Skip to content

AMDGPU: Avoid using exact class check in reg_sequence AGPR fold #156135

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 1 commit into from
Sep 3, 2025
Merged

AMDGPU: Avoid using exact class check in reg_sequence AGPR fold #156135

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 4 additions & 2 deletions llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1930,8 +1930,10 @@ bool SIFoldOperandsImpl::foldCopyToAGPRRegSequence(MachineInstr *CopyMI) const {
// Direct copy from SGPR to AGPR is not possible on gfx908. To avoid
// creation of exploded copies SGPR->VGPR->AGPR in the copyPhysReg()
// later, create a copy here and track if we already have such a copy.
if (TRI->getSubRegisterClass(MRI->getRegClass(Src.Reg), Src.SubReg) !=
VGPRUseSubRC) {
const TargetRegisterClass *SubRC =
TRI->getSubRegisterClass(MRI->getRegClass(Src.Reg), Src.SubReg);
if (!VGPRUseSubRC->hasSubClassEq(SubRC)) {
// TODO: Try to reconstrain class
VGPRCopy = MRI->createVirtualRegister(VGPRUseSubRC);
BuildMI(MBB, CopyMI, DL, TII->get(AMDGPU::COPY), VGPRCopy).add(*Def);
B.addReg(VGPRCopy);
Expand Down
13 changes: 4 additions & 9 deletions llvm/test/CodeGen/AMDGPU/si-fold-operands-agpr-copy-reg-sequence.mir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -308,8 +308,7 @@ body: |
; CHECK-LABEL: name: s_mov_b64_0_copy_vgpr_reg_sequence_128_splat_copy_to_agpr_elt64
; CHECK: [[V_MOV_B:%[0-9]+]]:vreg_64_align2 = V_MOV_B64_PSEUDO 0, implicit $exec
; CHECK-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[V_MOV_B]], %subreg.sub0_sub1, [[V_MOV_B]], %subreg.sub2_sub3
; CHECK-NEXT: [[COPY:%[0-9]+]]:vreg_64 = COPY [[V_MOV_B]]
; CHECK-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:areg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0_sub1, [[COPY]], %subreg.sub2_sub3
; CHECK-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:areg_128 = REG_SEQUENCE [[V_MOV_B]], %subreg.sub0_sub1, [[V_MOV_B]], %subreg.sub2_sub3
; CHECK-NEXT: $agpr0_agpr1_agpr2_agpr3 = COPY [[REG_SEQUENCE1]]
; CHECK-NEXT: S_ENDPGM 0, implicit $agpr0_agpr1_agpr2_agpr3
%0:sreg_64 = S_MOV_B64 0
Expand All @@ -329,8 +328,7 @@ body: |
; CHECK-LABEL: name: s_mov_b64_0_copy_vgpr_reg_sequence_128_splat_copy_to_agpr_subreg_elt32
; CHECK: [[V_MOV_B:%[0-9]+]]:vreg_64_align2 = V_MOV_B64_PSEUDO 0, implicit $exec
; CHECK-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[V_MOV_B]].sub0, %subreg.sub0, [[V_MOV_B]].sub1, %subreg.sub1, [[V_MOV_B]], %subreg.sub1_sub2
; CHECK-NEXT: [[COPY:%[0-9]+]]:vreg_64 = COPY [[V_MOV_B]]
; CHECK-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:areg_128 = REG_SEQUENCE [[V_MOV_B]].sub0, %subreg.sub0, [[V_MOV_B]].sub1, %subreg.sub1, [[COPY]], %subreg.sub1_sub2
; CHECK-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:areg_128 = REG_SEQUENCE [[V_MOV_B]].sub0, %subreg.sub0, [[V_MOV_B]].sub1, %subreg.sub1, [[V_MOV_B]], %subreg.sub1_sub2
; CHECK-NEXT: $agpr0_agpr1_agpr2_agpr3 = COPY [[REG_SEQUENCE1]]
; CHECK-NEXT: S_ENDPGM 0, implicit $agpr0_agpr1_agpr2_agpr3
%0:sreg_64 = S_MOV_B64 0
Expand All @@ -354,9 +352,7 @@ body: |
; CHECK-NEXT: [[V_MOV_B:%[0-9]+]]:vreg_64_align2 = V_MOV_B64_PSEUDO 0, implicit $exec
; CHECK-NEXT: [[COPY:%[0-9]+]]:vreg_64_align2 = COPY $vgpr0_vgpr1
; CHECK-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[V_MOV_B]], %subreg.sub0_sub1, [[COPY]], %subreg.sub2_sub3
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vreg_64 = COPY [[V_MOV_B]]
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY [[COPY]]
; CHECK-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:areg_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0_sub1, [[COPY2]], %subreg.sub2_sub3
; CHECK-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:areg_128 = REG_SEQUENCE [[V_MOV_B]], %subreg.sub0_sub1, [[COPY]], %subreg.sub2_sub3
; CHECK-NEXT: $agpr0_agpr1_agpr2_agpr3 = COPY [[REG_SEQUENCE1]]
; CHECK-NEXT: S_ENDPGM 0, implicit $agpr0_agpr1_agpr2_agpr3
%0:sreg_64 = S_MOV_B64 0
Expand All @@ -381,8 +377,7 @@ body: |
; CHECK-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr8_sgpr9
; CHECK-NEXT: [[COPY1:%[0-9]+]]:vreg_64_align2 = COPY killed [[COPY]]
; CHECK-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0_sub1, [[COPY1]], %subreg.sub2_sub3
; CHECK-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY [[COPY1]]
; CHECK-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:areg_128 = REG_SEQUENCE [[COPY2]], %subreg.sub0_sub1, [[COPY2]], %subreg.sub2_sub3
; CHECK-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:areg_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0_sub1, [[COPY1]], %subreg.sub2_sub3
; CHECK-NEXT: $agpr0_agpr1_agpr2_agpr3 = COPY [[REG_SEQUENCE1]]
; CHECK-NEXT: S_ENDPGM 0, implicit $agpr0_agpr1_agpr2_agpr3
%0:sreg_64 = COPY $sgpr8_sgpr9
Expand Down