intel/llvm
1
0
Fork 0
mirror of https://github.com/intel/llvm.git synced 2026-01-16 05:32:28 +08:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
This does better in cases which mix align2 and non-align2 classes.
This commit is contained in:
Matt Arsenault
2025-09-03 09:05:48 +09:00
committed by GitHub
parent 1e786fbe5b
commit 3a7d14acce
2 changed files with 8 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
View File

@@ -1940,8 +1940,10 @@ 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);

13
llvm/test/CodeGen/AMDGPU/si-fold-operands-agpr-copy-reg-sequence.mir
View File

@@ -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
@@ -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
@@ -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
@@ -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