This reverts r227987 "R600/SI: Determine target-specific encoding of READLANE and WRITELANE early v2".
All the codegen changes are caused by the post-RA scheduler no longer
treating readlane/writelane as scheduling barriers due to having
unmodelled side effects. (The pseudos are hasSideEffects = 0, but the
real instructions are hasSideEffects = ? which TableGen conservatively
treats as 1.)
Differential Revision: https://reviews.llvm.org/D90401
unsigned SDSTName;
switch (MI->getOpcode()) {
case AMDGPU::V_READLANE_B32:
- case AMDGPU::V_READLANE_B32_gfx10:
case AMDGPU::V_READFIRSTLANE_B32:
SDSTName = AMDGPU::OpName::vdst;
break;
// Save FP before setting it up.
// FIXME: This should respect spillSGPRToVGPR;
- BuildMI(MBB, MBBI, DL, TII->getMCOpcodeFromPseudo(AMDGPU::V_WRITELANE_B32),
- Spill[0].VGPR)
+ BuildMI(MBB, MBBI, DL, TII->get(AMDGPU::V_WRITELANE_B32), Spill[0].VGPR)
.addReg(FramePtrReg)
.addImm(Spill[0].Lane)
.addReg(Spill[0].VGPR, RegState::Undef);
// Save BP before setting it up.
// FIXME: This should respect spillSGPRToVGPR;
- BuildMI(MBB, MBBI, DL, TII->getMCOpcodeFromPseudo(AMDGPU::V_WRITELANE_B32),
- Spill[0].VGPR)
+ BuildMI(MBB, MBBI, DL, TII->get(AMDGPU::V_WRITELANE_B32), Spill[0].VGPR)
.addReg(BasePtrReg)
.addImm(Spill[0].Lane)
.addReg(Spill[0].VGPR, RegState::Undef);
ArrayRef<SIMachineFunctionInfo::SpilledReg> Spill =
FuncInfo->getSGPRToVGPRSpills(FI);
assert(Spill.size() == 1);
- BuildMI(MBB, MBBI, DL, TII->getMCOpcodeFromPseudo(AMDGPU::V_READLANE_B32),
- FramePtrReg)
+ BuildMI(MBB, MBBI, DL, TII->get(AMDGPU::V_READLANE_B32), FramePtrReg)
.addReg(Spill[0].VGPR)
.addImm(Spill[0].Lane);
}
ArrayRef<SIMachineFunctionInfo::SpilledReg> Spill =
FuncInfo->getSGPRToVGPRSpills(BasePtrFI);
assert(Spill.size() == 1);
- BuildMI(MBB, MBBI, DL, TII->getMCOpcodeFromPseudo(AMDGPU::V_READLANE_B32),
- BasePtrReg)
+ BuildMI(MBB, MBBI, DL, TII->get(AMDGPU::V_READLANE_B32), BasePtrReg)
.addReg(Spill[0].VGPR)
.addImm(Spill[0].Lane);
}
if (SIInstrInfo::isVALU(MI)) {
switch (MI.getOpcode()) {
case AMDGPU::V_READLANE_B32:
- case AMDGPU::V_READLANE_B32_gfx6_gfx7:
- case AMDGPU::V_READLANE_B32_gfx10:
- case AMDGPU::V_READLANE_B32_vi:
case AMDGPU::V_WRITELANE_B32:
- case AMDGPU::V_WRITELANE_B32_gfx6_gfx7:
- case AMDGPU::V_WRITELANE_B32_gfx10:
- case AMDGPU::V_WRITELANE_B32_vi:
return false;
}
} else if (!IsKill) {
// Restore SGPRs from appropriate VGPR lanes
if (!OnlyExecLo) {
- BuildMI(*MBB, MI, DL, TII->getMCOpcodeFromPseudo(AMDGPU::V_READLANE_B32),
+ BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_READLANE_B32),
getSubReg(SuperReg, SplitParts[FirstPart + ExecLane + 1]))
.addReg(VGPR)
.addImm(ExecLane + 1);
}
- BuildMI(*MBB, MI, DL, TII->getMCOpcodeFromPseudo(AMDGPU::V_READLANE_B32),
+ BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_READLANE_B32),
NumSubRegs == 1
? SavedExecReg
: getSubReg(SuperReg, SplitParts[FirstPart + ExecLane]))
// Mark the "old value of vgpr" input undef only if this is the first sgpr
// spill to this specific vgpr in the first basic block.
- auto MIB = BuildMI(*MBB, MI, DL,
- TII->getMCOpcodeFromPseudo(AMDGPU::V_WRITELANE_B32),
- Spill.VGPR)
- .addReg(SubReg, getKillRegState(UseKill))
- .addImm(Spill.Lane)
- .addReg(Spill.VGPR, VGPRDefined ? 0 : RegState::Undef);
+ auto MIB =
+ BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_WRITELANE_B32), Spill.VGPR)
+ .addReg(SubReg, getKillRegState(UseKill))
+ .addImm(Spill.Lane)
+ .addReg(Spill.VGPR, VGPRDefined ? 0 : RegState::Undef);
if (i == 0 && NumSubRegs > 1) {
// We may be spilling a super-register which is only partially defined,
NumSubRegs == 1 ? SuperReg : getSubReg(SuperReg, SplitParts[i]);
MachineInstrBuilder WriteLane =
- BuildMI(*MBB, MI, DL,
- TII->getMCOpcodeFromPseudo(AMDGPU::V_WRITELANE_B32),
- TmpVGPR)
+ BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_WRITELANE_B32), TmpVGPR)
.addReg(SubReg, SubKillState)
.addImm(i % PerVGPR)
.addReg(TmpVGPR, TmpVGPRFlags);
NumSubRegs == 1 ? SuperReg : getSubReg(SuperReg, SplitParts[i]);
SIMachineFunctionInfo::SpilledReg Spill = VGPRSpills[i];
- auto MIB =
- BuildMI(*MBB, MI, DL, TII->getMCOpcodeFromPseudo(AMDGPU::V_READLANE_B32),
- SubReg)
- .addReg(Spill.VGPR)
- .addImm(Spill.Lane);
+ auto MIB = BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_READLANE_B32), SubReg)
+ .addReg(Spill.VGPR)
+ .addImm(Spill.Lane);
if (NumSubRegs > 1 && i == 0)
MIB.addReg(SuperReg, RegState::ImplicitDefine);
}
bool LastSubReg = (i + 1 == e);
auto MIB =
- BuildMI(*MBB, MI, DL,
- TII->getMCOpcodeFromPseudo(AMDGPU::V_READLANE_B32), SubReg)
+ BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_READLANE_B32), SubReg)
.addReg(TmpVGPR, getKillRegState(LastSubReg))
.addImm(i);
if (NumSubRegs > 1 && i == 0)
; GCN-LABEL: {{^}}last_lane_vgpr_for_fp_csr:
; GCN: s_waitcnt
; GCN-NEXT: v_writelane_b32 v1, s33, 63
-; GCN-NEXT: s_mov_b32 s33, s32
+; GCN-COUNT-60: v_writelane_b32 v1
+; GCN: s_mov_b32 s33, s32
+; GCN-COUNT-2: v_writelane_b32 v1
; MUBUF: buffer_store_dword v41, off, s[0:3], s33 ; 4-byte Folded Spill
; FLATSCR: scratch_store_dword off, v41, s33 ; 4-byte Folded Spill
-; GCN-COUNT-63: v_writelane_b32 v1
; MUBUF: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s33 offset:8
; FLATSCR: scratch_store_dword off, v{{[0-9]+}}, s33 offset:8
; GCN: ;;#ASMSTART
-; GCN-COUNT-63: v_readlane_b32 s{{[0-9]+}}, v1
+; GCN: v_writelane_b32 v1
; MUBUF: s_add_u32 s32, s32, 0x300
-; MUBUF-NEXT: s_sub_u32 s32, s32, 0x300
+; MUBUF: s_sub_u32 s32, s32, 0x300
; FLATSCR: s_add_u32 s32, s32, 12
-; FLATSCR-NEXT: s_sub_u32 s32, s32, 12
+; FLATSCR: s_sub_u32 s32, s32, 12
; GCN-NEXT: v_readlane_b32 s33, v1, 63
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64
; Use a copy to a free SGPR instead of introducing a second CSR VGPR.
; GCN-LABEL: {{^}}no_new_vgpr_for_fp_csr:
; GCN: s_waitcnt
-; GCN-NEXT: s_mov_b32 [[FP_COPY:s[0-9]+]], s33
+; GCN-COUNT-62: v_writelane_b32 v1,
+; GCN: s_mov_b32 [[FP_COPY:s[0-9]+]], s33
; GCN-NEXT: s_mov_b32 s33, s32
-; MUBUF-NEXT: buffer_store_dword v41, off, s[0:3], s33 ; 4-byte Folded Spill
-; FLATSCR-NEXT: scratch_store_dword off, v41, s33 ; 4-byte Folded Spill
-; GCN-COUNT-64: v_writelane_b32 v1,
-
+; GCN: v_writelane_b32 v1,
+; MUBUF: buffer_store_dword v41, off, s[0:3], s33 ; 4-byte Folded Spill
+; FLATSCR: scratch_store_dword off, v41, s33 ; 4-byte Folded Spill
; MUBUF: buffer_store_dword
; FLATSCR: scratch_store_dword
; GCN: ;;#ASMSTART
-; GCN-COUNT-64: v_readlane_b32 s{{[0-9]+}}, v1
-
+; GCN: v_writelane_b32 v1,
; MUBUF: buffer_load_dword v41, off, s[0:3], s33 ; 4-byte Folded Reload
; FLATSCR: scratch_load_dword v41, off, s33 ; 4-byte Folded Reload
; MUBUF: s_add_u32 s32, s32, 0x300
-; MUBUF-NEXT: s_sub_u32 s32, s32, 0x300
; FLATSCR: s_add_u32 s32, s32, 12
+; GCN-COUNT-64: v_readlane_b32 s{{[0-9]+}}, v1
+; MUBUF-NEXT: s_sub_u32 s32, s32, 0x300
; FLATSCR-NEXT: s_sub_u32 s32, s32, 12
; GCN-NEXT: s_mov_b32 s33, [[FP_COPY]]
; GCN-NEXT: s_waitcnt vmcnt(0)
; MUBUF: s_add_u32 s32, s32, 0x300{{$}}
; FLATSCR: s_add_u32 s32, s32, 12{{$}}
-; GCN: ;;#ASMSTART
-
; GCN: v_readlane_b32 s4, [[CSR_VGPR]], 0
-; GCN-NEXT: v_readlane_b32 s5, [[CSR_VGPR]], 1
+; GCN: ;;#ASMSTART
+; GCN: v_readlane_b32 s5, [[CSR_VGPR]], 1
; MUBUF-NEXT: s_sub_u32 s32, s32, 0x300{{$}}
; FLATSCR-NEXT: s_sub_u32 s32, s32, 12{{$}}
; GCN-NEXT: v_readlane_b32 s33, [[CSR_VGPR]], 2
; MUBUF-DAG: buffer_store_dword
; FLATSCR-DAG: scratch_store_dword
-; GCN: ;;#ASMSTART
-
; GCN: v_readlane_b32 s4, [[CSR_VGPR]], 0
-; GCN-NEXT: v_readlane_b32 s5, [[CSR_VGPR]], 1
+; GCN: ;;#ASMSTART
+; GCN: v_readlane_b32 s5, [[CSR_VGPR]], 1
; MUBUF-NEXT: s_sub_u32 s32, s32, 0x40300{{$}}
; FLATSCR-NEXT: s_sub_u32 s32, s32, 0x100c{{$}}
; GCN-NEXT: v_readlane_b32 s33, [[CSR_VGPR]], 2
; GCN-NEXT: v_writelane_b32 v40, s31, 1
; GCN-NEXT: s_swappc_b64 s[30:31], s[4:5]
; GCN-NEXT: v_readlane_b32 s4, v40, 0
-; GCN-NEXT: v_readlane_b32 s5, v40, 1
; GCN-NEXT: v_mov_b32_e32 v1, v4
+; GCN-NEXT: v_readlane_b32 s5, v40, 1
; GCN-NEXT: s_sub_u32 s32, s32, 0x400
; GCN-NEXT: v_readlane_b32 s33, v40, 2
; GCN-NEXT: s_or_saveexec_b64 s[6:7], -1
; Make sure new higher SGPRs are callee saved
; GFX10-LABEL: {{^}}callee_new_sgprs:
; GFX10: v_writelane_b32 v0, s104, 0
-; GFX10: v_writelane_b32 v0, s105, 1
-; GFX10: ; clobber s104
+; GFX10-DAG: v_writelane_b32 v0, s105, 1
+; GFX10-DAG: ; clobber s104
; GFX10: ; clobber s105
; GFX10: v_readlane_b32 s105, v0, 1
; GFX10: v_readlane_b32 s104, v0, 0
; CHECK: S_WAITCNT 0
; CHECK: S_NOP 0, implicit-def $exec_lo
; CHECK: $sgpr0 = S_MOV_B32 $exec_lo
- ; CHECK: $vgpr0 = V_WRITELANE_B32_vi killed $sgpr0, 0, undef $vgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi $vgpr0, 0
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 killed $sgpr0, 0, undef $vgpr0
+ ; CHECK: $sgpr0 = V_READLANE_B32 $vgpr0, 0
; CHECK: S_NOP 0, implicit-def dead renamable $sgpr1, implicit-def dead renamable $sgpr0, implicit killed renamable $sgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi killed $vgpr0, 0
+ ; CHECK: $sgpr0 = V_READLANE_B32 killed $vgpr0, 0
; CHECK: $exec_lo = S_MOV_B32 killed $sgpr0
; CHECK: S_SENDMSG 0, implicit $m0, implicit $exec
S_NOP 0, implicit-def $exec_lo
; CHECK: S_WAITCNT 0
; CHECK: S_NOP 0, implicit-def $exec_hi
; CHECK: $sgpr0 = S_MOV_B32 $exec_hi
- ; CHECK: $vgpr0 = V_WRITELANE_B32_vi killed $sgpr0, 0, undef $vgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi $vgpr0, 0
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 killed $sgpr0, 0, undef $vgpr0
+ ; CHECK: $sgpr0 = V_READLANE_B32 $vgpr0, 0
; CHECK: S_NOP 0, implicit-def dead renamable $sgpr1, implicit-def dead renamable $sgpr0, implicit killed renamable $sgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi killed $vgpr0, 0
+ ; CHECK: $sgpr0 = V_READLANE_B32 killed $vgpr0, 0
; CHECK: $exec_hi = S_MOV_B32 killed $sgpr0
; CHECK: S_SENDMSG 0, implicit $m0, implicit $exec
S_NOP 0, implicit-def $exec_hi
; CHECK: S_WAITCNT 0
; CHECK: S_NOP 0, implicit-def $exec
; CHECK: $sgpr0_sgpr1 = S_MOV_B64 $exec
- ; CHECK: $vgpr0 = V_WRITELANE_B32_vi killed $sgpr0, 0, undef $vgpr0
- ; CHECK: $vgpr0 = V_WRITELANE_B32_vi killed $sgpr1, 1, killed $vgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi $vgpr0, 0, implicit-def $sgpr0_sgpr1
- ; CHECK: $sgpr1 = V_READLANE_B32_vi $vgpr0, 1
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 killed $sgpr0, 0, undef $vgpr0, implicit-def $sgpr0_sgpr1, implicit $sgpr0_sgpr1
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 killed $sgpr1, 1, killed $vgpr0, implicit $sgpr0_sgpr1
+ ; CHECK: $sgpr0 = V_READLANE_B32 $vgpr0, 0, implicit-def $sgpr0_sgpr1
+ ; CHECK: $sgpr1 = V_READLANE_B32 $vgpr0, 1
; CHECK: S_NOP 0, implicit-def dead renamable $sgpr2_sgpr3, implicit-def dead renamable $sgpr0_sgpr1, implicit killed renamable $sgpr0_sgpr1
- ; CHECK: $sgpr0 = V_READLANE_B32_vi $vgpr0, 0, implicit-def $sgpr0_sgpr1
- ; CHECK: $sgpr1 = V_READLANE_B32_vi killed $vgpr0, 1
+ ; CHECK: $sgpr0 = V_READLANE_B32 $vgpr0, 0, implicit-def $sgpr0_sgpr1
+ ; CHECK: $sgpr1 = V_READLANE_B32 killed $vgpr0, 1
; CHECK: $exec = S_MOV_B64 killed $sgpr0_sgpr1
; CHECK: S_SENDMSG 0, implicit $m0, implicit $exec
S_NOP 0, implicit-def $exec
; CHECK: liveins: $vgpr0
; CHECK: S_WAITCNT 0
; CHECK: S_NOP 0, implicit-def renamable $sgpr0, implicit-def dead renamable $sgpr1, implicit-def $exec_lo
- ; CHECK: $vgpr0 = V_WRITELANE_B32_vi killed $sgpr0, 0, undef $vgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi $vgpr0, 0
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 killed $sgpr0, 0, undef $vgpr0
+ ; CHECK: $sgpr0 = V_READLANE_B32 $vgpr0, 0
; CHECK: S_NOP 0, implicit killed renamable $sgpr0, implicit-def dead renamable $sgpr1, implicit-def dead renamable $sgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi killed $vgpr0, 0
+ ; CHECK: $sgpr0 = V_READLANE_B32 killed $vgpr0, 0
; CHECK: $exec_lo = S_MOV_B32 killed $sgpr0
; CHECK: S_SENDMSG 0, implicit $m0, implicit $exec
S_NOP 0, implicit-def %0:sreg_32, implicit-def %1:sreg_32, implicit-def $exec_lo
; CHECK: liveins: $vgpr0
; CHECK: S_WAITCNT 0
; CHECK: S_NOP 0, implicit-def renamable $sgpr0, implicit-def dead renamable $sgpr1, implicit-def $exec_hi
- ; CHECK: $vgpr0 = V_WRITELANE_B32_vi killed $sgpr0, 0, undef $vgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi $vgpr0, 0
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 killed $sgpr0, 0, undef $vgpr0
+ ; CHECK: $sgpr0 = V_READLANE_B32 $vgpr0, 0
; CHECK: S_NOP 0, implicit killed renamable $sgpr0, implicit-def dead renamable $sgpr1, implicit-def dead renamable $sgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi killed $vgpr0, 0
+ ; CHECK: $sgpr0 = V_READLANE_B32 killed $vgpr0, 0
; CHECK: $exec_hi = S_MOV_B32 killed $sgpr0
; CHECK: S_SENDMSG 0, implicit $m0, implicit $exec
S_NOP 0, implicit-def %0:sreg_32, implicit-def %1:sreg_32, implicit-def $exec_hi
; CHECK: liveins: $vgpr0
; CHECK: S_WAITCNT 0
; CHECK: S_NOP 0, implicit-def renamable $sgpr0_sgpr1, implicit-def dead renamable $sgpr2_sgpr3, implicit-def $exec
- ; CHECK: $vgpr0 = V_WRITELANE_B32_vi killed $sgpr0, 0, undef $vgpr0
- ; CHECK: $vgpr0 = V_WRITELANE_B32_vi killed $sgpr1, 1, killed $vgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi $vgpr0, 0, implicit-def $sgpr0_sgpr1
- ; CHECK: $sgpr1 = V_READLANE_B32_vi $vgpr0, 1
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 killed $sgpr0, 0, undef $vgpr0, implicit-def $sgpr0_sgpr1, implicit $sgpr0_sgpr1
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 killed $sgpr1, 1, killed $vgpr0, implicit $sgpr0_sgpr1
+ ; CHECK: $sgpr0 = V_READLANE_B32 $vgpr0, 0, implicit-def $sgpr0_sgpr1
+ ; CHECK: $sgpr1 = V_READLANE_B32 $vgpr0, 1
; CHECK: S_NOP 0, implicit killed renamable $sgpr0_sgpr1, implicit-def dead renamable $sgpr2_sgpr3, implicit-def dead renamable $sgpr0_sgpr1
- ; CHECK: $sgpr0 = V_READLANE_B32_vi $vgpr0, 0, implicit-def $sgpr0_sgpr1
- ; CHECK: $sgpr1 = V_READLANE_B32_vi killed $vgpr0, 1
+ ; CHECK: $sgpr0 = V_READLANE_B32 $vgpr0, 0, implicit-def $sgpr0_sgpr1
+ ; CHECK: $sgpr1 = V_READLANE_B32 killed $vgpr0, 1
; CHECK: $exec = S_MOV_B64 killed $sgpr0_sgpr1
; CHECK: S_SENDMSG 0, implicit $m0, implicit $exec
S_NOP 0, implicit-def %0:sreg_64, implicit-def %1:sreg_64, implicit-def $exec
; CHECK: S_WAITCNT 0
; CHECK: S_NOP 0, implicit-def $m0
; CHECK: $sgpr0 = S_MOV_B32 $m0
- ; CHECK: $vgpr0 = V_WRITELANE_B32_vi killed $sgpr0, 0, undef $vgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi $vgpr0, 0
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 killed $sgpr0, 0, undef $vgpr0
+ ; CHECK: $sgpr0 = V_READLANE_B32 $vgpr0, 0
; CHECK: S_NOP 0, implicit-def dead renamable $sgpr1, implicit-def dead renamable $sgpr0, implicit killed renamable $sgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi killed $vgpr0, 0
+ ; CHECK: $sgpr0 = V_READLANE_B32 killed $vgpr0, 0
; CHECK: $m0 = S_MOV_B32 killed $sgpr0
; CHECK: S_NOP 0
; CHECK: S_SENDMSG 0, implicit $m0, implicit $exec
; CHECK: liveins: $vgpr0
; CHECK: S_WAITCNT 0
; CHECK: S_NOP 0, implicit-def renamable $sgpr0, implicit-def dead renamable $sgpr1, implicit-def $m0
- ; CHECK: $vgpr0 = V_WRITELANE_B32_vi killed $sgpr0, 0, undef $vgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi $vgpr0, 0
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 killed $sgpr0, 0, undef $vgpr0
+ ; CHECK: $sgpr0 = V_READLANE_B32 $vgpr0, 0
; CHECK: S_NOP 0, implicit killed renamable $sgpr0, implicit-def dead renamable $sgpr1, implicit-def dead renamable $sgpr0
- ; CHECK: $sgpr0 = V_READLANE_B32_vi killed $vgpr0, 0
+ ; CHECK: $sgpr0 = V_READLANE_B32 killed $vgpr0, 0
; CHECK: $m0 = S_MOV_B32 killed $sgpr0
; CHECK: S_NOP 0
; CHECK: S_SENDMSG 0, implicit $m0, implicit $exec
; GFX9-NEXT: v_writelane_b32 v43, s33, 4
; GFX9-NEXT: s_mov_b32 s33, s32
; GFX9-NEXT: s_add_u32 s32, s32, 0x800
-; GFX9-NEXT: buffer_store_dword v40, off, s[0:3], s33 offset:8 ; 4-byte Folded Spill
-; GFX9-NEXT: buffer_store_dword v41, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
-; GFX9-NEXT: buffer_store_dword v42, off, s[0:3], s33 ; 4-byte Folded Spill
; GFX9-NEXT: v_writelane_b32 v43, s34, 0
; GFX9-NEXT: s_getpc_b64 s[4:5]
; GFX9-NEXT: s_add_u32 s4, s4, foo@gotpcrel32@lo+4
; GFX9-NEXT: s_addc_u32 s5, s5, foo@gotpcrel32@hi+12
; GFX9-NEXT: v_writelane_b32 v43, s35, 1
; GFX9-NEXT: s_load_dwordx2 s[34:35], s[4:5], 0x0
+; GFX9-NEXT: s_waitcnt lgkmcnt(0)
+; GFX9-NEXT: buffer_store_dword v40, off, s[0:3], s33 offset:8 ; 4-byte Folded Spill
+; GFX9-NEXT: buffer_store_dword v41, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
+; GFX9-NEXT: buffer_store_dword v42, off, s[0:3], s33 ; 4-byte Folded Spill
; GFX9-NEXT: v_mov_b32_e32 v40, v1
; GFX9-NEXT: v_mov_b32_e32 v41, v0
; GFX9-NEXT: v_writelane_b32 v43, s30, 2
; GFX9-NEXT: v_mul_u32_u24_e32 v0, v41, v40
; GFX9-NEXT: v_writelane_b32 v43, s31, 3
; GFX9-NEXT: v_and_b32_e32 v42, 0xffffff, v40
-; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: s_swappc_b64 s[30:31], s[34:35]
; GFX9-NEXT: v_mad_u32_u24 v40, v41, v40, v42
; GFX9-NEXT: v_mov_b32_e32 v0, v40
; GFX9-NEXT: s_swappc_b64 s[30:31], s[34:35]
; GFX9-NEXT: v_add_u32_e32 v0, v40, v42
; GFX9-NEXT: s_swappc_b64 s[30:31], s[34:35]
+; GFX9-NEXT: buffer_load_dword v42, off, s[0:3], s33 ; 4-byte Folded Reload
+; GFX9-NEXT: buffer_load_dword v41, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
+; GFX9-NEXT: buffer_load_dword v40, off, s[0:3], s33 offset:8 ; 4-byte Folded Reload
; GFX9-NEXT: v_readlane_b32 s4, v43, 2
; GFX9-NEXT: v_readlane_b32 s5, v43, 3
; GFX9-NEXT: v_readlane_b32 s35, v43, 1
; GFX9-NEXT: v_readlane_b32 s34, v43, 0
-; GFX9-NEXT: buffer_load_dword v42, off, s[0:3], s33 ; 4-byte Folded Reload
-; GFX9-NEXT: buffer_load_dword v41, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
-; GFX9-NEXT: buffer_load_dword v40, off, s[0:3], s33 offset:8 ; 4-byte Folded Reload
; GFX9-NEXT: s_sub_u32 s32, s32, 0x800
; GFX9-NEXT: v_readlane_b32 s33, v43, 4
; GFX9-NEXT: s_or_saveexec_b64 s[6:7], -1
; GFX8-LABEL: name: pei_scavenge_vgpr_spill
; GFX8: 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
- ; GFX8: $vgpr2 = V_WRITELANE_B32_vi $sgpr33, 0, undef $vgpr2
+ ; GFX8: $vgpr2 = V_WRITELANE_B32 $sgpr33, 0, undef $vgpr2
; GFX8: $sgpr4 = frame-setup S_ADD_U32 $sgpr32, 524224, implicit-def $scc
; GFX8: $sgpr33 = frame-setup S_AND_B32 killed $sgpr4, 4294443008, implicit-def $scc
; GFX8: $sgpr32 = frame-setup S_ADD_U32 $sgpr32, 1572864, implicit-def $scc
; GFX8: $vgpr3, dead $vcc = V_ADD_CO_U32_e64 killed $vcc_lo, killed $vgpr3, 0, implicit $exec
; GFX8: $vgpr0 = V_OR_B32_e32 killed $vgpr3, $vgpr1, implicit $exec
; GFX8: $sgpr32 = frame-destroy S_SUB_U32 $sgpr32, 1572864, implicit-def $scc
- ; GFX8: $sgpr33 = V_READLANE_B32_vi $vgpr2, 0
+ ; GFX8: $sgpr33 = V_READLANE_B32 $vgpr2, 0
; GFX8: $sgpr4 = S_ADD_U32 $sgpr33, 524544, implicit-def $scc
; GFX8: $vgpr3 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, killed $sgpr4, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.3, addrspace 5)
; GFX8: S_ENDPGM 0, csr_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: $vgpr2 = V_WRITELANE_B32_vi $sgpr33, 0, undef $vgpr2
+ ; GFX9: $vgpr2 = V_WRITELANE_B32 $sgpr33, 0, undef $vgpr2
; GFX9: $sgpr4 = frame-setup S_ADD_U32 $sgpr32, 524224, implicit-def $scc
; GFX9: $sgpr33 = frame-setup S_AND_B32 killed $sgpr4, 4294443008, implicit-def $scc
; GFX9: $sgpr32 = frame-setup S_ADD_U32 $sgpr32, 1572864, implicit-def $scc
; GFX9: $vgpr3 = V_ADD_U32_e32 8192, killed $vgpr3, implicit $exec
; GFX9: $vgpr0 = V_OR_B32_e32 killed $vgpr3, $vgpr1, implicit $exec
; GFX9: $sgpr32 = frame-destroy S_SUB_U32 $sgpr32, 1572864, implicit-def $scc
- ; GFX9: $sgpr33 = V_READLANE_B32_vi $vgpr2, 0
+ ; GFX9: $sgpr33 = V_READLANE_B32 $vgpr2, 0
; GFX9: $sgpr4 = S_ADD_U32 $sgpr33, 524544, implicit-def $scc
; GFX9: $vgpr3 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, killed $sgpr4, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.3, addrspace 5)
; GFX9: S_ENDPGM 0, csr_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: $vgpr2 = V_WRITELANE_B32_vi $sgpr33, 0, undef $vgpr2
+ ; GFX9-FLATSCR: $vgpr2 = V_WRITELANE_B32 $sgpr33, 0, undef $vgpr2
; GFX9-FLATSCR: $sgpr4 = frame-setup S_ADD_U32 $sgpr32, 8191, implicit-def $scc
; GFX9-FLATSCR: $sgpr33 = frame-setup S_AND_B32 killed $sgpr4, 4294959104, implicit-def $scc
; GFX9-FLATSCR: $sgpr32 = frame-setup S_ADD_U32 $sgpr32, 24576, implicit-def $scc
; GFX9-FLATSCR: $vcc_hi = S_ADD_U32 $sgpr33, 8192, implicit-def $scc
; GFX9-FLATSCR: $vgpr0 = V_OR_B32_e32 killed $vcc_hi, $vgpr1, implicit $exec
; GFX9-FLATSCR: $sgpr32 = frame-destroy S_SUB_U32 $sgpr32, 24576, implicit-def $scc
- ; GFX9-FLATSCR: $sgpr33 = V_READLANE_B32_vi $vgpr2, 0
+ ; GFX9-FLATSCR: $sgpr33 = V_READLANE_B32 $vgpr2, 0
; GFX9-FLATSCR: S_ENDPGM 0, csr_amdgpu_allvgprs
$vgpr0 = V_OR_B32_e32 %stack.1, $vgpr1, implicit $exec
S_ENDPGM 0, csr_amdgpu_allvgprs
; CHECK-LABEL: name: sgpr_spill_s64_undef_high32
; CHECK: liveins: $sgpr4, $vgpr0
- ; CHECK: $vgpr0 = V_WRITELANE_B32_gfx6_gfx7 $sgpr4, 0, undef $vgpr0, implicit-def $sgpr4_sgpr5
- ; CHECK: $vgpr0 = V_WRITELANE_B32_gfx6_gfx7 $sgpr5, 1, $vgpr0
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 $sgpr4, 0, undef $vgpr0, implicit-def $sgpr4_sgpr5, implicit $sgpr4_sgpr5
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 $sgpr5, 1, $vgpr0, implicit $sgpr4_sgpr5
SI_SPILL_S64_SAVE renamable $sgpr4_sgpr5, %stack.0, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32 :: (store 8 into %stack.0, align 4, addrspace 5)
...
; CHECK-LABEL: name: sgpr_spill_s64_undef_low32
; CHECK: liveins: $sgpr5, $vgpr0
- ; CHECK: $vgpr0 = V_WRITELANE_B32_gfx6_gfx7 $sgpr4, 0, undef $vgpr0, implicit-def $sgpr4_sgpr5
- ; CHECK: $vgpr0 = V_WRITELANE_B32_gfx6_gfx7 $sgpr5, 1, $vgpr0
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 $sgpr4, 0, undef $vgpr0, implicit-def $sgpr4_sgpr5, implicit $sgpr4_sgpr5
+ ; CHECK: $vgpr0 = V_WRITELANE_B32 $sgpr5, 1, $vgpr0, implicit $sgpr4_sgpr5
SI_SPILL_S64_SAVE renamable $sgpr4_sgpr5, %stack.0, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32 :: (store 8 into %stack.0, align 4, addrspace 5)
...
; GCN: s_swappc_b64
-; GCN-DAG: v_readlane_b32 s34, v42, 0
-; GCN-DAG: v_readlane_b32 s35, v42, 1
-
-; GCN: buffer_load_dword v41, off, s[0:3], s33 ; 4-byte Folded Reload
-; GCN: buffer_load_dword v40, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
+; GCN-DAG: buffer_load_dword v41, off, s[0:3], s33 ; 4-byte Folded Reload
+; GCN-DAG: buffer_load_dword v40, off, s[0:3], s33 offset:4 ; 4-byte Folded Reload
; GCN: s_getpc_b64 s[4:5]
; GCN-NEXT: s_add_u32 s4, s4, sibling_call_i32_fastcc_i32_i32@rel32@lo+4
; GCN-NEXT: s_addc_u32 s5, s5, sibling_call_i32_fastcc_i32_i32@rel32@hi+12
+; GCN-DAG: v_readlane_b32 s34, v42, 0
+; GCN-DAG: v_readlane_b32 s35, v42, 1
+
; GCN: s_sub_u32 s32, s32, 0x400
; GCN-NEXT: v_readlane_b32 s33,
; GCN-NEXT: s_or_saveexec_b64 s[6:7], -1
S_ENDPGM 0
...
-# Workaround since spilling/restoring SGPRs use real opcodes.
-# GCN-LABEL: name: hazard_smem_war_readlane_gfx10
-# GCN: S_LOAD_DWORD_IMM
-# GCN: $sgpr_null = S_MOV_B32 0
-# GCN-NEXT: V_READLANE_B32_gfx10
----
-name: hazard_smem_war_readlane_gfx10
-body: |
- bb.0:
- liveins: $sgpr0, $sgpr1, $sgpr3, $vgpr0
- $sgpr2 = S_LOAD_DWORD_IMM $sgpr0_sgpr1, 0, 0, 0
- $sgpr0 = V_READLANE_B32_gfx10 $vgpr0, $sgpr3
- S_ENDPGM 0
-...
-
# GCN-LABEL: name: hazard_smem_war_readfirstlane
# GCN: S_LOAD_DWORD_IMM
# GCN: $sgpr_null = S_MOV_B32 0
; GCN-LABEL: name: spill_sgpr128_use_subreg
; GCN: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $vgpr0, $vgpr1, $vgpr2, $vgpr3
; GCN: renamable $sgpr1 = COPY $sgpr2
- ; GCN: $vgpr0 = V_WRITELANE_B32_vi $sgpr0, 0, undef $vgpr0, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3
- ; GCN: $vgpr0 = V_WRITELANE_B32_vi $sgpr1, 1, $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3
- ; GCN: $vgpr0 = V_WRITELANE_B32_vi $sgpr2, 2, $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3
- ; GCN: $vgpr0 = V_WRITELANE_B32_vi $sgpr3, 3, $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GCN: $vgpr0 = V_WRITELANE_B32 $sgpr0, 0, undef $vgpr0, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GCN: $vgpr0 = V_WRITELANE_B32 $sgpr1, 1, $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GCN: $vgpr0 = V_WRITELANE_B32 $sgpr2, 2, $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GCN: $vgpr0 = V_WRITELANE_B32 $sgpr3, 3, $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3
; GCN: renamable $sgpr8 = COPY killed renamable $sgpr1
; GCN: S_ENDPGM 0, implicit $sgpr8
renamable $sgpr1 = COPY $sgpr2
; GCN-LABEL: name: spill_sgpr128_use_kill
; GCN: liveins: $sgpr0, $sgpr1, $sgpr2, $sgpr3, $sgpr4, $sgpr5, $sgpr6, $sgpr7, $vgpr0, $vgpr1, $vgpr2, $vgpr3
; GCN: renamable $sgpr1 = COPY $sgpr2
- ; GCN: $vgpr0 = V_WRITELANE_B32_vi $sgpr0, 0, undef $vgpr0, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3
- ; GCN: $vgpr0 = V_WRITELANE_B32_vi $sgpr1, 1, $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3
- ; GCN: $vgpr0 = V_WRITELANE_B32_vi $sgpr2, 2, $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3
- ; GCN: $vgpr0 = V_WRITELANE_B32_vi killed $sgpr3, 3, $vgpr0, implicit killed $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GCN: $vgpr0 = V_WRITELANE_B32 $sgpr0, 0, undef $vgpr0, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GCN: $vgpr0 = V_WRITELANE_B32 $sgpr1, 1, $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GCN: $vgpr0 = V_WRITELANE_B32 $sgpr2, 2, $vgpr0, implicit $sgpr0_sgpr1_sgpr2_sgpr3
+ ; GCN: $vgpr0 = V_WRITELANE_B32 killed $sgpr3, 3, $vgpr0, implicit killed $sgpr0_sgpr1_sgpr2_sgpr3
; GCN: S_ENDPGM 0
renamable $sgpr1 = COPY $sgpr2
SI_SPILL_S128_SAVE renamable killed $sgpr0_sgpr1_sgpr2_sgpr3, %stack.0, implicit $exec, implicit $sgpr100_sgpr101_sgpr102_sgpr103, implicit $sgpr32 :: (store 16 into %stack.0, align 4, addrspace 5)
bb.0:
liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7
- ; CHECK-LABEL: name: check_vcc
- ; CHECK: liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr9
-
+ ; GFX9-LABEL: name: check_vcc
+ ; GFX9: liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr9
; GFX9: $sgpr33 = S_MOV_B32 0
; GFX9: $sgpr12 = S_MOV_B32 &SCRATCH_RSRC_DWORD0, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
; GFX9: $sgpr13 = S_MOV_B32 &SCRATCH_RSRC_DWORD1, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
; GFX9: $sgpr12 = S_ADD_U32 $sgpr12, $sgpr9, implicit-def $scc, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
; GFX9: $sgpr13 = S_ADDC_U32 $sgpr13, 0, implicit-def $scc, implicit $scc, implicit-def $sgpr12_sgpr13_sgpr14_sgpr15
; GFX9: $vcc = IMPLICIT_DEF
- ; GFX9: $vgpr0 = V_WRITELANE_B32_vi $vcc_lo, 0, undef $vgpr0, implicit $vcc
- ; GFX9: $vgpr0 = V_WRITELANE_B32_vi $vcc_hi, 1, $vgpr0, implicit $vcc
+ ; GFX9: $vgpr0 = V_WRITELANE_B32 $vcc_lo, 0, undef $vgpr0, implicit $vcc
+ ; GFX9: $vgpr0 = V_WRITELANE_B32 $vcc_hi, 1, $vgpr0, implicit $vcc
; GFX9: $vcc = S_MOV_B64 $exec
; GFX9: $exec = S_MOV_B64 3
; GFX9: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
; GFX9: $exec = S_MOV_B64 $vcc
- ; GFX9: $vcc_hi = V_READLANE_B32_vi $vgpr0, 1
- ; GFX9: $vcc_lo = V_READLANE_B32_vi killed $vgpr0, 0
+ ; GFX9: $vcc_hi = V_READLANE_B32 $vgpr0, 1
+ ; GFX9: $vcc_lo = V_READLANE_B32 killed $vgpr0, 0
; GFX9: $vcc = IMPLICIT_DEF
- ; GFX9: $vgpr0 = V_WRITELANE_B32_vi $vcc_lo, 0, undef $vgpr0, implicit $vcc
- ; GFX9: $vgpr0 = V_WRITELANE_B32_vi $vcc_hi, 1, $vgpr0, implicit killed $vcc
+ ; GFX9: $vgpr0 = V_WRITELANE_B32 $vcc_lo, 0, undef $vgpr0, implicit $vcc
+ ; GFX9: $vgpr0 = V_WRITELANE_B32 $vcc_hi, 1, $vgpr0, implicit killed $vcc
; GFX9: $vcc = S_MOV_B64 $exec
; GFX9: $exec = S_MOV_B64 3
; GFX9: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
; GFX9: $exec = S_MOV_B64 3
; GFX9: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr12_sgpr13_sgpr14_sgpr15, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.0, addrspace 5)
; GFX9: $exec = S_MOV_B64 killed $vcc
- ; GFX9: $vcc_lo = V_READLANE_B32_vi $vgpr0, 0, implicit-def $vcc
- ; GFX9: $vcc_hi = V_READLANE_B32_vi killed $vgpr0, 1
-
+ ; GFX9: $vcc_lo = V_READLANE_B32 $vgpr0, 0, implicit-def $vcc
+ ; GFX9: $vcc_hi = V_READLANE_B32 killed $vgpr0, 1
+ ; GFX10-LABEL: name: check_vcc
+ ; GFX10: liveins: $sgpr8, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr9
; GFX10: $sgpr33 = S_MOV_B32 0
; GFX10: $sgpr96 = S_MOV_B32 &SCRATCH_RSRC_DWORD0, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
; GFX10: $sgpr97 = S_MOV_B32 &SCRATCH_RSRC_DWORD1, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
; GFX10: $sgpr96 = S_ADD_U32 $sgpr96, $sgpr9, implicit-def $scc, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
; GFX10: $sgpr97 = S_ADDC_U32 $sgpr97, 0, implicit-def $scc, implicit $scc, implicit-def $sgpr96_sgpr97_sgpr98_sgpr99
; GFX10: $vcc = IMPLICIT_DEF
- ; GFX10: $vgpr0 = V_WRITELANE_B32_gfx10 $vcc_lo, 0, undef $vgpr0, implicit $vcc
- ; GFX10: $vgpr0 = V_WRITELANE_B32_gfx10 $vcc_hi, 1, $vgpr0, implicit $vcc
+ ; GFX10: $vgpr0 = V_WRITELANE_B32 $vcc_lo, 0, undef $vgpr0, implicit $vcc
+ ; GFX10: $vgpr0 = V_WRITELANE_B32 $vcc_hi, 1, $vgpr0, implicit $vcc
; GFX10: $vcc = S_MOV_B64 $exec
; GFX10: $exec = S_MOV_B64 3
; GFX10: BUFFER_STORE_DWORD_OFFSET $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
; GFX10: $exec = S_MOV_B64 $vcc
- ; GFX10: $vcc_hi = V_READLANE_B32_gfx10 $vgpr0, 1
- ; GFX10: $vcc_lo = V_READLANE_B32_gfx10 killed $vgpr0, 0
+ ; GFX10: $vcc_hi = V_READLANE_B32 $vgpr0, 1
+ ; GFX10: $vcc_lo = V_READLANE_B32 killed $vgpr0, 0
; GFX10: $vcc = IMPLICIT_DEF
- ; GFX10: $vgpr0 = V_WRITELANE_B32_gfx10 $vcc_lo, 0, undef $vgpr0, implicit $vcc
- ; GFX10: $vgpr0 = V_WRITELANE_B32_gfx10 $vcc_hi, 1, $vgpr0, implicit killed $vcc
+ ; GFX10: $vgpr0 = V_WRITELANE_B32 $vcc_lo, 0, undef $vgpr0, implicit $vcc
+ ; GFX10: $vgpr0 = V_WRITELANE_B32 $vcc_hi, 1, $vgpr0, implicit killed $vcc
; GFX10: $vcc = S_MOV_B64 $exec
; GFX10: $exec = S_MOV_B64 3
; GFX10: BUFFER_STORE_DWORD_OFFSET killed $vgpr0, $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (store 4 into %stack.0, addrspace 5)
; GFX10: $exec = S_MOV_B64 3
; GFX10: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr96_sgpr97_sgpr98_sgpr99, $sgpr33, 4, 0, 0, 0, 0, 0, implicit $exec :: (load 4 from %stack.0, addrspace 5)
; GFX10: $exec = S_MOV_B64 killed $vcc
- ; GFX10: $vcc_lo = V_READLANE_B32_gfx10 $vgpr0, 0, implicit-def $vcc
- ; GFX10: $vcc_hi = V_READLANE_B32_gfx10 killed $vgpr0, 1
+ ; GFX10: $vcc_lo = V_READLANE_B32 $vgpr0, 0, implicit-def $vcc
+ ; GFX10: $vcc_hi = V_READLANE_B32 killed $vgpr0, 1
$vcc = IMPLICIT_DEF
SI_SPILL_S64_SAVE $vcc, %stack.0, implicit $exec, implicit $sgpr96_sgpr97_sgpr98_sgpr99, implicit $sgpr32
; EXPANDED: successors: %bb.1(0x80000000)
; EXPANDED: liveins: $vgpr0
; EXPANDED: S_NOP 0, implicit-def renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
- ; EXPANDED: $vgpr0 = V_WRITELANE_B32_gfx6_gfx7 $sgpr4, 0, undef $vgpr0, implicit-def $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9, implicit $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
- ; EXPANDED: $vgpr0 = V_WRITELANE_B32_gfx6_gfx7 $sgpr5, 1, $vgpr0, implicit $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
- ; EXPANDED: $vgpr0 = V_WRITELANE_B32_gfx6_gfx7 $sgpr6, 2, $vgpr0, implicit $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
- ; EXPANDED: $vgpr0 = V_WRITELANE_B32_gfx6_gfx7 $sgpr7, 3, $vgpr0, implicit $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
- ; EXPANDED: $vgpr0 = V_WRITELANE_B32_gfx6_gfx7 $sgpr8, 4, $vgpr0, implicit $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
- ; EXPANDED: $vgpr0 = V_WRITELANE_B32_gfx6_gfx7 killed $sgpr9, 5, $vgpr0, implicit killed $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
+ ; EXPANDED: $vgpr0 = V_WRITELANE_B32 $sgpr4, 0, undef $vgpr0, implicit-def $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9, implicit $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
+ ; EXPANDED: $vgpr0 = V_WRITELANE_B32 $sgpr5, 1, $vgpr0, implicit $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
+ ; EXPANDED: $vgpr0 = V_WRITELANE_B32 $sgpr6, 2, $vgpr0, implicit $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
+ ; EXPANDED: $vgpr0 = V_WRITELANE_B32 $sgpr7, 3, $vgpr0, implicit $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
+ ; EXPANDED: $vgpr0 = V_WRITELANE_B32 $sgpr8, 4, $vgpr0, implicit $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
+ ; EXPANDED: $vgpr0 = V_WRITELANE_B32 killed $sgpr9, 5, $vgpr0, implicit killed $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
; EXPANDED: S_CBRANCH_SCC1 %bb.1, implicit undef $scc
; EXPANDED: bb.1:
; EXPANDED: successors: %bb.2(0x80000000)
; EXPANDED: S_NOP 1
; EXPANDED: bb.2:
; EXPANDED: liveins: $vgpr0
- ; EXPANDED: $sgpr4 = V_READLANE_B32_gfx6_gfx7 $vgpr0, 0, implicit-def $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
- ; EXPANDED: $sgpr5 = V_READLANE_B32_gfx6_gfx7 $vgpr0, 1
- ; EXPANDED: $sgpr6 = V_READLANE_B32_gfx6_gfx7 $vgpr0, 2
- ; EXPANDED: $sgpr7 = V_READLANE_B32_gfx6_gfx7 $vgpr0, 3
- ; EXPANDED: $sgpr8 = V_READLANE_B32_gfx6_gfx7 $vgpr0, 4
- ; EXPANDED: $sgpr9 = V_READLANE_B32_gfx6_gfx7 $vgpr0, 5
+ ; EXPANDED: $sgpr4 = V_READLANE_B32 $vgpr0, 0, implicit-def $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
+ ; EXPANDED: $sgpr5 = V_READLANE_B32 $vgpr0, 1
+ ; EXPANDED: $sgpr6 = V_READLANE_B32 $vgpr0, 2
+ ; EXPANDED: $sgpr7 = V_READLANE_B32 $vgpr0, 3
+ ; EXPANDED: $sgpr8 = V_READLANE_B32 $vgpr0, 4
+ ; EXPANDED: $sgpr9 = V_READLANE_B32 $vgpr0, 5
; EXPANDED: S_NOP 0, implicit killed renamable $sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9
bb.0:
S_NOP 0, implicit-def %0:sgpr_192
; RUN: llc -mtriple amdgcn-amd-amdhsa -mcpu=gfx803 -verify-machineinstrs < %s | FileCheck -enable-var-scope %s
; CHECK-LABEL: {{^}}spill_more_than_wavesize_csr_sgprs:
-; CHECK: v_writelane_b32 v0, s98, 63
-; CHECK-NEXT: v_writelane_b32 v1, s99, 0
-; CHECK: v_readlane_b32 s99, v1, 0
-; CHECK-NEXT: v_readlane_b32 s98, v0, 63
+; CHECK-DAG: v_writelane_b32 v0, s98, 63
+; CHECK-DAG: v_writelane_b32 v1, s99, 0
+; CHECK-NOT: dummy
+; CHECK-DAG: v_readlane_b32 s99, v1, 0
+; CHECK-DAG: v_readlane_b32 s98, v0, 63
define void @spill_more_than_wavesize_csr_sgprs() {
call void asm sideeffect "",
}
; CHECK-LABEL: {{^}}spill_more_than_wavesize_csr_sgprs_with_stack_object:
-; CHECK: v_writelane_b32 v1, s98, 63
-; CHECK-NEXT: v_writelane_b32 v2, s99, 0
-; CHECK: v_readlane_b32 s99, v2, 0
-; CHECK-NEXT: v_readlane_b32 s98, v1, 63
+; CHECK-DAG: v_writelane_b32 v1, s98, 63
+; CHECK-DAG: v_writelane_b32 v2, s99, 0
+; CHECK-NOT: dummy
+; CHECK-DAG: v_readlane_b32 s99, v2, 0
+; CHECK-DAG: v_readlane_b32 s98, v1, 63
define void @spill_more_than_wavesize_csr_sgprs_with_stack_object() {
%alloca = alloca i32, align 4, addrspace(5)
; GCN: buffer_store_dword [[VGPR_REG:v[0-9]+]], off, s[0:3], s32 offset:1028 ; 4-byte Folded Spill
; GCN-NEXT: s_mov_b64 exec, s[4:5]
; GCN-NEXT: v_writelane_b32 [[VGPR_REG]], s33, 2
-; GCN-NEXT: v_writelane_b32 [[VGPR_REG]], s34, 3
-; GCN: s_add_u32 [[SCRATCH_REG:s[0-9]+]], s32, 0xffc0
+; GCN-DAG: v_writelane_b32 [[VGPR_REG]], s34, 3
+; GCN-DAG: s_add_u32 [[SCRATCH_REG:s[0-9]+]], s32, 0xffc0
; GCN: s_and_b32 s33, [[SCRATCH_REG]], 0xffff0000
; GCN: s_mov_b32 s34, s32
; GCN: v_mov_b32_e32 v32, 0
; GCN: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s32
; GCN-NEXT: s_swappc_b64 s[30:31], s[4:5]
-; GCN: v_readlane_b32 s33, [[VGPR_REG]], 2
-; GCN-NEXT: s_sub_u32 s32, s32, 0x30000
+; GCN: s_sub_u32 s32, s32, 0x30000
+; GCN-NEXT: v_readlane_b32 s33, [[VGPR_REG]], 2
; GCN-NEXT: v_readlane_b32 s34, [[VGPR_REG]], 3
; GCN-NEXT: s_or_saveexec_b64 s[6:7], -1
; GCN-NEXT: buffer_load_dword [[VGPR_REG]], off, s[0:3], s32 offset:1028 ; 4-byte Folded Reload
; GCN: v_writelane_b32 [[VGPR_REG:v[0-9]+]], s34, 0
; GCN-NEXT: s_mov_b32 s34, s32
; GCN-NEXT: buffer_load_dword v{{[0-9]+}}, off, s[0:3], s34
+; GCN: v_readlane_b32 s34, [[VGPR_REG:v[0-9]+]], 0
; GCN: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s33 offset:128
; GCN-NEXT: ;;#ASMSTART
; GCN-NEXT: ;;#ASMEND
-; GCN: v_readlane_b32 s34, [[VGPR_REG:v[0-9]+]], 0
-; GCN-NEXT: s_waitcnt vmcnt(0)
+; GCN: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64 s[30:31]
%local_val = alloca i32, align 128, addrspace(5)
store volatile i32 %b, i32 addrspace(5)* %local_val, align 128
# instructions to fix vccz.
# CHECK-LABEL: name: reload_vcc_from_vgpr
-# CHECK: $vcc_lo = V_READLANE_B32_vi $vgpr0, 8, implicit-def $vcc
-# CHECK: $vcc_hi = V_READLANE_B32_vi $vgpr0, 9
+# CHECK: $vcc_lo = V_READLANE_B32 $vgpr0, 8, implicit-def $vcc
+# CHECK: $vcc_hi = V_READLANE_B32 $vgpr0, 9
# SI: $vcc = S_MOV_B64 $vcc
# GFX9: $vcc = S_MOV_B64 $vcc
# CHECK-NEXT: S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
name: reload_vcc_from_vgpr
body: |
bb.0:
- $vcc_lo = V_READLANE_B32_vi $vgpr0, 8, implicit-def $vcc
- $vcc_hi = V_READLANE_B32_vi $vgpr0, 9
+ $vcc_lo = V_READLANE_B32 $vgpr0, 8, implicit-def $vcc
+ $vcc_hi = V_READLANE_B32 $vgpr0, 9
S_CBRANCH_VCCNZ %bb.1, implicit killed $vcc
bb.1:
; GFX9-NEXT: buffer_store_dword v42, off, s[0:3], s33 offset:4 ; 4-byte Folded Spill
; GFX9-NEXT: buffer_store_dword v43, off, s[0:3], s33 ; 4-byte Folded Spill
-; GFX9: v_writelane_b32 v44, s30, 0
-; GFX9-NEXT: v_mov_b32_e32 v36, v16
+; GFX9: v_mov_b32_e32 v36, v16
; GFX9-NEXT: v_mov_b32_e32 v35, v15
; GFX9-NEXT: v_mov_b32_e32 v34, v14
; GFX9-NEXT: v_mov_b32_e32 v33, v13
; GFX9-NEXT: v_mov_b32_e32 v32, v12
-
; GFX9: ;;#ASMSTART
; GFX9-NEXT: ;;#ASMEND
-
; GFX9: image_gather4_c_b_cl v[40:43], v[32:39], s[4:11], s[4:7] dmask:0x1
; GFX9-NEXT: s_getpc_b64 s[4:5]
; GFX9-NEXT: s_add_u32 s4, s4, extern_func@gotpcrel32@lo+4
; GFX9-NEXT: s_addc_u32 s5, s5, extern_func@gotpcrel32@hi+12
; GFX9-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
-; GFX9-NEXT: s_waitcnt lgkmcnt(0)
+; GFX9-NEXT: v_writelane_b32 v44, s30, 0
+; GFX9: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: s_swappc_b64 s[30:31], s[4:5]
; GFX9: buffer_load_dword v43, off, s[0:3], s33 ; 4-byte Folded Reload
; GFX10-NEXT: s_getpc_b64 s[4:5]
; GFX10-NEXT: s_add_u32 s4, s4, extern_func@gotpcrel32@lo+4
; GFX10-NEXT: s_addc_u32 s5, s5, extern_func@gotpcrel32@hi+12
+; GFX10: s_load_dwordx2 s[4:5], s[4:5], 0x0
; GFX10-NEXT: ; implicit-def: $vcc_hi
-; GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
-; GFX10-NEXT: s_waitcnt lgkmcnt(0)
+; GFX10: s_waitcnt lgkmcnt(0)
; GFX10-NEXT: s_swappc_b64 s[30:31], s[4:5]
; GFX10: buffer_load_dword v43, off, s[0:3], s33
; GFX9-NEXT: s_add_u32 s4, s4, extern_func@gotpcrel32@lo+4
; GFX9-NEXT: s_addc_u32 s5, s5, extern_func@gotpcrel32@hi+12
; GFX9-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
-; GFX9-NEXT: s_waitcnt vmcnt(0)
+; GFX9: s_waitcnt vmcnt(0)
; GFX9-NEXT: global_store_dwordx4 v[0:1], v[0:3], off
; GFX9-NEXT: s_waitcnt lgkmcnt(0)
; GFX9-NEXT: s_swappc_b64 s[30:31], s[4:5]
; GFX10-NEXT: s_getpc_b64 s[4:5]
; GFX10-NEXT: s_add_u32 s4, s4, extern_func@gotpcrel32@lo+4
; GFX10-NEXT: s_addc_u32 s5, s5, extern_func@gotpcrel32@hi+12
-; GFX10-NEXT: v_mov_b32_e32 v41, v15
+; GFX10-NEXT: v_mov_b32_e32 v40, v16
; GFX10-NEXT: s_load_dwordx2 s[4:5], s[4:5], 0x0
+; GFX10-NEXT: v_mov_b32_e32 v41, v15
; GFX10-NEXT: v_mov_b32_e32 v42, v14
; GFX10-NEXT: v_mov_b32_e32 v43, v13
; GFX10-NEXT: v_mov_b32_e32 v44, v12