FLATSCR-NEXT: $agpr33 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec ; GFX90A-FLATSCR-NEXT: $agpr32 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec - ; GFX90A-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX90A-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 @@ -1010,7 +1010,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- @@ -1048,7 +1048,7 @@ body: | ; GFX908-NEXT: S_NOP 0 ; GFX908-NEXT: {{ $}} ; GFX908-NEXT: bb.2: - ; GFX908-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX908-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX90A-LABEL: name: agpr64_restore_clobber_scc ; GFX90A: bb.0: ; GFX90A-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -1519,7 +1519,7 @@ body: | ; GFX90A-NEXT: $agpr34 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec ; GFX90A-NEXT: $agpr33 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec ; GFX90A-NEXT: $agpr32 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec - ; GFX90A-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX90A-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX908-FLATSCR-LABEL: name: agpr64_restore_clobber_scc ; GFX908-FLATSCR: bb.0: ; GFX908-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -1542,7 +1542,7 @@ body: | ; GFX908-FLATSCR-NEXT: S_NOP 0 ; GFX908-FLATSCR-NEXT: {{ $}} ; GFX908-FLATSCR-NEXT: bb.2: - ; GFX908-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX908-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX90A-FLATSCR-LABEL: name: agpr64_restore_clobber_scc ; GFX90A-FLATSCR: bb.0: ; GFX90A-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -2013,7 +2013,7 @@ body: | ; GFX90A-FLATSCR-NEXT: $agpr34 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec ; GFX90A-FLATSCR-NEXT: $agpr33 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec ; GFX90A-FLATSCR-NEXT: $agpr32 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec - ; GFX90A-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX90A-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 @@ -2025,7 +2025,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- @@ -2065,7 +2065,7 @@ body: | ; GFX908-NEXT: S_NOP 0 ; GFX908-NEXT: {{ $}} ; GFX908-NEXT: bb.2: - ; GFX908-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX908-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX90A-LABEL: name: agpr96_restore_clobber_scc ; GFX90A: bb.0: ; GFX90A-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -2537,7 +2537,7 @@ body: | ; GFX90A-NEXT: $agpr34 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec ; GFX90A-NEXT: $agpr33 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec ; GFX90A-NEXT: $agpr32 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec - ; GFX90A-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX90A-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX908-FLATSCR-LABEL: name: agpr96_restore_clobber_scc ; GFX908-FLATSCR: bb.0: ; GFX908-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -2562,7 +2562,7 @@ body: | ; GFX908-FLATSCR-NEXT: S_NOP 0 ; GFX908-FLATSCR-NEXT: {{ $}} ; GFX908-FLATSCR-NEXT: bb.2: - ; GFX908-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX908-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX90A-FLATSCR-LABEL: name: agpr96_restore_clobber_scc ; GFX90A-FLATSCR: bb.0: ; GFX90A-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -3033,7 +3033,7 @@ body: | ; GFX90A-FLATSCR-NEXT: $agpr34 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec ; GFX90A-FLATSCR-NEXT: $agpr33 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec ; GFX90A-FLATSCR-NEXT: $agpr32 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec - ; GFX90A-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX90A-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 @@ -3045,7 +3045,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- @@ -3081,7 +3081,7 @@ body: | ; GFX908-NEXT: S_NOP 0 ; GFX908-NEXT: {{ $}} ; GFX908-NEXT: bb.2: - ; GFX908-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX908-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX90A-LABEL: name: agpr32_save_clobber_scc ; GFX90A: bb.0: ; GFX90A-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -3551,7 +3551,7 @@ body: | ; GFX90A-NEXT: $agpr34 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec ; GFX90A-NEXT: $agpr33 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec ; GFX90A-NEXT: $agpr32 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec - ; GFX90A-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX90A-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX908-FLATSCR-LABEL: name: agpr32_save_clobber_scc ; GFX908-FLATSCR: bb.0: ; GFX908-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -3572,7 +3572,7 @@ body: | ; GFX908-FLATSCR-NEXT: S_NOP 0 ; GFX908-FLATSCR-NEXT: {{ $}} ; GFX908-FLATSCR-NEXT: bb.2: - ; GFX908-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX908-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX90A-FLATSCR-LABEL: name: agpr32_save_clobber_scc ; GFX90A-FLATSCR: bb.0: ; GFX90A-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -4043,7 +4043,7 @@ body: | ; GFX90A-FLATSCR-NEXT: $agpr34 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec ; GFX90A-FLATSCR-NEXT: $agpr33 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec ; GFX90A-FLATSCR-NEXT: $agpr32 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec - ; GFX90A-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX90A-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255, $agpr0 @@ -4055,7 +4055,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- @@ -4092,7 +4092,7 @@ body: | ; GFX908-NEXT: S_NOP 0 ; GFX908-NEXT: {{ $}} ; GFX908-NEXT: bb.2: - ; GFX908-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX908-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX90A-LABEL: name: agpr64_save_clobber_scc ; GFX90A: bb.0: ; GFX90A-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -4563,7 +4563,7 @@ body: | ; GFX90A-NEXT: $agpr34 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec ; GFX90A-NEXT: $agpr33 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec ; GFX90A-NEXT: $agpr32 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec - ; GFX90A-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX90A-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX908-FLATSCR-LABEL: name: agpr64_save_clobber_scc ; GFX908-FLATSCR: bb.0: ; GFX908-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -4586,7 +4586,7 @@ body: | ; GFX908-FLATSCR-NEXT: S_NOP 0 ; GFX908-FLATSCR-NEXT: {{ $}} ; GFX908-FLATSCR-NEXT: bb.2: - ; GFX908-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX908-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX90A-FLATSCR-LABEL: name: agpr64_save_clobber_scc ; GFX90A-FLATSCR: bb.0: ; GFX90A-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -5057,7 +5057,7 @@ body: | ; GFX90A-FLATSCR-NEXT: $agpr34 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec ; GFX90A-FLATSCR-NEXT: $agpr33 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec ; GFX90A-FLATSCR-NEXT: $agpr32 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec - ; GFX90A-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX90A-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255, $agpr0_agpr1 @@ -5069,7 +5069,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- name: agpr96_save_clobber_scc @@ -5107,7 +5107,7 @@ body: | ; GFX908-NEXT: S_NOP 0 ; GFX908-NEXT: {{ $}} ; GFX908-NEXT: bb.2: - ; GFX908-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX908-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX90A-LABEL: name: agpr96_save_clobber_scc ; GFX90A: bb.0: ; GFX90A-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -5579,7 +5579,7 @@ body: | ; GFX90A-NEXT: $agpr34 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec ; GFX90A-NEXT: $agpr33 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec ; GFX90A-NEXT: $agpr32 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec - ; GFX90A-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX90A-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX908-FLATSCR-LABEL: name: agpr96_save_clobber_scc ; GFX908-FLATSCR: bb.0: ; GFX908-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -5604,7 +5604,7 @@ body: | ; GFX908-FLATSCR-NEXT: S_NOP 0 ; GFX908-FLATSCR-NEXT: {{ $}} ; GFX908-FLATSCR-NEXT: bb.2: - ; GFX908-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX908-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX90A-FLATSCR-LABEL: name: agpr96_save_clobber_scc ; GFX90A-FLATSCR: bb.0: ; GFX90A-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -6075,7 +6075,7 @@ body: | ; GFX90A-FLATSCR-NEXT: $agpr34 = V_ACCVGPR_WRITE_B32_e64 $vgpr2, implicit $exec ; GFX90A-FLATSCR-NEXT: $agpr33 = V_ACCVGPR_WRITE_B32_e64 $vgpr1, implicit $exec ; GFX90A-FLATSCR-NEXT: $agpr32 = V_ACCVGPR_WRITE_B32_e64 $vgpr0, implicit $exec - ; GFX90A-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX90A-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255, $agpr0_agpr1 @@ -6087,5 +6087,5 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... diff --git a/llvm/test/CodeGen/AMDGPU/agpr-copy-no-vgprs.mir b/llvm/test/CodeGen/AMDGPU/agpr-copy-no-vgprs.mir index 7dc888f..c5cac8f 100644 --- a/llvm/test/CodeGen/AMDGPU/agpr-copy-no-vgprs.mir +++ b/llvm/test/CodeGen/AMDGPU/agpr-copy-no-vgprs.mir @@ -14,14 +14,14 @@ body: | ; GFX908-NEXT: {{ $}} ; GFX908-NEXT: $vgpr63 = V_ACCVGPR_READ_B32_e64 $agpr0, implicit $exec ; GFX908-NEXT: $agpr1 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr63, implicit $exec - ; GFX908-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $agpr1 + ; GFX908-NEXT: S_ENDPGM 0, amdgpu_allvgprs, implicit $agpr1 ; GFX90A-LABEL: name: no_free_vgprs_for_copy_a32_to_a32 ; GFX90A: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253, $vgpr254, $vgpr255, $agpr0 ; GFX90A-NEXT: {{ $}} ; GFX90A-NEXT: $agpr1 = V_ACCVGPR_MOV_B32 $agpr0, implicit $exec - ; GFX90A-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $agpr1 + ; GFX90A-NEXT: S_ENDPGM 0, amdgpu_allvgprs, implicit $agpr1 $agpr1 = COPY $agpr0 - S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $agpr1 + S_ENDPGM 0, amdgpu_allvgprs, implicit $agpr1 ... --- name: no_free_vgprs_for_copy_a64_to_a64 @@ -37,13 +37,13 @@ body: | ; GFX908-NEXT: $agpr3 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr63, implicit $exec, implicit-def $agpr2_agpr3 ; GFX908-NEXT: $vgpr63 = V_ACCVGPR_READ_B32_e64 $agpr0, implicit $exec, implicit $agpr0_agpr1 ; GFX908-NEXT: $agpr2 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr63, implicit $exec - ; GFX908-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $agpr2_agpr3 + ; GFX908-NEXT: S_ENDPGM 0, amdgpu_allvgprs, implicit $agpr2_agpr3 ; GFX90A-LABEL: name: no_free_vgprs_for_copy_a64_to_a64 ; GFX90A: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253, $vgpr254, $vgpr255, $agpr0_agpr1 ; GFX90A-NEXT: {{ $}} ; GFX90A-NEXT: $agpr3 = V_ACCVGPR_MOV_B32 $agpr1, implicit $exec, implicit-def $agpr2_agpr3, implicit $agpr0_agpr1 ; GFX90A-NEXT: $agpr2 = V_ACCVGPR_MOV_B32 $agpr0, implicit $exec, implicit $agpr0_agpr1 - ; GFX90A-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $agpr2_agpr3 + ; GFX90A-NEXT: S_ENDPGM 0, amdgpu_allvgprs, implicit $agpr2_agpr3 $agpr2_agpr3 = COPY $agpr0_agpr1 - S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $agpr2_agpr3 + S_ENDPGM 0, amdgpu_allvgprs, implicit $agpr2_agpr3 ... diff --git a/llvm/test/CodeGen/AMDGPU/agpr-copy-sgpr-no-vgprs.mir b/llvm/test/CodeGen/AMDGPU/agpr-copy-sgpr-no-vgprs.mir index 4e32833..bcfbe44 100644 --- a/llvm/test/CodeGen/AMDGPU/agpr-copy-sgpr-no-vgprs.mir +++ b/llvm/test/CodeGen/AMDGPU/agpr-copy-sgpr-no-vgprs.mir @@ -14,14 +14,14 @@ body: | ; GFX908-NEXT: {{ $}} ; GFX908-NEXT: $vgpr63 = V_MOV_B32_e32 $sgpr8, implicit $exec ; GFX908-NEXT: $agpr1 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr63, implicit $exec - ; GFX908-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $agpr1 + ; GFX908-NEXT: S_ENDPGM 0, amdgpu_allvgprs, implicit $agpr1 ; GFX90A-LABEL: name: no_free_vgprs_for_copy_s32_to_a32 ; GFX90A: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253, $vgpr254, $vgpr255, $sgpr8 ; GFX90A-NEXT: {{ $}} ; GFX90A-NEXT: $agpr1 = V_ACCVGPR_WRITE_B32_e64 $sgpr8, implicit $exec - ; GFX90A-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $agpr1 + ; GFX90A-NEXT: S_ENDPGM 0, amdgpu_allvgprs, implicit $agpr1 $agpr1 = COPY $sgpr8 - S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $agpr1 + S_ENDPGM 0, amdgpu_allvgprs, implicit $agpr1 ... --- @@ -38,13 +38,13 @@ body: | ; GFX908-NEXT: $agpr2 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr63, implicit $exec, implicit-def $agpr2_agpr3 ; GFX908-NEXT: $vgpr63 = V_MOV_B32_e32 $sgpr9, implicit $exec, implicit $sgpr8_sgpr9 ; GFX908-NEXT: $agpr3 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr63, implicit $exec - ; GFX908-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $agpr2_agpr3 + ; GFX908-NEXT: S_ENDPGM 0, amdgpu_allvgprs, implicit $agpr2_agpr3 ; GFX90A-LABEL: name: no_free_vgprs_for_copy_s64_to_a64 ; GFX90A: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253, $vgpr254, $vgpr255, $sgpr8_sgpr9 ; GFX90A-NEXT: {{ $}} ; GFX90A-NEXT: $agpr2 = V_ACCVGPR_WRITE_B32_e64 $sgpr8, implicit $exec, implicit-def $agpr2_agpr3, implicit $sgpr8_sgpr9 ; GFX90A-NEXT: $agpr3 = V_ACCVGPR_WRITE_B32_e64 $sgpr9, implicit $exec, implicit $sgpr8_sgpr9 - ; GFX90A-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $agpr2_agpr3 + ; GFX90A-NEXT: S_ENDPGM 0, amdgpu_allvgprs, implicit $agpr2_agpr3 $agpr2_agpr3 = COPY $sgpr8_sgpr9 - S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $agpr2_agpr3 + S_ENDPGM 0, amdgpu_allvgprs, implicit $agpr2_agpr3 ... diff --git a/llvm/test/CodeGen/AMDGPU/av_spill_cross_bb_usage.mir b/llvm/test/CodeGen/AMDGPU/av_spill_cross_bb_usage.mir index 720c4eb..cf073dc 100644 --- a/llvm/test/CodeGen/AMDGPU/av_spill_cross_bb_usage.mir +++ b/llvm/test/CodeGen/AMDGPU/av_spill_cross_bb_usage.mir @@ -64,7 +64,7 @@ body: | ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr15, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 60, 0, 0, 0, implicit $exec, implicit killed $vgpr14_vgpr15 :: (store (s32) into %stack.1 + 4, addrspace 5) ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr10, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 64, 0, 0, 0, implicit $exec, implicit-def $vgpr10_vgpr11, implicit $vgpr10_vgpr11 :: (store (s32) into %stack.2, addrspace 5) ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr11, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 68, 0, 0, 0, implicit $exec, implicit killed $vgpr10_vgpr11 :: (store (s32) into %stack.2 + 4, addrspace 5) - ; GCN-NEXT: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr16_sgpr17, 0, csr_amdgpu_highregs, implicit-def dead $vgpr0 + ; GCN-NEXT: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr16_sgpr17, 0, csr_amdgpu, implicit-def dead $vgpr0 ; GCN-NEXT: $vgpr14 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 56, 0, 0, 0, implicit $exec, implicit-def $vgpr14_vgpr15 :: (load (s32) from %stack.1, addrspace 5) ; GCN-NEXT: $vgpr15 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 60, 0, 0, 0, implicit $exec, implicit-def $vgpr14_vgpr15 :: (load (s32) from %stack.1 + 4, addrspace 5) ; GCN-NEXT: renamable $vgpr0_vgpr1 = nofpexcept V_FMA_F64_e64 0, killed $vgpr45_vgpr46, 0, killed $vgpr41_vgpr42, 0, killed $vgpr60_vgpr61, 0, 0, implicit $mode, implicit $exec @@ -122,7 +122,7 @@ body: | renamable $sgpr16_sgpr17 = IMPLICIT_DEF $vgpr40 = V_WRITELANE_B32 $sgpr30, 0, $vgpr40, implicit-def $sgpr30_sgpr31, implicit $sgpr30_sgpr31 $vgpr40 = V_WRITELANE_B32 killed $sgpr31, 1, $vgpr40, implicit killed $sgpr30_sgpr31 - dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr16_sgpr17, 0, csr_amdgpu_highregs, implicit-def dead $vgpr0 + dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr16_sgpr17, 0, csr_amdgpu, implicit-def dead $vgpr0 %8:vreg_64 = nofpexcept V_FMA_F64_e64 0, %7, 0, %6, 0, %5, 0, 0, implicit $mode, implicit $exec ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 FLAT_STORE_DWORDX2 %4, %8, 0, 0, implicit $exec, implicit $flat_scr :: (store (s64)) diff --git a/llvm/test/CodeGen/AMDGPU/call-waw-waitcnt.mir b/llvm/test/CodeGen/AMDGPU/call-waw-waitcnt.mir index 2b62a18..039c902 100644 --- a/llvm/test/CodeGen/AMDGPU/call-waw-waitcnt.mir +++ b/llvm/test/CodeGen/AMDGPU/call-waw-waitcnt.mir @@ -36,7 +36,7 @@ body: | ; GCN: } ; GCN: $sgpr32 = S_MOV_B32 $sgpr33 ; GCN: S_WAITCNT 49279 - ; GCN: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def dead $vgpr0 + ; GCN: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def dead $vgpr0 ; GCN: S_ENDPGM 0 $sgpr30_sgpr31 = S_LOAD_DWORDX2_IMM $sgpr4_sgpr5, 0, 0 $sgpr33 = S_MOV_B32 killed $sgpr7 @@ -48,6 +48,6 @@ body: | $sgpr5 = S_ADDC_U32 internal $sgpr5, target-flags(amdgpu-rel32-hi) @func + 4, implicit-def $scc, implicit internal $scc } $sgpr32 = S_MOV_B32 $sgpr33 - dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def dead $vgpr0 + dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit-def dead $vgpr0 S_ENDPGM 0 ... diff --git a/llvm/test/CodeGen/AMDGPU/collapse-endcf2.mir b/llvm/test/CodeGen/AMDGPU/collapse-endcf2.mir index 53e645a..d6dff64 100644 --- a/llvm/test/CodeGen/AMDGPU/collapse-endcf2.mir +++ b/llvm/test/CodeGen/AMDGPU/collapse-endcf2.mir @@ -59,7 +59,7 @@ body: | ; GCN: successors: %bb.4(0x80000000) ; GCN: $exec = S_OR_B64 $exec, [[COPY4]], implicit-def $scc ; GCN: [[DEF:%[0-9]+]]:sreg_64 = IMPLICIT_DEF - ; GCN: dead %16:sreg_64 = SI_CALL [[DEF]], @func, csr_amdgpu_highregs + ; GCN: dead %16:sreg_64 = SI_CALL [[DEF]], @func, csr_amdgpu ; GCN: bb.4: ; GCN: $exec = S_OR_B64 $exec, [[COPY2]], implicit-def $scc ; GCN: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 3, implicit $exec @@ -108,7 +108,7 @@ body: | bb.3: $exec = S_OR_B64 $exec, %12, implicit-def $scc %20:sreg_64 = IMPLICIT_DEF - %21:sreg_64 = SI_CALL %20, @func, csr_amdgpu_highregs + %21:sreg_64 = SI_CALL %20, @func, csr_amdgpu bb.4: $exec = S_OR_B64 $exec, %3, implicit-def $scc diff --git a/llvm/test/CodeGen/AMDGPU/debug-value-scheduler-crash.mir b/llvm/test/CodeGen/AMDGPU/debug-value-scheduler-crash.mir index 0fcccde..8ceca99 100644 --- a/llvm/test/CodeGen/AMDGPU/debug-value-scheduler-crash.mir +++ b/llvm/test/CodeGen/AMDGPU/debug-value-scheduler-crash.mir @@ -70,7 +70,7 @@ body: | ; CHECK-NEXT: $vgpr0 = COPY %16 ; CHECK-NEXT: $vgpr1 = COPY %17 ; CHECK-NEXT: $vgpr2 = COPY %18 - ; CHECK-NEXT: dead $sgpr30_sgpr31 = SI_CALL [[DEF13]], @foo, csr_amdgpu_highregs, implicit undef $sgpr0_sgpr1_sgpr2_sgpr3, implicit killed $sgpr4, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit-def $vgpr0 + ; CHECK-NEXT: dead $sgpr30_sgpr31 = SI_CALL [[DEF13]], @foo, csr_amdgpu, implicit undef $sgpr0_sgpr1_sgpr2_sgpr3, implicit killed $sgpr4, implicit $vgpr0, implicit $vgpr1, implicit $vgpr2, implicit-def $vgpr0 ; CHECK-NEXT: %25:vgpr_32 = nofpexcept V_ADD_F32_e32 %9, [[DEF7]], implicit $mode, implicit $exec ; CHECK-NEXT: %25:vgpr_32 = nofpexcept V_MAC_F32_e32 [[DEF11]], [[DEF8]], %25, implicit $mode, implicit $exec ; CHECK-NEXT: dead %26:vgpr_32 = nofpexcept V_MAD_F32_e64 0, %25, 0, [[DEF3]], 0, [[DEF]], 0, 0, implicit $mode, implicit $exec @@ -129,7 +129,7 @@ body: | $vgpr1 = COPY %17 $vgpr2 = COPY %18 $sgpr4 = IMPLICIT_DEF - dead $sgpr30_sgpr31 = SI_CALL %24, @foo, csr_amdgpu_highregs, implicit undef $sgpr0_sgpr1_sgpr2_sgpr3, implicit killed $sgpr4, implicit killed $vgpr0, implicit killed $vgpr1, implicit killed $vgpr2, implicit-def $vgpr0 + dead $sgpr30_sgpr31 = SI_CALL %24, @foo, csr_amdgpu, implicit undef $sgpr0_sgpr1_sgpr2_sgpr3, implicit killed $sgpr4, implicit killed $vgpr0, implicit killed $vgpr1, implicit killed $vgpr2, implicit-def $vgpr0 %25:vgpr_32 = nofpexcept V_ADD_F32_e32 %9, %8, implicit $mode, implicit $exec %25:vgpr_32 = nofpexcept V_MAC_F32_e32 %15, %10, %25, implicit $mode, implicit $exec %26:vgpr_32 = nofpexcept V_MAD_F32_e64 0, %25, 0, %4, 0, %1, 0, 0, implicit $mode, implicit $exec diff --git a/llvm/test/CodeGen/AMDGPU/fold-operands-remove-m0-redef.mir b/llvm/test/CodeGen/AMDGPU/fold-operands-remove-m0-redef.mir index 2e97644..c3295f1 100644 --- a/llvm/test/CodeGen/AMDGPU/fold-operands-remove-m0-redef.mir +++ b/llvm/test/CodeGen/AMDGPU/fold-operands-remove-m0-redef.mir @@ -270,14 +270,14 @@ body: | ; GCN: [[COPY1:%[0-9]+]]:sgpr_32 = COPY $sgpr0 ; GCN: $m0 = COPY [[COPY1]] ; GCN: [[DS_READ_B32_:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 0, 0, implicit $m0, implicit $exec :: (load (s32)) - ; GCN: dead $sgpr30_sgpr31 = SI_CALL undef $sgpr6_sgpr7, @func, csr_amdgpu_highregs + ; GCN: dead $sgpr30_sgpr31 = SI_CALL undef $sgpr6_sgpr7, @func, csr_amdgpu ; GCN: $m0 = COPY [[COPY1]] ; GCN: [[DS_READ_B32_1:%[0-9]+]]:vgpr_32 = DS_READ_B32 [[COPY]], 64, 0, implicit $m0, implicit $exec :: (load (s32)) %0:vgpr_32 = COPY $vgpr0 %1:sgpr_32 = COPY $sgpr0 $m0 = COPY %1 %2:vgpr_32 = DS_READ_B32 %0, 0, 0, implicit $m0, implicit $exec :: (load (s32)) - dead $sgpr30_sgpr31 = SI_CALL undef $sgpr6_sgpr7, @func, csr_amdgpu_highregs + dead $sgpr30_sgpr31 = SI_CALL undef $sgpr6_sgpr7, @func, csr_amdgpu $m0 = COPY %1 %3:vgpr_32 = DS_READ_B32 %0, 64, 0, implicit $m0, implicit $exec :: (load (s32)) diff --git a/llvm/test/CodeGen/AMDGPU/greedy-alloc-fail-sgpr1024-spill.mir b/llvm/test/CodeGen/AMDGPU/greedy-alloc-fail-sgpr1024-spill.mir index 87cc6b5..bb8b1dc 100644 --- a/llvm/test/CodeGen/AMDGPU/greedy-alloc-fail-sgpr1024-spill.mir +++ b/llvm/test/CodeGen/AMDGPU/greedy-alloc-fail-sgpr1024-spill.mir @@ -57,7 +57,7 @@ body: | ; CHECK: renamable $sgpr64 = S_MOV_B32 0 ; CHECK: renamable $sgpr68_sgpr69 = IMPLICIT_DEF ; CHECK: ADJCALLSTACKUP 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 - ; CHECK: dead $sgpr30_sgpr31 = SI_CALL renamable $sgpr68_sgpr69, 0, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + ; CHECK: dead $sgpr30_sgpr31 = SI_CALL renamable $sgpr68_sgpr69, 0, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3 ; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 ; CHECK: ADJCALLSTACKUP 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 ; CHECK: $sgpr4_sgpr5 = COPY killed renamable $sgpr40_sgpr41 @@ -66,7 +66,7 @@ body: | ; CHECK: $sgpr10_sgpr11 = COPY killed renamable $sgpr36_sgpr37 ; CHECK: $sgpr12 = COPY killed renamable $sgpr42 ; CHECK: $sgpr13 = COPY killed renamable $sgpr33 - ; CHECK: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr68_sgpr69, 0, csr_amdgpu_highregs, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit killed $sgpr12, implicit killed $sgpr13, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + ; CHECK: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr68_sgpr69, 0, csr_amdgpu, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit killed $sgpr12, implicit killed $sgpr13, implicit $sgpr0_sgpr1_sgpr2_sgpr3 ; CHECK: ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 ; CHECK: renamable $sgpr4_sgpr5 = COPY $exec, implicit-def $exec ; CHECK: dead renamable $sgpr6_sgpr7 = IMPLICIT_DEF @@ -151,7 +151,7 @@ body: | %7.sub20:sgpr_1024 = S_MOV_B32 0 %8:sreg_64 = IMPLICIT_DEF ADJCALLSTACKUP 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 - dead $sgpr30_sgpr31 = SI_CALL %8, 0, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + dead $sgpr30_sgpr31 = SI_CALL %8, 0, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3 ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 ADJCALLSTACKUP 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 $sgpr4_sgpr5 = COPY %5 @@ -160,7 +160,7 @@ body: | $sgpr10_sgpr11 = COPY %3 $sgpr12 = COPY %2 $sgpr13 = COPY %1 - dead $sgpr30_sgpr31 = SI_CALL %8, 0, csr_amdgpu_highregs, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit killed $sgpr12, implicit killed $sgpr13, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + dead $sgpr30_sgpr31 = SI_CALL %8, 0, csr_amdgpu, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit killed $sgpr12, implicit killed $sgpr13, implicit $sgpr0_sgpr1_sgpr2_sgpr3 ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 %9:sreg_64 = COPY $exec, implicit-def $exec %10:sreg_64 = IMPLICIT_DEF diff --git a/llvm/test/CodeGen/AMDGPU/limit-soft-clause-reg-pressure.mir b/llvm/test/CodeGen/AMDGPU/limit-soft-clause-reg-pressure.mir index 0688a6b..46fe85a 100644 --- a/llvm/test/CodeGen/AMDGPU/limit-soft-clause-reg-pressure.mir +++ b/llvm/test/CodeGen/AMDGPU/limit-soft-clause-reg-pressure.mir @@ -24,7 +24,7 @@ body: | ; CHECK-NEXT: [[S_LOAD_DWORDX16_IMM4:%[0-9]+]]:sgpr_512 = S_LOAD_DWORDX16_IMM %3, 64, 0 :: (load (s512), align 4, addrspace 4) ; CHECK-NEXT: [[S_LOAD_DWORDX16_IMM5:%[0-9]+]]:sgpr_512 = S_LOAD_DWORDX16_IMM %3, 4160, 0 :: (load (s512), align 4, addrspace 4) ; CHECK-NEXT: [[S_LOAD_DWORDX16_IMM6:%[0-9]+]]:sgpr_512 = S_LOAD_DWORDX16_IMM %3, 8256, 0 :: (load (s512), align 4, addrspace 4) - ; CHECK-NEXT: dead $sgpr30_sgpr31 = SI_CALL undef $sgpr4_sgpr5, 0, csr_amdgpu_highregs, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31, implicit-def $sgpr32_sgpr33_sgpr34_sgpr35_sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51_sgpr52_sgpr53_sgpr54_sgpr55_sgpr56_sgpr57_sgpr58_sgpr59_sgpr60_sgpr61_sgpr62_sgpr63, implicit-def $sgpr70, implicit-def $sgpr80, implicit-def $sgpr90, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit-def $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47_vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63 + ; CHECK-NEXT: dead $sgpr30_sgpr31 = SI_CALL undef $sgpr4_sgpr5, 0, csr_amdgpu, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31, implicit-def $sgpr32_sgpr33_sgpr34_sgpr35_sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51_sgpr52_sgpr53_sgpr54_sgpr55_sgpr56_sgpr57_sgpr58_sgpr59_sgpr60_sgpr61_sgpr62_sgpr63, implicit-def $sgpr70, implicit-def $sgpr80, implicit-def $sgpr90, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit-def $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47_vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63 bb.0: liveins: $vgpr0, $sgpr4_sgpr5, $sgpr6 @@ -42,7 +42,7 @@ body: | %8:sgpr_512 = S_LOAD_DWORDX16_IMM %3, 64, 0 :: (load (s512), align 4, addrspace 4) %9:sgpr_512 = S_LOAD_DWORDX16_IMM %3, 4160, 0 :: (load (s512), align 4, addrspace 4) %10:sgpr_512 = S_LOAD_DWORDX16_IMM %3, 8256, 0 :: (load (s512), align 4, addrspace 4) - dead $sgpr30_sgpr31 = SI_CALL undef $sgpr4_sgpr5, 0, csr_amdgpu_highregs, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31, implicit-def $sgpr32_sgpr33_sgpr34_sgpr35_sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51_sgpr52_sgpr53_sgpr54_sgpr55_sgpr56_sgpr57_sgpr58_sgpr59_sgpr60_sgpr61_sgpr62_sgpr63, implicit-def $sgpr70, implicit-def $sgpr80, implicit-def $sgpr90, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit-def $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47_vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63 + dead $sgpr30_sgpr31 = SI_CALL undef $sgpr4_sgpr5, 0, csr_amdgpu, implicit-def $vgpr0, implicit-def $vgpr1, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15_sgpr16_sgpr17_sgpr18_sgpr19_sgpr20_sgpr21_sgpr22_sgpr23_sgpr24_sgpr25_sgpr26_sgpr27_sgpr28_sgpr29_sgpr30_sgpr31, implicit-def $sgpr32_sgpr33_sgpr34_sgpr35_sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51_sgpr52_sgpr53_sgpr54_sgpr55_sgpr56_sgpr57_sgpr58_sgpr59_sgpr60_sgpr61_sgpr62_sgpr63, implicit-def $sgpr70, implicit-def $sgpr80, implicit-def $sgpr90, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15_vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, implicit-def $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47_vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63 dead %11:vgpr_32 = nofpexcept V_ADD_F32_e64 0, 0, 0, %4.sub1, 0, 0, implicit $mode, implicit $exec dead %12:vgpr_32 = nofpexcept V_ADD_F32_e64 0, 0, 0, %4.sub2, 0, 0, implicit $mode, implicit $exec dead %13:vgpr_32 = nofpexcept V_ADD_F32_e64 0, 0, 0, %4.sub3, 0, 0, implicit $mode, implicit $exec diff --git a/llvm/test/CodeGen/AMDGPU/pei-scavenge-vgpr-spill.mir b/llvm/test/CodeGen/AMDGPU/pei-scavenge-vgpr-spill.mir index d2ea398..5c8a427 100644 --- a/llvm/test/CodeGen/AMDGPU/pei-scavenge-vgpr-spill.mir +++ b/llvm/test/CodeGen/AMDGPU/pei-scavenge-vgpr-spill.mir @@ -49,7 +49,7 @@ body: | ; GFX8-NEXT: $vgpr2 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, killed $sgpr6, 0, 0, 0, 0, implicit $exec :: (load (s32) from %stack.3, addrspace 5) ; GFX8-NEXT: $exec = S_MOV_B64 killed $sgpr4_sgpr5 ; GFX8-NEXT: $vgpr3 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load (s32) from %stack.4, addrspace 5) - ; GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX9-LABEL: name: pei_scavenge_vgpr_spill ; GFX9: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255, $vgpr2 ; GFX9-NEXT: {{ $}} @@ -74,7 +74,7 @@ body: | ; GFX9-NEXT: $vgpr2 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, killed $sgpr6, 0, 0, 0, 0, implicit $exec :: (load (s32) from %stack.3, addrspace 5) ; GFX9-NEXT: $exec = S_MOV_B64 killed $sgpr4_sgpr5 ; GFX9-NEXT: $vgpr3 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr33, 0, 0, 0, 0, implicit $exec :: (load (s32) from %stack.4, addrspace 5) - ; GFX9-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX9-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX9-FLATSCR-LABEL: name: pei_scavenge_vgpr_spill ; GFX9-FLATSCR: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255, $vgpr2 ; GFX9-FLATSCR-NEXT: {{ $}} @@ -96,8 +96,8 @@ body: | ; GFX9-FLATSCR-NEXT: $sgpr6 = S_ADD_I32 $sgpr32, 16388, implicit-def dead $scc ; GFX9-FLATSCR-NEXT: $vgpr2 = SCRATCH_LOAD_DWORD_SADDR killed $sgpr6, 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from %stack.3, addrspace 5) ; GFX9-FLATSCR-NEXT: $exec = S_MOV_B64 killed $sgpr4_sgpr5 - ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs $vgpr0 = V_MOV_B32_e32 %stack.0, implicit $exec $vgpr0 = V_OR_B32_e32 %stack.1, $vgpr1, implicit $exec - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... diff --git a/llvm/test/CodeGen/AMDGPU/sched-crash-dbg-value.mir b/llvm/test/CodeGen/AMDGPU/sched-crash-dbg-value.mir index 430ce95..094f34e 100644 --- a/llvm/test/CodeGen/AMDGPU/sched-crash-dbg-value.mir +++ b/llvm/test/CodeGen/AMDGPU/sched-crash-dbg-value.mir @@ -326,7 +326,7 @@ body: | $vgpr0 = COPY %124 $vgpr1_vgpr2 = IMPLICIT_DEF $vgpr3 = COPY %126 - dead $sgpr30_sgpr31 = SI_CALL %127, @func, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4, implicit $vgpr0, implicit $vgpr1_vgpr2, implicit killed $vgpr3 + dead $sgpr30_sgpr31 = SI_CALL %127, @func, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4, implicit $vgpr0, implicit $vgpr1_vgpr2, implicit killed $vgpr3 ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32 %128:vreg_64, dead %129:sreg_64 = V_MAD_I64_I32_e64 %20, %34, 0, 0, implicit $exec S_ENDPGM 0 diff --git a/llvm/test/CodeGen/AMDGPU/sgpr-spill-to-vmem-scc-clobber.mir b/llvm/test/CodeGen/AMDGPU/sgpr-spill-to-vmem-scc-clobber.mir index f6b2110..ab1b49b 100644 --- a/llvm/test/CodeGen/AMDGPU/sgpr-spill-to-vmem-scc-clobber.mir +++ b/llvm/test/CodeGen/AMDGPU/sgpr-spill-to-vmem-scc-clobber.mir @@ -239,7 +239,7 @@ body: | ; VMEM-GFX8-NEXT: S_NOP 0 ; VMEM-GFX8-NEXT: {{ $}} ; VMEM-GFX8-NEXT: bb.2: - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255, $sgpr8 S_CMP_EQ_U32 0, 0, implicit-def $scc @@ -250,7 +250,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- @@ -293,7 +293,7 @@ body: | ; VMEM-GFX8-NEXT: bb.2: ; VMEM-GFX8-NEXT: liveins: $sgpr8 ; VMEM-GFX8-NEXT: {{ $}} - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $sgpr8 + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs, implicit $sgpr8 bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 S_CMP_EQ_U32 0, 0, implicit-def $scc @@ -306,7 +306,7 @@ body: | bb.2: liveins: $sgpr8 - S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $sgpr8 + S_ENDPGM 0, amdgpu_allvgprs, implicit $sgpr8 ... --- @@ -347,7 +347,7 @@ body: | ; VMEM-GFX8-NEXT: S_NOP 0 ; VMEM-GFX8-NEXT: {{ $}} ; VMEM-GFX8-NEXT: bb.2: - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255, $sgpr8_sgpr9 S_CMP_EQ_U32 0, 0, implicit-def $scc @@ -358,7 +358,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- @@ -402,7 +402,7 @@ body: | ; VMEM-GFX8-NEXT: bb.2: ; VMEM-GFX8-NEXT: liveins: $sgpr8_sgpr9 ; VMEM-GFX8-NEXT: {{ $}} - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $sgpr8_sgpr9 + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs, implicit $sgpr8_sgpr9 bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 S_CMP_EQ_U32 0, 0, implicit-def $scc @@ -415,7 +415,7 @@ body: | bb.2: liveins: $sgpr8_sgpr9 - S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $sgpr8_sgpr9 + S_ENDPGM 0, amdgpu_allvgprs, implicit $sgpr8_sgpr9 ... # Test with 2 spills we need to handle, so we're sure the scavenger state is consistent after the first is processed. @@ -468,7 +468,7 @@ body: | ; VMEM-GFX8-NEXT: S_NOP 0 ; VMEM-GFX8-NEXT: {{ $}} ; VMEM-GFX8-NEXT: bb.2: - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255, $sgpr8, $sgpr9 S_CMP_EQ_U32 0, 0, implicit-def $scc @@ -480,7 +480,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- name: sgpr32_restore_clobber_scc_emergency_stack_slot_x2 @@ -533,7 +533,7 @@ body: | ; VMEM-GFX8-NEXT: bb.2: ; VMEM-GFX8-NEXT: liveins: $sgpr8, $sgpr9 ; VMEM-GFX8-NEXT: {{ $}} - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $sgpr8, implicit $sgpr9 + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs, implicit $sgpr8, implicit $sgpr9 bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 S_CMP_EQ_U32 0, 0, implicit-def $scc @@ -547,5 +547,5 @@ body: | bb.2: liveins: $sgpr8, $sgpr9 - S_ENDPGM 0, csr_amdgpu_allvgprs, implicit $sgpr8, implicit $sgpr9 + S_ENDPGM 0, amdgpu_allvgprs, implicit $sgpr8, implicit $sgpr9 ... diff --git a/llvm/test/CodeGen/AMDGPU/sgpr-spill-wrong-stack-id.mir b/llvm/test/CodeGen/AMDGPU/sgpr-spill-wrong-stack-id.mir index c822d4f..84e890d3 100644 --- a/llvm/test/CodeGen/AMDGPU/sgpr-spill-wrong-stack-id.mir +++ b/llvm/test/CodeGen/AMDGPU/sgpr-spill-wrong-stack-id.mir @@ -40,11 +40,11 @@ # SHARE: SI_SPILL_V32_SAVE killed $vgpr0, %stack.0, $sgpr32, 0, implicit $exec :: (store (s32) into %stack.0, addrspace 5) # SHARE: SI_SPILL_S64_SAVE killed renamable $sgpr4_sgpr5, %stack.1, implicit $exec, implicit $sgpr32 :: (store (s64) into %stack.1, align 4, addrspace 5) # SHARE: renamable $sgpr4_sgpr5 = SI_SPILL_S64_RESTORE %stack.1, implicit $exec, implicit $sgpr32 :: (load (s64) from %stack.1, align 4, addrspace 5) -# SHARE: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu_highregs, implicit undef $vgpr0 +# SHARE: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu, implicit undef $vgpr0 # SHARE: $sgpr32 = SI_SPILL_S32_RESTORE %stack.2, implicit $exec, implicit $sgpr32 :: (load (s32) from %stack.2, addrspace 5) # SHARE: $vgpr0 = SI_SPILL_V32_RESTORE %stack.0, $sgpr32, 0, implicit $exec :: (load (s32) from %stack.0, addrspace 5) # SHARE: renamable $sgpr4_sgpr5 = SI_SPILL_S64_RESTORE %stack.1, implicit $exec, implicit $sgpr32 :: (load (s64) from %stack.1, align 4, addrspace 5) -# SHARE: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu_highregs, implicit $vgpr0 +# SHARE: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu, implicit $vgpr0 # SHARE: $sgpr32 = SI_SPILL_S32_RESTORE %stack.2, implicit $exec, implicit $sgpr32 :: (load (s32) from %stack.2, addrspace 5) # NOSHARE: stack: @@ -65,12 +65,12 @@ # NOSHARE: SI_SPILL_V32_SAVE killed $vgpr0, %stack.0, $sgpr32, 0, implicit $exec :: (store (s32) into %stack.0, addrspace 5) # NOSHARE: SI_SPILL_S64_SAVE killed renamable $sgpr4_sgpr5, %stack.1, implicit $exec, implicit $sgpr32 :: (store (s64) into %stack.1, align 4, addrspace 5) # NOSHARE: renamable $sgpr4_sgpr5 = SI_SPILL_S64_RESTORE %stack.1, implicit $exec, implicit $sgpr32 :: (load (s64) from %stack.1, align 4, addrspace 5) -# NOSHARE: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu_highregs, implicit undef $vgpr0 +# NOSHARE: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu, implicit undef $vgpr0 # NOSHARE: $sgpr32 = SI_SPILL_S32_RESTORE %stack.2, implicit $exec, implicit $sgpr32 :: (load (s32) from %stack.2, addrspace 5) # NOSHARE: SI_SPILL_S32_SAVE $sgpr32, %stack.3, implicit $exec, implicit $sgpr32 :: (store (s32) into %stack.3, addrspace 5) # NOSHARE: $vgpr0 = SI_SPILL_V32_RESTORE %stack.0, $sgpr32, 0, implicit $exec :: (load (s32) from %stack.0, addrspace 5) # NOSHARE: renamable $sgpr4_sgpr5 = SI_SPILL_S64_RESTORE %stack.1, implicit $exec, implicit $sgpr32 :: (load (s64) from %stack.1, align 4, addrspace 5) -# NOSHARE: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu_highregs, implicit $vgpr0 +# NOSHARE: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu, implicit $vgpr0 # NOSHARE: $sgpr32 = SI_SPILL_S32_RESTORE %stack.3, implicit $exec, implicit $sgpr32 :: (load (s32) from %stack.3, addrspace 5) ... @@ -90,13 +90,13 @@ body: | %2:vgpr_32 = FLAT_LOAD_DWORD %1, 0, 0, implicit $exec, implicit $flat_scr %3:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @func + 4, target-flags(amdgpu-rel32-hi) @func + 4, implicit-def dead $scc ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32 - dead $sgpr30_sgpr31 = SI_CALL %3, @func, csr_amdgpu_highregs, implicit undef $vgpr0 + dead $sgpr30_sgpr31 = SI_CALL %3, @func, csr_amdgpu, implicit undef $vgpr0 $sgpr32 = COPY %0 %4:sreg_32_xm0 = COPY $sgpr32 ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32 ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32 $vgpr0 = COPY %2 - dead $sgpr30_sgpr31 = SI_CALL %3, @func, csr_amdgpu_highregs, implicit killed $vgpr0 + dead $sgpr30_sgpr31 = SI_CALL %3, @func, csr_amdgpu, implicit killed $vgpr0 $sgpr32 = COPY %4 ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32 diff --git a/llvm/test/CodeGen/AMDGPU/splitkit-copy-bundle.mir b/llvm/test/CodeGen/AMDGPU/splitkit-copy-bundle.mir index d7e368f..8074e72 100644 --- a/llvm/test/CodeGen/AMDGPU/splitkit-copy-bundle.mir +++ b/llvm/test/CodeGen/AMDGPU/splitkit-copy-bundle.mir @@ -80,7 +80,7 @@ body: | ; RA: %3.sub31:sgpr_1024 = COPY %3.sub0 ; RA: bb.2: ; RA: successors: %bb.1(0x40000000), %bb.2(0x40000000) - ; RA: S_NOP 0, csr_amdgpu_highregs, implicit [[DEF]], implicit [[DEF1]] + ; RA: S_NOP 0, csr_amdgpu, implicit [[DEF]], implicit [[DEF1]] ; RA: S_CBRANCH_VCCNZ %bb.1, implicit undef $vcc ; RA: S_BRANCH %bb.2 ; VR-LABEL: name: splitkit_copy_bundle @@ -156,7 +156,7 @@ body: | ; VR: bb.2: ; VR: successors: %bb.1(0x40000000), %bb.2(0x40000000) ; VR: liveins: $sgpr36_sgpr37_sgpr38_sgpr39_sgpr40_sgpr41_sgpr42_sgpr43_sgpr44_sgpr45_sgpr46_sgpr47_sgpr48_sgpr49_sgpr50_sgpr51_sgpr52_sgpr53_sgpr54_sgpr55_sgpr56_sgpr57_sgpr58_sgpr59_sgpr60_sgpr61_sgpr62_sgpr63_sgpr64_sgpr65_sgpr66_sgpr67:0x000000000000000F, $sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75_sgpr76_sgpr77_sgpr78_sgpr79_sgpr80_sgpr81_sgpr82_sgpr83_sgpr84_sgpr85_sgpr86_sgpr87_sgpr88_sgpr89_sgpr90_sgpr91_sgpr92_sgpr93_sgpr94_sgpr95_sgpr96_sgpr97_sgpr98_sgpr99:0x0000000000000003, $sgpr30_sgpr31, $sgpr34_sgpr35 - ; VR: S_NOP 0, csr_amdgpu_highregs, implicit renamable $sgpr30_sgpr31, implicit renamable $sgpr34_sgpr35 + ; VR: S_NOP 0, csr_amdgpu, implicit renamable $sgpr30_sgpr31, implicit renamable $sgpr34_sgpr35 ; VR: S_CBRANCH_VCCNZ %bb.1, implicit undef $vcc ; VR: S_BRANCH %bb.2 bb.0: @@ -228,7 +228,7 @@ body: | %3.sub31:sgpr_1024 = COPY %3.sub0 bb.2: - S_NOP 0, implicit %0, implicit %1, csr_amdgpu_highregs + S_NOP 0, implicit %0, implicit %1, csr_amdgpu S_CBRANCH_VCCNZ %bb.1, implicit undef $vcc S_BRANCH %bb.2 diff --git a/llvm/test/CodeGen/AMDGPU/verify-gfx90a-aligned-vgprs.mir b/llvm/test/CodeGen/AMDGPU/verify-gfx90a-aligned-vgprs.mir index bc6137e..be68753 100644 --- a/llvm/test/CodeGen/AMDGPU/verify-gfx90a-aligned-vgprs.mir +++ b/llvm/test/CodeGen/AMDGPU/verify-gfx90a-aligned-vgprs.mir @@ -11,7 +11,7 @@ body: | S_NOP 0, implicit %0 %1:sreg_64_xexec = IMPLICIT_DEF - %2:sreg_64_xexec = SI_CALL %1, 0, csr_amdgpu_highregs, implicit $vgpr1_vgpr2 + %2:sreg_64_xexec = SI_CALL %1, 0, csr_amdgpu, implicit $vgpr1_vgpr2 ; noreg is OK DS_WRITE_B64_gfx9 $noreg, $noreg, 0, 0, implicit $exec diff --git a/llvm/test/CodeGen/AMDGPU/vgpr-spill-scc-clobber.mir b/llvm/test/CodeGen/AMDGPU/vgpr-spill-scc-clobber.mir index c50cd75..6641b82 100644 --- a/llvm/test/CodeGen/AMDGPU/vgpr-spill-scc-clobber.mir +++ b/llvm/test/CodeGen/AMDGPU/vgpr-spill-scc-clobber.mir @@ -416,7 +416,7 @@ body: | ; MUBUF-NEXT: S_NOP 0 ; MUBUF-NEXT: {{ $}} ; MUBUF-NEXT: bb.2: - ; MUBUF-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; MUBUF-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX9-FLATSCR-LABEL: name: vgpr32_restore_clobber_scc_emergency_stack_slot ; GFX9-FLATSCR: bb.0: ; GFX9-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -436,7 +436,7 @@ body: | ; GFX9-FLATSCR-NEXT: S_NOP 0 ; GFX9-FLATSCR-NEXT: {{ $}} ; GFX9-FLATSCR-NEXT: bb.2: - ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX10-FLATSCR-LABEL: name: vgpr32_restore_clobber_scc_emergency_stack_slot ; GFX10-FLATSCR: bb.0: ; GFX10-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -455,7 +455,7 @@ body: | ; GFX10-FLATSCR-NEXT: S_NOP 0 ; GFX10-FLATSCR-NEXT: {{ $}} ; GFX10-FLATSCR-NEXT: bb.2: - ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; VMEM-GFX8-LABEL: name: vgpr32_restore_clobber_scc_emergency_stack_slot ; VMEM-GFX8: bb.0: ; VMEM-GFX8-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -474,7 +474,7 @@ body: | ; VMEM-GFX8-NEXT: S_NOP 0 ; VMEM-GFX8-NEXT: {{ $}} ; VMEM-GFX8-NEXT: bb.2: - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 @@ -486,7 +486,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- @@ -521,7 +521,7 @@ body: | ; MUBUF-NEXT: S_NOP 0 ; MUBUF-NEXT: {{ $}} ; MUBUF-NEXT: bb.2: - ; MUBUF-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; MUBUF-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX9-FLATSCR-LABEL: name: vgpr64_restore_clobber_scc_emergency_stack_slot ; GFX9-FLATSCR: bb.0: ; GFX9-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -541,7 +541,7 @@ body: | ; GFX9-FLATSCR-NEXT: S_NOP 0 ; GFX9-FLATSCR-NEXT: {{ $}} ; GFX9-FLATSCR-NEXT: bb.2: - ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX10-FLATSCR-LABEL: name: vgpr64_restore_clobber_scc_emergency_stack_slot ; GFX10-FLATSCR: bb.0: ; GFX10-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -560,7 +560,7 @@ body: | ; GFX10-FLATSCR-NEXT: S_NOP 0 ; GFX10-FLATSCR-NEXT: {{ $}} ; GFX10-FLATSCR-NEXT: bb.2: - ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; VMEM-GFX8-LABEL: name: vgpr64_restore_clobber_scc_emergency_stack_slot ; VMEM-GFX8: bb.0: ; VMEM-GFX8-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -580,7 +580,7 @@ body: | ; VMEM-GFX8-NEXT: S_NOP 0 ; VMEM-GFX8-NEXT: {{ $}} ; VMEM-GFX8-NEXT: bb.2: - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 @@ -592,7 +592,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- @@ -628,7 +628,7 @@ body: | ; MUBUF-NEXT: S_NOP 0 ; MUBUF-NEXT: {{ $}} ; MUBUF-NEXT: bb.2: - ; MUBUF-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; MUBUF-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX9-FLATSCR-LABEL: name: vgpr96_restore_clobber_scc_emergency_stack_slot ; GFX9-FLATSCR: bb.0: ; GFX9-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -648,7 +648,7 @@ body: | ; GFX9-FLATSCR-NEXT: S_NOP 0 ; GFX9-FLATSCR-NEXT: {{ $}} ; GFX9-FLATSCR-NEXT: bb.2: - ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX10-FLATSCR-LABEL: name: vgpr96_restore_clobber_scc_emergency_stack_slot ; GFX10-FLATSCR: bb.0: ; GFX10-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -667,7 +667,7 @@ body: | ; GFX10-FLATSCR-NEXT: S_NOP 0 ; GFX10-FLATSCR-NEXT: {{ $}} ; GFX10-FLATSCR-NEXT: bb.2: - ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; VMEM-GFX8-LABEL: name: vgpr96_restore_clobber_scc_emergency_stack_slot ; VMEM-GFX8: bb.0: ; VMEM-GFX8-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -688,7 +688,7 @@ body: | ; VMEM-GFX8-NEXT: S_NOP 0 ; VMEM-GFX8-NEXT: {{ $}} ; VMEM-GFX8-NEXT: bb.2: - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 @@ -700,7 +700,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- @@ -734,7 +734,7 @@ body: | ; MUBUF-NEXT: S_NOP 0 ; MUBUF-NEXT: {{ $}} ; MUBUF-NEXT: bb.2: - ; MUBUF-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; MUBUF-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX9-FLATSCR-LABEL: name: vgpr32_save_clobber_scc_emergency_stack_slot ; GFX9-FLATSCR: bb.0: ; GFX9-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -754,7 +754,7 @@ body: | ; GFX9-FLATSCR-NEXT: S_NOP 0 ; GFX9-FLATSCR-NEXT: {{ $}} ; GFX9-FLATSCR-NEXT: bb.2: - ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX10-FLATSCR-LABEL: name: vgpr32_save_clobber_scc_emergency_stack_slot ; GFX10-FLATSCR: bb.0: ; GFX10-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -773,7 +773,7 @@ body: | ; GFX10-FLATSCR-NEXT: S_NOP 0 ; GFX10-FLATSCR-NEXT: {{ $}} ; GFX10-FLATSCR-NEXT: bb.2: - ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; VMEM-GFX8-LABEL: name: vgpr32_save_clobber_scc_emergency_stack_slot ; VMEM-GFX8: bb.0: ; VMEM-GFX8-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -792,7 +792,7 @@ body: | ; VMEM-GFX8-NEXT: S_NOP 0 ; VMEM-GFX8-NEXT: {{ $}} ; VMEM-GFX8-NEXT: bb.2: - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 @@ -804,7 +804,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- @@ -839,7 +839,7 @@ body: | ; MUBUF-NEXT: S_NOP 0 ; MUBUF-NEXT: {{ $}} ; MUBUF-NEXT: bb.2: - ; MUBUF-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; MUBUF-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX9-FLATSCR-LABEL: name: vgpr64_save_clobber_scc_emergency_stack_slot ; GFX9-FLATSCR: bb.0: ; GFX9-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -859,7 +859,7 @@ body: | ; GFX9-FLATSCR-NEXT: S_NOP 0 ; GFX9-FLATSCR-NEXT: {{ $}} ; GFX9-FLATSCR-NEXT: bb.2: - ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX10-FLATSCR-LABEL: name: vgpr64_save_clobber_scc_emergency_stack_slot ; GFX10-FLATSCR: bb.0: ; GFX10-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -878,7 +878,7 @@ body: | ; GFX10-FLATSCR-NEXT: S_NOP 0 ; GFX10-FLATSCR-NEXT: {{ $}} ; GFX10-FLATSCR-NEXT: bb.2: - ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; VMEM-GFX8-LABEL: name: vgpr64_save_clobber_scc_emergency_stack_slot ; VMEM-GFX8: bb.0: ; VMEM-GFX8-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -898,7 +898,7 @@ body: | ; VMEM-GFX8-NEXT: S_NOP 0 ; VMEM-GFX8-NEXT: {{ $}} ; VMEM-GFX8-NEXT: bb.2: - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 @@ -910,7 +910,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- @@ -946,7 +946,7 @@ body: | ; MUBUF-NEXT: S_NOP 0 ; MUBUF-NEXT: {{ $}} ; MUBUF-NEXT: bb.2: - ; MUBUF-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; MUBUF-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX9-FLATSCR-LABEL: name: vgpr96_save_clobber_scc_emergency_stack_slot ; GFX9-FLATSCR: bb.0: ; GFX9-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -966,7 +966,7 @@ body: | ; GFX9-FLATSCR-NEXT: S_NOP 0 ; GFX9-FLATSCR-NEXT: {{ $}} ; GFX9-FLATSCR-NEXT: bb.2: - ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX10-FLATSCR-LABEL: name: vgpr96_save_clobber_scc_emergency_stack_slot ; GFX10-FLATSCR: bb.0: ; GFX10-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -985,7 +985,7 @@ body: | ; GFX10-FLATSCR-NEXT: S_NOP 0 ; GFX10-FLATSCR-NEXT: {{ $}} ; GFX10-FLATSCR-NEXT: bb.2: - ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; VMEM-GFX8-LABEL: name: vgpr96_save_clobber_scc_emergency_stack_slot ; VMEM-GFX8: bb.0: ; VMEM-GFX8-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -1006,7 +1006,7 @@ body: | ; VMEM-GFX8-NEXT: S_NOP 0 ; VMEM-GFX8-NEXT: {{ $}} ; VMEM-GFX8-NEXT: bb.2: - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 @@ -1018,7 +1018,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- @@ -1049,7 +1049,7 @@ body: | ; MUBUF-NEXT: S_NOP 0 ; MUBUF-NEXT: {{ $}} ; MUBUF-NEXT: bb.2: - ; MUBUF-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; MUBUF-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX9-FLATSCR-LABEL: name: mubuf_load_restore_clobber_scc ; GFX9-FLATSCR: bb.0: ; GFX9-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -1066,7 +1066,7 @@ body: | ; GFX9-FLATSCR-NEXT: S_NOP 0 ; GFX9-FLATSCR-NEXT: {{ $}} ; GFX9-FLATSCR-NEXT: bb.2: - ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX10-FLATSCR-LABEL: name: mubuf_load_restore_clobber_scc ; GFX10-FLATSCR: bb.0: ; GFX10-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -1083,7 +1083,7 @@ body: | ; GFX10-FLATSCR-NEXT: S_NOP 0 ; GFX10-FLATSCR-NEXT: {{ $}} ; GFX10-FLATSCR-NEXT: bb.2: - ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; VMEM-GFX8-LABEL: name: mubuf_load_restore_clobber_scc ; VMEM-GFX8: bb.0: ; VMEM-GFX8-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -1099,7 +1099,7 @@ body: | ; VMEM-GFX8-NEXT: S_NOP 0 ; VMEM-GFX8-NEXT: {{ $}} ; VMEM-GFX8-NEXT: bb.2: - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: S_CMP_EQ_U32 0, 0, implicit-def $scc @@ -1110,7 +1110,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... # The expansion of the frame index clobbers SCC, which we cannot @@ -1148,7 +1148,7 @@ body: | ; MUBUF-NEXT: S_NOP 0 ; MUBUF-NEXT: {{ $}} ; MUBUF-NEXT: bb.2: - ; MUBUF-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; MUBUF-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX9-FLATSCR-LABEL: name: mubuf_load_restore_clobber_scc_no_vgprs_emergency_stack_slot ; GFX9-FLATSCR: bb.0: ; GFX9-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -1168,7 +1168,7 @@ body: | ; GFX9-FLATSCR-NEXT: S_NOP 0 ; GFX9-FLATSCR-NEXT: {{ $}} ; GFX9-FLATSCR-NEXT: bb.2: - ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX9-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; GFX10-FLATSCR-LABEL: name: mubuf_load_restore_clobber_scc_no_vgprs_emergency_stack_slot ; GFX10-FLATSCR: bb.0: ; GFX10-FLATSCR-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -1188,7 +1188,7 @@ body: | ; GFX10-FLATSCR-NEXT: S_NOP 0 ; GFX10-FLATSCR-NEXT: {{ $}} ; GFX10-FLATSCR-NEXT: bb.2: - ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; GFX10-FLATSCR-NEXT: S_ENDPGM 0, amdgpu_allvgprs ; VMEM-GFX8-LABEL: name: mubuf_load_restore_clobber_scc_no_vgprs_emergency_stack_slot ; VMEM-GFX8: bb.0: ; VMEM-GFX8-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) @@ -1207,7 +1207,7 @@ body: | ; VMEM-GFX8-NEXT: S_NOP 0 ; VMEM-GFX8-NEXT: {{ $}} ; VMEM-GFX8-NEXT: bb.2: - ; VMEM-GFX8-NEXT: S_ENDPGM 0, csr_amdgpu_allvgprs + ; VMEM-GFX8-NEXT: S_ENDPGM 0, amdgpu_allvgprs bb.0: liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15, $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27_vgpr28_vgpr29_vgpr30_vgpr31, $vgpr32_vgpr33_vgpr34_vgpr35_vgpr36_vgpr37_vgpr38_vgpr39_vgpr40_vgpr41_vgpr42_vgpr43_vgpr44_vgpr45_vgpr46_vgpr47, $vgpr48_vgpr49_vgpr50_vgpr51_vgpr52_vgpr53_vgpr54_vgpr55_vgpr56_vgpr57_vgpr58_vgpr59_vgpr60_vgpr61_vgpr62_vgpr63, $vgpr64_vgpr65_vgpr66_vgpr67_vgpr68_vgpr69_vgpr70_vgpr71_vgpr72_vgpr73_vgpr74_vgpr75_vgpr76_vgpr77_vgpr78_vgpr79, $vgpr80_vgpr81_vgpr82_vgpr83_vgpr84_vgpr85_vgpr86_vgpr87_vgpr88_vgpr89_vgpr90_vgpr91_vgpr92_vgpr93_vgpr94_vgpr95, $vgpr96_vgpr97_vgpr98_vgpr99_vgpr100_vgpr101_vgpr102_vgpr103_vgpr104_vgpr105_vgpr106_vgpr107_vgpr108_vgpr109_vgpr110_vgpr111, $vgpr112_vgpr113_vgpr114_vgpr115_vgpr116_vgpr117_vgpr118_vgpr119_vgpr120_vgpr121_vgpr122_vgpr123_vgpr124_vgpr125_vgpr126_vgpr127, $vgpr128_vgpr129_vgpr130_vgpr131_vgpr132_vgpr133_vgpr134_vgpr135_vgpr136_vgpr137_vgpr138_vgpr139_vgpr140_vgpr141_vgpr142_vgpr143, $vgpr144_vgpr145_vgpr146_vgpr147_vgpr148_vgpr149_vgpr150_vgpr151_vgpr152_vgpr153_vgpr154_vgpr155_vgpr156_vgpr157_vgpr158_vgpr159, $vgpr160_vgpr161_vgpr162_vgpr163_vgpr164_vgpr165_vgpr166_vgpr167_vgpr168_vgpr169_vgpr170_vgpr171_vgpr172_vgpr173_vgpr174_vgpr175, $vgpr176_vgpr177_vgpr178_vgpr179_vgpr180_vgpr181_vgpr182_vgpr183_vgpr184_vgpr185_vgpr186_vgpr187_vgpr188_vgpr189_vgpr190_vgpr191, $vgpr192_vgpr193_vgpr194_vgpr195_vgpr196_vgpr197_vgpr198_vgpr199_vgpr200_vgpr201_vgpr202_vgpr203_vgpr204_vgpr205_vgpr206_vgpr207, $vgpr208_vgpr209_vgpr210_vgpr211_vgpr212_vgpr213_vgpr214_vgpr215_vgpr216_vgpr217_vgpr218_vgpr219_vgpr220_vgpr221_vgpr222_vgpr223, $vgpr224_vgpr225_vgpr226_vgpr227_vgpr228_vgpr229_vgpr230_vgpr231_vgpr232_vgpr233_vgpr234_vgpr235_vgpr236_vgpr237_vgpr238_vgpr239, $vgpr240_vgpr241_vgpr242_vgpr243_vgpr244_vgpr245_vgpr246_vgpr247, $vgpr248_vgpr249_vgpr250_vgpr251, $vgpr252_vgpr253_vgpr254_vgpr255 @@ -1220,7 +1220,7 @@ body: | S_NOP 0 bb.2: - S_ENDPGM 0, csr_amdgpu_allvgprs + S_ENDPGM 0, amdgpu_allvgprs ... --- diff --git a/llvm/test/CodeGen/AMDGPU/virtregrewrite-undef-identity-copy.mir b/llvm/test/CodeGen/AMDGPU/virtregrewrite-undef-identity-copy.mir index 06aec73..8a3df85 100644 --- a/llvm/test/CodeGen/AMDGPU/virtregrewrite-undef-identity-copy.mir +++ b/llvm/test/CodeGen/AMDGPU/virtregrewrite-undef-identity-copy.mir @@ -33,7 +33,7 @@ body: | ; CHECK: renamable $sgpr6_sgpr7 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @foo + 4, target-flags(amdgpu-rel32-hi) @foo + 4, implicit-def dead $scc ; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr95, implicit-def $scc ; CHECK: $sgpr4 = COPY $sgpr95 - ; CHECK: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr6_sgpr7, @foo, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4 + ; CHECK: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr6_sgpr7, @foo, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4 ; CHECK: ADJCALLSTACKDOWN 0, 4, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr95 ; CHECK: renamable $sgpr6_sgpr7 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @bar + 4, target-flags(amdgpu-rel32-hi) @bar + 4, implicit-def dead $scc ; CHECK: ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr95 @@ -42,7 +42,7 @@ body: | ; CHECK: $vgpr1 = COPY renamable $vgpr41 ; CHECK: $vgpr2 = COPY killed renamable $vgpr42 ; CHECK: $vgpr3 = KILL undef renamable $vgpr3 - ; CHECK: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr6_sgpr7, @bar, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4, implicit $vgpr0, implicit killed $vgpr1, implicit killed $vgpr2, implicit killed $vgpr3, implicit-def $vgpr0 + ; CHECK: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr6_sgpr7, @bar, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4, implicit $vgpr0, implicit killed $vgpr1, implicit killed $vgpr2, implicit killed $vgpr3, implicit-def $vgpr0 ; CHECK: ADJCALLSTACKDOWN 0, 4, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr95 ; CHECK: FLAT_STORE_DWORD undef renamable $vgpr0_vgpr1, killed renamable $vgpr0, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1) ; CHECK: S_ENDPGM 0 @@ -50,7 +50,7 @@ body: | %2:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @foo + 4, target-flags(amdgpu-rel32-hi) @foo + 4, implicit-def dead $scc ADJCALLSTACKUP 0, 0, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr95, implicit-def $scc $sgpr4 = COPY $sgpr95 - dead $sgpr30_sgpr31 = SI_CALL %2, @foo, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4 + dead $sgpr30_sgpr31 = SI_CALL %2, @foo, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4 ADJCALLSTACKDOWN 0, 4, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr95 %3:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @bar + 4, target-flags(amdgpu-rel32-hi) @bar + 4, implicit-def dead $scc ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr95 @@ -59,7 +59,7 @@ body: | $vgpr1 = COPY %0.sub1 $vgpr2 = COPY %0.sub2 $vgpr3 = COPY undef %4:vgpr_32 - dead $sgpr30_sgpr31 = SI_CALL %3, @bar, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4, implicit $vgpr0, implicit killed $vgpr1, implicit killed $vgpr2, implicit killed $vgpr3, implicit-def $vgpr0 + dead $sgpr30_sgpr31 = SI_CALL %3, @bar, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4, implicit $vgpr0, implicit killed $vgpr1, implicit killed $vgpr2, implicit killed $vgpr3, implicit-def $vgpr0 %5:vgpr_32 = COPY $vgpr0 ADJCALLSTACKDOWN 0, 4, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr95 FLAT_STORE_DWORD undef %6:vreg_64, %5, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32), addrspace 1) diff --git a/llvm/test/CodeGen/MIR/AMDGPU/stack-id-assert.mir b/llvm/test/CodeGen/MIR/AMDGPU/stack-id-assert.mir index 6e9f4da..156891f 100644 --- a/llvm/test/CodeGen/MIR/AMDGPU/stack-id-assert.mir +++ b/llvm/test/CodeGen/MIR/AMDGPU/stack-id-assert.mir @@ -49,7 +49,7 @@ body: | ADJCALLSTACKUP 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 renamable $sgpr4_sgpr5 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @foo + 4, target-flags(amdgpu-gotprel32-hi) @foo + 12, implicit-def dead $scc renamable $sgpr4_sgpr5 = S_LOAD_DWORDX2_IMM killed renamable $sgpr4_sgpr5, 0, 0 - dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @foo, csr_amdgpu_highregs, implicit $sgpr0_sgpr1_sgpr2_sgpr3 + dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @foo, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3 ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 SI_RETURN -- 2.7.4