Skip to content

[AMDGPU] Fix register class constraints for si-fold-operands pass when folding immediate into copies #131387

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Apr 30, 2025
Merged

[AMDGPU] Fix register class constraints for si-fold-operands pass when folding immediate into copies #131387

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
e2e886d
[AMDGPU] Fix register class constraints for si-fold-operands pass
mssefat Mar 14, 2025
26a3099
Removed changes for fold-imm-copy.mir and created a nfc for it with a…
mssefat Apr 15, 2025
547d52f
Fixes #130020
mssefat Apr 15, 2025
e655bd6
[AMDGPU] Fix register class constraints for si-fold-operands pass
mssefat Apr 16, 2025
ec4ad28
Reverting to previous approach of using DestRC->hasSuperClassEq(ResRC)
mssefat Apr 30, 2025
a73c5ee
Formatted SIFoldOperands.cpp
mssefat Apr 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1068,6 +1068,16 @@ void SIFoldOperandsImpl::foldOperand(
if (MovOp == AMDGPU::COPY)
return;

// Fold if the destination register class of the MOV instruction (ResRC)
// is a superclass of (or equal to) the destination register class of the
// COPY (DestRC). If this condition fails, folding would be illegal.
const MCInstrDesc &MovDesc = TII->get(MovOp);
assert(MovDesc.getNumDefs() > 0 && MovDesc.operands()[0].RegClass != -1);
const TargetRegisterClass *ResRC =
TRI->getRegClass(MovDesc.operands()[0].RegClass);
if (!DestRC->hasSuperClassEq(ResRC))
return;

MachineInstr::mop_iterator ImpOpI = UseMI->implicit_operands().begin();
MachineInstr::mop_iterator ImpOpE = UseMI->implicit_operands().end();
while (ImpOpI != ImpOpE) {
Expand Down
116 changes: 67 additions & 49 deletions llvm/test/CodeGen/AMDGPU/fold-imm-copy.mir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,52 +202,70 @@ body: |
...

# FIXME: Register class restrictions of av register not respected,
# issue 130020

# ---
# name: s_mov_b32_inlineimm_copy_s_to_av_32
# tracksRegLiveness: true
# body: |
# bb.0:
# %0:sreg_32 = S_MOV_B32 32
# %1:av_32 = COPY %0
# $agpr0 = COPY %1
# S_ENDPGM 0

# ...

# ---
# name: v_mov_b32_inlineimm_copy_v_to_av_32
# tracksRegLiveness: true
# body: |
# bb.0:
# %0:vgpr_32 = V_MOV_B32_e32 32, implicit $exec
# %1:av_32 = COPY %0
# $agpr0 = COPY %1
# S_ENDPGM 0
# ...

# ---
# name: s_mov_b32_imm_literal_copy_s_to_av_32
# tracksRegLiveness: true
# body: |
# bb.0:
# %0:sreg_32 = S_MOV_B32 999
# %1:av_32 = COPY %0
# $agpr0 = COPY %1
# S_ENDPGM 0

# ...

# ---
# name: v_mov_b32_imm_literal_copy_v_to_av_32
# tracksRegLiveness: true
# body: |
# bb.0:
# %0:vgpr_32 = V_MOV_B32_e32 999, implicit $exec
# %1:av_32 = COPY %0
# $agpr0 = COPY %1
# S_ENDPGM 0

# ...
---
name: s_mov_b32_inlineimm_copy_s_to_av_32
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

New tests need checks for the expected output. Maybe convert the while file to use update_mir_test_checks?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I have pushed the updated changes. Could you please review?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ping

tracksRegLiveness: true
body: |
bb.0:
; GCN-LABEL: name: s_mov_b32_inlineimm_copy_s_to_av_32
; GCN: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 32
; GCN-NEXT: [[COPY:%[0-9]+]]:av_32 = COPY [[S_MOV_B32_]]
; GCN-NEXT: $agpr0 = COPY [[COPY]]
; GCN-NEXT: S_ENDPGM 0
%0:sreg_32 = S_MOV_B32 32
%1:av_32 = COPY %0
$agpr0 = COPY %1
S_ENDPGM 0
...

---
name: v_mov_b32_inlineimm_copy_v_to_av_32
tracksRegLiveness: true
body: |
bb.0:
; GCN-LABEL: name: v_mov_b32_inlineimm_copy_v_to_av_32
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 32, implicit $exec
; GCN-NEXT: [[COPY:%[0-9]+]]:av_32 = COPY [[V_MOV_B32_e32_]]
; GCN-NEXT: $agpr0 = COPY [[COPY]]
; GCN-NEXT: S_ENDPGM 0
%0:vgpr_32 = V_MOV_B32_e32 32, implicit $exec
%1:av_32 = COPY %0
$agpr0 = COPY %1
S_ENDPGM 0

...

---
name: s_mov_b32_imm_literal_copy_s_to_av_32
tracksRegLiveness: true
body: |
bb.0:
; GCN-LABEL: name: s_mov_b32_imm_literal_copy_s_to_av_32
; GCN: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 999
; GCN-NEXT: [[COPY:%[0-9]+]]:av_32 = COPY [[S_MOV_B32_]]
; GCN-NEXT: $agpr0 = COPY [[COPY]]
; GCN-NEXT: S_ENDPGM 0
%0:sreg_32 = S_MOV_B32 999
%1:av_32 = COPY %0
$agpr0 = COPY %1
S_ENDPGM 0
...

---
name: v_mov_b32_imm_literal_copy_v_to_av_32
tracksRegLiveness: true
body: |
bb.0:
; GCN-LABEL: name: v_mov_b32_imm_literal_copy_v_to_av_32
; GCN: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 999, implicit $exec
; GCN-NEXT: [[COPY:%[0-9]+]]:av_32 = COPY [[V_MOV_B32_e32_]]
; GCN-NEXT: $agpr0 = COPY [[COPY]]
; GCN-NEXT: S_ENDPGM 0
%0:vgpr_32 = V_MOV_B32_e32 999, implicit $exec
%1:av_32 = COPY %0
$agpr0 = COPY %1
S_ENDPGM 0
...