+; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
;RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 --stop-after=greedy,1 -verify-machineinstrs < %s | FileCheck -check-prefix=REGALLOC-GFX908 %s
;RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 --stop-after=prologepilog -verify-machineinstrs < %s | FileCheck -check-prefix=PEI-GFX908 %s
;RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a --stop-after=greedy,1 -verify-machineinstrs < %s | FileCheck -check-prefix=REGALLOC-GFX90A %s
define amdgpu_kernel void @partial_copy(<4 x i32> %arg) #0 {
; REGALLOC-GFX908-LABEL: name: partial_copy
; REGALLOC-GFX908: bb.0 (%ir-block.0):
- ; REGALLOC-GFX908: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 2949130 /* regdef:VReg_64 */, def [[VREG_64:%[0-9]+]]
- ; REGALLOC-GFX908: SI_SPILL_V64_SAVE [[VREG_64]], %stack.0
- ; REGALLOC-GFX908: [[V_MFMA_I32_4X4X4I8_A128:%[0-9]+]]:areg_128 = V_MFMA_I32_4X4X4I8_e64
- ; REGALLOC-GFX908: [[SI_SPILL_V64_RESTORE:%[0-9]+]]:vreg_64 = SI_SPILL_V64_RESTORE %stack.0
- ; REGALLOC-GFX908: GLOBAL_STORE_DWORDX2 undef %{{[0-9]+}}:vreg_64, [[SI_SPILL_V64_RESTORE]]
- ; REGALLOC-GFX908: [[COPY_A128_TO_V128:%[0-9]+]]:vreg_128 = COPY [[V_MFMA_I32_4X4X4I8_A128]]
- ; REGALLOC-GFX908: GLOBAL_STORE_DWORDX4 undef %{{[0-9]+}}:vreg_64, [[COPY_A128_TO_V128]]
- ;
+ ; REGALLOC-GFX908-NEXT: liveins: $sgpr4_sgpr5
+ ; REGALLOC-GFX908-NEXT: {{ $}}
+ ; REGALLOC-GFX908-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 1769481 /* reguse:AGPR_32 */, undef %5:agpr_32
+ ; REGALLOC-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 4784138 /* regdef:VReg_128 */, def %26
+ ; REGALLOC-GFX908-NEXT: [[COPY:%[0-9]+]]:av_128 = COPY %26
+ ; REGALLOC-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 2949130 /* regdef:VReg_64 */, def %23
+ ; REGALLOC-GFX908-NEXT: SI_SPILL_V64_SAVE %23, %stack.0, $sgpr32, 0, implicit $exec :: (store (s64) into %stack.0, align 4, addrspace 5)
+ ; REGALLOC-GFX908-NEXT: [[COPY1:%[0-9]+]]:vreg_128 = COPY [[COPY]]
+ ; REGALLOC-GFX908-NEXT: GLOBAL_STORE_DWORDX4 undef %14:vreg_64, [[COPY1]], 0, 0, implicit $exec :: (volatile store (s128) into `<4 x i32> addrspace(1)* undef`, addrspace 1)
+ ; REGALLOC-GFX908-NEXT: renamable $sgpr0_sgpr1_sgpr2_sgpr3 = S_LOAD_DWORDX4_IMM killed renamable $sgpr4_sgpr5, 0, 0 :: (dereferenceable invariant load (s128) from %ir.arg.kernarg.offset.cast, addrspace 4)
+ ; REGALLOC-GFX908-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
+ ; REGALLOC-GFX908-NEXT: [[COPY2:%[0-9]+]]:areg_128 = COPY killed renamable $sgpr0_sgpr1_sgpr2_sgpr3
+ ; REGALLOC-GFX908-NEXT: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2, implicit $exec
+ ; REGALLOC-GFX908-NEXT: [[V_MFMA_I32_4X4X4I8_e64_:%[0-9]+]]:areg_128 = V_MFMA_I32_4X4X4I8_e64 [[V_MOV_B32_e32_]], [[V_MOV_B32_e32_1]], [[COPY2]], 0, 0, 0, implicit $mode, implicit $exec
+ ; REGALLOC-GFX908-NEXT: [[SI_SPILL_V64_RESTORE:%[0-9]+]]:vreg_64 = SI_SPILL_V64_RESTORE %stack.0, $sgpr32, 0, implicit $exec :: (load (s64) from %stack.0, align 4, addrspace 5)
+ ; REGALLOC-GFX908-NEXT: GLOBAL_STORE_DWORDX2 undef %16:vreg_64, [[SI_SPILL_V64_RESTORE]], 0, 0, implicit $exec :: (volatile store (s64) into `<2 x i32> addrspace(1)* undef`, addrspace 1)
+ ; REGALLOC-GFX908-NEXT: [[COPY3:%[0-9]+]]:vreg_128 = COPY [[V_MFMA_I32_4X4X4I8_e64_]]
+ ; REGALLOC-GFX908-NEXT: GLOBAL_STORE_DWORDX4 undef %18:vreg_64, [[COPY3]], 0, 0, implicit $exec :: (volatile store (s128) into `<4 x i32> addrspace(1)* undef`, addrspace 1)
+ ; REGALLOC-GFX908-NEXT: S_ENDPGM 0
; PEI-GFX908-LABEL: name: partial_copy
; PEI-GFX908: bb.0 (%ir-block.0):
- ; PEI-GFX908: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 2949130 /* regdef:VReg_64 */, def renamable $vgpr0_vgpr1
- ; PEI-GFX908: BUFFER_STORE_DWORD_OFFSET killed $vgpr0
- ; PEI-GFX908: $agpr4 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr1
- ; PEI-GFX908: renamable $agpr0_agpr1_agpr2_agpr3 = V_MFMA_I32_4X4X4I8_e64
- ; PEI-GFX908: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET
- ; PEI-GFX908: $vgpr1 = V_ACCVGPR_READ_B32_e64 $agpr4
- ; PEI-GFX908: GLOBAL_STORE_DWORDX2 undef renamable ${{.*}}, killed renamable $vgpr0_vgpr1
- ; PEI-GFX908: renamable $vgpr0_vgpr1_vgpr2_vgpr3 = COPY killed renamable $agpr0_agpr1_agpr2_agpr3, implicit $exec
- ; PEI-GFX908: GLOBAL_STORE_DWORDX4 undef renamable ${{.*}}, killed renamable $vgpr0_vgpr1_vgpr2_vgpr3
- ;
+ ; PEI-GFX908-NEXT: liveins: $agpr4, $sgpr4_sgpr5, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr7
+ ; PEI-GFX908-NEXT: {{ $}}
+ ; PEI-GFX908-NEXT: $sgpr8_sgpr9_sgpr10_sgpr11 = COPY killed $sgpr0_sgpr1_sgpr2_sgpr3
+ ; PEI-GFX908-NEXT: $sgpr8 = S_ADD_U32 $sgpr8, $sgpr7, implicit-def $scc, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
+ ; PEI-GFX908-NEXT: $sgpr9 = S_ADDC_U32 $sgpr9, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
+ ; PEI-GFX908-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 1769481 /* reguse:AGPR_32 */, undef renamable $agpr0
+ ; PEI-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 4784138 /* regdef:VReg_128 */, def renamable $vgpr0_vgpr1_vgpr2_vgpr3
+ ; PEI-GFX908-NEXT: renamable $agpr0_agpr1_agpr2_agpr3 = COPY killed renamable $vgpr0_vgpr1_vgpr2_vgpr3, implicit $exec
+ ; PEI-GFX908-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 2949130 /* regdef:VReg_64 */, def renamable $vgpr0_vgpr1
+ ; PEI-GFX908-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr8_sgpr9_sgpr10_sgpr11, 0, 4, 0, 0, 0, implicit $exec, implicit-def $vgpr0_vgpr1, implicit $vgpr0_vgpr1 :: (store (s32) into %stack.0, addrspace 5)
+ ; PEI-GFX908-NEXT: $agpr4 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr1, implicit $exec, implicit killed $vgpr0_vgpr1
+ ; PEI-GFX908-NEXT: renamable $vgpr0_vgpr1_vgpr2_vgpr3 = COPY killed renamable $agpr0_agpr1_agpr2_agpr3, implicit $exec
+ ; PEI-GFX908-NEXT: GLOBAL_STORE_DWORDX4 undef renamable $vgpr0_vgpr1, killed renamable $vgpr0_vgpr1_vgpr2_vgpr3, 0, 0, implicit $exec :: (volatile store (s128) into `<4 x i32> addrspace(1)* undef`, addrspace 1)
+ ; PEI-GFX908-NEXT: renamable $sgpr0_sgpr1_sgpr2_sgpr3 = S_LOAD_DWORDX4_IMM killed renamable $sgpr4_sgpr5, 0, 0 :: (dereferenceable invariant load (s128) from %ir.arg.kernarg.offset.cast, addrspace 4)
+ ; PEI-GFX908-NEXT: renamable $vgpr0 = V_MOV_B32_e32 1, implicit $exec
+ ; PEI-GFX908-NEXT: renamable $agpr0_agpr1_agpr2_agpr3 = COPY killed renamable $sgpr0_sgpr1_sgpr2_sgpr3, implicit $exec
+ ; PEI-GFX908-NEXT: renamable $vgpr1 = V_MOV_B32_e32 2, implicit $exec
+ ; PEI-GFX908-NEXT: renamable $agpr0_agpr1_agpr2_agpr3 = V_MFMA_I32_4X4X4I8_e64 killed $vgpr0, killed $vgpr1, killed $agpr0_agpr1_agpr2_agpr3, 0, 0, 0, implicit $mode, implicit $exec
+ ; PEI-GFX908-NEXT: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr8_sgpr9_sgpr10_sgpr11, 0, 4, 0, 0, 0, implicit $exec, implicit-def $vgpr0_vgpr1 :: (load (s32) from %stack.0, addrspace 5)
+ ; PEI-GFX908-NEXT: $vgpr1 = V_ACCVGPR_READ_B32_e64 $agpr4, implicit $exec, implicit-def $vgpr0_vgpr1
+ ; PEI-GFX908-NEXT: GLOBAL_STORE_DWORDX2 undef renamable $vgpr0_vgpr1, killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec :: (volatile store (s64) into `<2 x i32> addrspace(1)* undef`, addrspace 1)
+ ; PEI-GFX908-NEXT: renamable $vgpr0_vgpr1_vgpr2_vgpr3 = COPY killed renamable $agpr0_agpr1_agpr2_agpr3, implicit $exec
+ ; PEI-GFX908-NEXT: GLOBAL_STORE_DWORDX4 undef renamable $vgpr0_vgpr1, killed renamable $vgpr0_vgpr1_vgpr2_vgpr3, 0, 0, implicit $exec :: (volatile store (s128) into `<4 x i32> addrspace(1)* undef`, addrspace 1)
+ ; PEI-GFX908-NEXT: S_ENDPGM 0
; REGALLOC-GFX90A-LABEL: name: partial_copy
; REGALLOC-GFX90A: bb.0 (%ir-block.0):
- ; REGALLOC-GFX90A: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 3080202 /* regdef:VReg_64_Align2 */, def [[VREG_64:%[0-9]+]]
- ; REGALLOC-GFX90A: SI_SPILL_V64_SAVE [[VREG_64]], %stack.0
- ; REGALLOC-GFX90A: [[V_MFMA_I32_4X4X4I8_A128:%[0-9]+]]:areg_128_align2 = V_MFMA_I32_4X4X4I8_e64
- ; REGALLOC-GFX90A: [[SI_SPILL_AV64_RESTORE:%[0-9]+]]:av_64_align2 = SI_SPILL_AV64_RESTORE %stack.0
- ; REGALLOC-GFX90A: GLOBAL_STORE_DWORDX2 undef %{{[0-9]+}}:vreg_64_align2, [[SI_SPILL_AV64_RESTORE]]
- ; REGALLOC-GFX90A: GLOBAL_STORE_DWORDX4 undef %{{[0-9]+}}:vreg_64_align2, [[V_MFMA_I32_4X4X4I8_A128]]
- ;
+ ; REGALLOC-GFX90A-NEXT: liveins: $sgpr4_sgpr5
+ ; REGALLOC-GFX90A-NEXT: {{ $}}
+ ; REGALLOC-GFX90A-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 1769481 /* reguse:AGPR_32 */, undef %5:agpr_32
+ ; REGALLOC-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 4980746 /* regdef:VReg_128_Align2 */, def %25
+ ; REGALLOC-GFX90A-NEXT: [[COPY:%[0-9]+]]:av_128_align2 = COPY %25
+ ; REGALLOC-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 3080202 /* regdef:VReg_64_Align2 */, def %23
+ ; REGALLOC-GFX90A-NEXT: SI_SPILL_V64_SAVE %23, %stack.0, $sgpr32, 0, implicit $exec :: (store (s64) into %stack.0, align 4, addrspace 5)
+ ; REGALLOC-GFX90A-NEXT: GLOBAL_STORE_DWORDX4 undef %14:vreg_64_align2, [[COPY]], 0, 0, implicit $exec :: (volatile store (s128) into `<4 x i32> addrspace(1)* undef`, addrspace 1)
+ ; REGALLOC-GFX90A-NEXT: renamable $sgpr0_sgpr1_sgpr2_sgpr3 = S_LOAD_DWORDX4_IMM killed renamable $sgpr4_sgpr5, 0, 0 :: (dereferenceable invariant load (s128) from %ir.arg.kernarg.offset.cast, addrspace 4)
+ ; REGALLOC-GFX90A-NEXT: [[COPY1:%[0-9]+]]:areg_128_align2 = COPY killed renamable $sgpr0_sgpr1_sgpr2_sgpr3
+ ; REGALLOC-GFX90A-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
+ ; REGALLOC-GFX90A-NEXT: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 2, implicit $exec
+ ; REGALLOC-GFX90A-NEXT: [[V_MFMA_I32_4X4X4I8_e64_:%[0-9]+]]:areg_128_align2 = V_MFMA_I32_4X4X4I8_e64 [[V_MOV_B32_e32_]], [[V_MOV_B32_e32_1]], [[COPY1]], 0, 0, 0, implicit $mode, implicit $exec
+ ; REGALLOC-GFX90A-NEXT: [[SI_SPILL_AV64_RESTORE:%[0-9]+]]:av_64_align2 = SI_SPILL_AV64_RESTORE %stack.0, $sgpr32, 0, implicit $exec :: (load (s64) from %stack.0, align 4, addrspace 5)
+ ; REGALLOC-GFX90A-NEXT: GLOBAL_STORE_DWORDX2 undef %16:vreg_64_align2, [[SI_SPILL_AV64_RESTORE]], 0, 0, implicit $exec :: (volatile store (s64) into `<2 x i32> addrspace(1)* undef`, addrspace 1)
+ ; REGALLOC-GFX90A-NEXT: GLOBAL_STORE_DWORDX4 undef %18:vreg_64_align2, [[V_MFMA_I32_4X4X4I8_e64_]], 0, 0, implicit $exec :: (volatile store (s128) into `<4 x i32> addrspace(1)* undef`, addrspace 1)
+ ; REGALLOC-GFX90A-NEXT: S_ENDPGM 0
; PEI-GFX90A-LABEL: name: partial_copy
; PEI-GFX90A: bb.0 (%ir-block.0):
- ; PEI-GFX90A: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 3080202 /* regdef:VReg_64_Align2 */, def renamable $vgpr0_vgpr1
- ; PEI-GFX90A: BUFFER_STORE_DWORD_OFFSET killed $vgpr0
- ; PEI-GFX90A: $agpr4 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr1
- ; PEI-GFX90A: renamable $agpr0_agpr1_agpr2_agpr3 = V_MFMA_I32_4X4X4I8_e64
- ; PEI-GFX90A: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET
- ; PEI-GFX90A: $vgpr1 = V_ACCVGPR_READ_B32_e64 $agpr4
- ; PEI-GFX90A: GLOBAL_STORE_DWORDX2 undef renamable ${{.*}}, killed renamable $vgpr0_vgpr1
- ; PEI-GFX90A: GLOBAL_STORE_DWORDX4 undef renamable ${{.*}}, killed renamable $agpr0_agpr1_agpr2_agpr3
+ ; PEI-GFX90A-NEXT: liveins: $agpr4, $sgpr4_sgpr5, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr7
+ ; PEI-GFX90A-NEXT: {{ $}}
+ ; PEI-GFX90A-NEXT: $sgpr8_sgpr9_sgpr10_sgpr11 = COPY killed $sgpr0_sgpr1_sgpr2_sgpr3
+ ; PEI-GFX90A-NEXT: $sgpr8 = S_ADD_U32 $sgpr8, $sgpr7, implicit-def $scc, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
+ ; PEI-GFX90A-NEXT: $sgpr9 = S_ADDC_U32 $sgpr9, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr8_sgpr9_sgpr10_sgpr11
+ ; PEI-GFX90A-NEXT: INLINEASM &"; use $0", 1 /* sideeffect attdialect */, 1769481 /* reguse:AGPR_32 */, undef renamable $agpr0
+ ; PEI-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 4980746 /* regdef:VReg_128_Align2 */, def renamable $vgpr0_vgpr1_vgpr2_vgpr3
+ ; PEI-GFX90A-NEXT: renamable $agpr0_agpr1_agpr2_agpr3 = COPY killed renamable $vgpr0_vgpr1_vgpr2_vgpr3, implicit $exec
+ ; PEI-GFX90A-NEXT: INLINEASM &"; def $0", 1 /* sideeffect attdialect */, 3080202 /* regdef:VReg_64_Align2 */, def renamable $vgpr0_vgpr1
+ ; PEI-GFX90A-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr8_sgpr9_sgpr10_sgpr11, 0, 4, 0, 0, 0, implicit $exec, implicit-def $vgpr0_vgpr1, implicit $vgpr0_vgpr1 :: (store (s32) into %stack.0, addrspace 5)
+ ; PEI-GFX90A-NEXT: $agpr4 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr1, implicit $exec, implicit killed $vgpr0_vgpr1
+ ; PEI-GFX90A-NEXT: GLOBAL_STORE_DWORDX4 undef renamable $vgpr0_vgpr1, killed renamable $agpr0_agpr1_agpr2_agpr3, 0, 0, implicit $exec :: (volatile store (s128) into `<4 x i32> addrspace(1)* undef`, addrspace 1)
+ ; PEI-GFX90A-NEXT: renamable $sgpr0_sgpr1_sgpr2_sgpr3 = S_LOAD_DWORDX4_IMM killed renamable $sgpr4_sgpr5, 0, 0 :: (dereferenceable invariant load (s128) from %ir.arg.kernarg.offset.cast, addrspace 4)
+ ; PEI-GFX90A-NEXT: renamable $agpr0_agpr1_agpr2_agpr3 = COPY killed renamable $sgpr0_sgpr1_sgpr2_sgpr3, implicit $exec
+ ; PEI-GFX90A-NEXT: renamable $vgpr0 = V_MOV_B32_e32 1, implicit $exec
+ ; PEI-GFX90A-NEXT: renamable $vgpr1 = V_MOV_B32_e32 2, implicit $exec
+ ; PEI-GFX90A-NEXT: renamable $agpr0_agpr1_agpr2_agpr3 = V_MFMA_I32_4X4X4I8_e64 killed $vgpr0, killed $vgpr1, killed $agpr0_agpr1_agpr2_agpr3, 0, 0, 0, implicit $mode, implicit $exec
+ ; PEI-GFX90A-NEXT: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr8_sgpr9_sgpr10_sgpr11, 0, 4, 0, 0, 0, implicit $exec, implicit-def $vgpr0_vgpr1 :: (load (s32) from %stack.0, addrspace 5)
+ ; PEI-GFX90A-NEXT: $vgpr1 = V_ACCVGPR_READ_B32_e64 $agpr4, implicit $exec, implicit-def $vgpr0_vgpr1
+ ; PEI-GFX90A-NEXT: GLOBAL_STORE_DWORDX2 undef renamable $vgpr0_vgpr1, killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec :: (volatile store (s64) into `<2 x i32> addrspace(1)* undef`, addrspace 1)
+ ; PEI-GFX90A-NEXT: GLOBAL_STORE_DWORDX4 undef renamable $vgpr0_vgpr1, killed renamable $agpr0_agpr1_agpr2_agpr3, 0, 0, implicit $exec :: (volatile store (s128) into `<4 x i32> addrspace(1)* undef`, addrspace 1)
+ ; PEI-GFX90A-NEXT: S_ENDPGM 0
call void asm sideeffect "; use $0", "a" (i32 undef)
%v0 = call <4 x i32> asm sideeffect "; def $0", "=v" ()
%v1 = call <2 x i32> asm sideeffect "; def $0", "=v" ()