maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

AMDGPU: Replace shrunk instruction with dummy implicit_def 

This was broken if the original operand was killed. The kill flag
would appear on both instructions, and fail the verifier. Keep the
kill flag, but remove the operands from the old instruction. This has
an added benefit of really reducing the use count for future folds.

Ideally the pass would be structured more like what PeepholeOptimizer
does to avoid this hack to avoid breaking instruction iterators.

llvm-svn: 359891
This commit is contained in:
Matt Arsenault 2019-05-03 14:40:10 +00:00
parent bc876df3a5
commit 0446fbe45e
2 changed files with 64 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
View File

@ -233,8 +233,6 @@ static bool updateOperand(FoldCandidate &Fold,
const TargetRegisterClass *Dst0RC = MRI.getRegClass(Dst0.getReg());
unsigned NewReg0 = MRI.createVirtualRegister(Dst0RC);
const TargetRegisterClass *Dst1RC = MRI.getRegClass(Dst1.getReg());
unsigned NewReg1 = MRI.createVirtualRegister(Dst1RC);
MachineInstr *Inst32 = TII.buildShrunkInst(*MI, Op32);
@ -244,9 +242,15 @@ static bool updateOperand(FoldCandidate &Fold,
}
// Keep the old instruction around to avoid breaking iterators, but
// replace the outputs with dummy registers.
// replace it with a dummy instruction to remove uses.
//
// FIXME: We should not invert how this pass looks at operands to avoid
// this. Should track set of foldable movs instead of looking for uses
// when looking at a use.
Dst0.setReg(NewReg0);
Dst1.setReg(NewReg1);
for (unsigned I = MI->getNumOperands() - 1; I > 0; --I)
MI->RemoveOperand(I);
MI->setDesc(TII.get(AMDGPU::IMPLICIT_DEF));
if (Fold.isCommuted())
TII.commuteInstruction(*Inst32, false);

56
llvm/test/CodeGen/AMDGPU/fold-immediate-operand-shrink.mir
View File

@ -590,3 +590,59 @@ body: |
S_ENDPGM 0, implicit %2
...
---
name: shrink_add_kill_flags_src0
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GCN-LABEL: name: shrink_add_kill_flags_src0
; GCN: liveins: $vgpr0
; GCN: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 518144, implicit $exec
; GCN: [[V_ADD_I32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_I32_e32 killed [[V_MOV_B32_e32_]], [[COPY]], implicit-def $vcc, implicit $exec
; GCN: S_ENDPGM 0, implicit [[V_ADD_I32_e32_]]
%0:vgpr_32 = COPY $vgpr0
%1:vgpr_32 = V_MOV_B32_e32 518144, implicit $exec
%2:vgpr_32, %3:sreg_64_xexec = V_ADD_I32_e64 killed %1, %0, 0, implicit $exec
S_ENDPGM 0, implicit %2
...
---
name: shrink_add_kill_flags_src1
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0
; GCN-LABEL: name: shrink_add_kill_flags_src1
; GCN: liveins: $vgpr0
; GCN: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 518144, implicit $exec
; GCN: [[V_ADD_I32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_I32_e32 [[V_MOV_B32_e32_]], killed [[COPY]], implicit-def $vcc, implicit $exec
; GCN: S_ENDPGM 0, implicit [[V_ADD_I32_e32_]]
%0:vgpr_32 = COPY $vgpr0
%1:vgpr_32 = V_MOV_B32_e32 518144, implicit $exec
%2:vgpr_32, %3:sreg_64_xexec = V_ADD_I32_e64 %1, killed %0, 0, implicit $exec
S_ENDPGM 0, implicit %2
...
---
name: shrink_addc_kill_flags_src2
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0, $vcc
; GCN-LABEL: name: shrink_addc_kill_flags_src2
; GCN: liveins: $vgpr0, $vcc
; GCN: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 518144, implicit $exec
; GCN: [[COPY1:%[0-9]+]]:sreg_64_xexec = COPY $vcc
; GCN: [[V_ADDC_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADDC_U32_e64_1:%[0-9]+]]:sreg_64_xexec = V_ADDC_U32_e64 [[V_MOV_B32_e32_]], [[COPY]], [[COPY1]], 0, implicit $exec
; GCN: S_ENDPGM 0, implicit [[V_ADDC_U32_e64_]]
%0:vgpr_32 = COPY $vgpr0
%1:vgpr_32 = V_MOV_B32_e32 518144, implicit $exec
%2:sreg_64_xexec = COPY $vcc
%3:vgpr_32, %4:sreg_64_xexec = V_ADDC_U32_e64 %1, %0, %2, 0, implicit $exec
S_ENDPGM 0, implicit %3
...