[llvm] 8df0575 - AMDGPU: Add peephole opt baseline tests (#161309)
via llvm-commits
llvm-commits at lists.llvm.org
Wed Oct 1 06:48:17 PDT 2025
Author: Matt Arsenault
Date: 2025-10-01T22:48:12+09:00
New Revision: 8df0575125c6f7575aff05a8a9effa07bedc7e92
URL: https://github.com/llvm/llvm-project/commit/8df0575125c6f7575aff05a8a9effa07bedc7e92
DIFF: https://github.com/llvm/llvm-project/commit/8df0575125c6f7575aff05a8a9effa07bedc7e92.diff
LOG: AMDGPU: Add peephole opt baseline tests (#161309)
Add tests which show missed folds of subregister extracts with
intermediate full copies.
Added:
Modified:
llvm/test/CodeGen/AMDGPU/peephole-opt-regseq-removal.mir
Removed:
################################################################################
diff --git a/llvm/test/CodeGen/AMDGPU/peephole-opt-regseq-removal.mir b/llvm/test/CodeGen/AMDGPU/peephole-opt-regseq-removal.mir
index f1f2eb6baf008..0c723a09809c6 100644
--- a/llvm/test/CodeGen/AMDGPU/peephole-opt-regseq-removal.mir
+++ b/llvm/test/CodeGen/AMDGPU/peephole-opt-regseq-removal.mir
@@ -80,3 +80,151 @@ body: |
%4:vreg_128 = REG_SEQUENCE %3.sub0, %subreg.sub0, %3.sub1, %subreg.sub1, %3.sub2, %subreg.sub2, %3.sub3, %subreg.sub3
KILL implicit %4
...
+
+---
+name: copy_vreg_64_subreg_from_vgpr_reg_sequence
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1
+ ; GCN-LABEL: name: copy_vreg_64_subreg_from_vgpr_reg_sequence
+ ; GCN: liveins: $vgpr0, $vgpr1
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GCN-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]]
+ ; GCN-NEXT: $vgpr0 = COPY [[COPY2]]
+ %0:vgpr_32 = COPY $vgpr0
+ %1:vgpr_32 = COPY $vgpr1
+ %2:vreg_64 = REG_SEQUENCE %0, %subreg.sub0, %1, %subreg.sub1
+ %3:vgpr_32 = COPY %2.sub0
+ $vgpr0 = COPY %3
+...
+
+---
+name: copy_vreg_64_subreg_from_vgpr_reg_sequence_extra_copy
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1
+ ; GCN-LABEL: name: copy_vreg_64_subreg_from_vgpr_reg_sequence_extra_copy
+ ; GCN: liveins: $vgpr0, $vgpr1
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GCN-NEXT: [[COPY2:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]]
+ ; GCN-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[COPY2]].sub0
+ ; GCN-NEXT: $vgpr0 = COPY [[COPY3]]
+ %0:vgpr_32 = COPY $vgpr0
+ %1:vgpr_32 = COPY $vgpr1
+ %2:vreg_64 = REG_SEQUENCE %0, %subreg.sub0, %1, %subreg.sub1
+ %3:vreg_64 = COPY %2
+ %4:vgpr_32 = COPY %3.sub0
+ $vgpr0 = COPY %4
+...
+
+---
+name: copy_av_64_subreg_from_vgpr_reg_sequence
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1
+ ; GCN-LABEL: name: copy_av_64_subreg_from_vgpr_reg_sequence
+ ; GCN: liveins: $vgpr0, $vgpr1
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GCN-NEXT: [[COPY2:%[0-9]+]]:av_64_align2 = COPY [[REG_SEQUENCE]]
+ ; GCN-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY [[COPY2]].sub0
+ ; GCN-NEXT: $vgpr0 = COPY [[COPY3]]
+ %0:vgpr_32 = COPY $vgpr0
+ %1:vgpr_32 = COPY $vgpr1
+ %2:vreg_64_align2 = REG_SEQUENCE %0, %subreg.sub0, %1, %subreg.sub1
+ %3:av_64_align2 = COPY %2
+ %4:vgpr_32 = COPY %3.sub0
+ $vgpr0 = COPY %4
+...
+
+---
+name: copy_vreg_64_subreg_from_vgpr_reg_sequence_with_sub0_compose
+body: |
+ bb.0:
+ liveins: $vgpr0_vgpr1
+ ; GCN-LABEL: name: copy_vreg_64_subreg_from_vgpr_reg_sequence_with_sub0_compose
+ ; GCN: liveins: $vgpr0_vgpr1
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
+ ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]].sub0, %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GCN-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
+ ; GCN-NEXT: $vgpr0 = COPY [[COPY2]]
+ %0:vreg_64 = COPY $vgpr0_vgpr1
+ %1:vgpr_32 = COPY $vgpr1
+ %2:vreg_64 = REG_SEQUENCE %0.sub0, %subreg.sub0, %1, %subreg.sub1
+ %3:vgpr_32 = COPY %2.sub0
+ $vgpr0 = COPY %3
+...
+
+---
+name: copy_vreg_64_subreg_from_vgpr_reg_sequence_with_sub1_compose
+body: |
+ bb.0:
+ liveins: $vgpr0_vgpr1
+ ; GCN-LABEL: name: copy_vreg_64_subreg_from_vgpr_reg_sequence_with_sub1_compose
+ ; GCN: liveins: $vgpr0_vgpr1
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
+ ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]].sub1, %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GCN-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub1
+ ; GCN-NEXT: $vgpr0 = COPY [[COPY2]]
+ %0:vreg_64 = COPY $vgpr0_vgpr1
+ %1:vgpr_32 = COPY $vgpr1
+ %2:vreg_64 = REG_SEQUENCE %0.sub1, %subreg.sub0, %1, %subreg.sub1
+ %3:vgpr_32 = COPY %2.sub0
+ $vgpr0 = COPY %3
+...
+
+---
+name: copy_vreg_64_subreg_from_multiple_vgpr_reg_sequence
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GCN-LABEL: name: copy_vreg_64_subreg_from_multiple_vgpr_reg_sequence
+ ; GCN: liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
+ ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
+ ; GCN-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr2
+ ; GCN-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY $vgpr3
+ ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
+ ; GCN-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY3]], %subreg.sub1
+ ; GCN-NEXT: [[REG_SEQUENCE2:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[REG_SEQUENCE]], %subreg.sub0_sub1, [[REG_SEQUENCE1]], %subreg.sub2_sub3
+ ; GCN-NEXT: [[COPY4:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]]
+ ; GCN-NEXT: [[COPY5:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE2]].sub1_sub2
+ ; GCN-NEXT: [[COPY6:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE1]]
+ ; GCN-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE1]].sub0
+ ; GCN-NEXT: [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[REG_SEQUENCE]].sub0
+ ; GCN-NEXT: $vgpr0_vgpr1 = COPY [[COPY4]]
+ ; GCN-NEXT: $vgpr2_vgpr3 = COPY [[COPY5]]
+ ; GCN-NEXT: $vgpr4_vgpr5 = COPY [[COPY6]]
+ ; GCN-NEXT: $vgpr6 = COPY [[COPY7]]
+ ; GCN-NEXT: $vgpr6 = COPY [[COPY8]]
+ %0:vgpr_32 = COPY $vgpr0
+ %1:vgpr_32 = COPY $vgpr1
+ %2:vgpr_32 = COPY $vgpr2
+ %3:vgpr_32 = COPY $vgpr3
+ %4:vreg_64 = REG_SEQUENCE %0, %subreg.sub0, %1, %subreg.sub1
+ %5:vreg_64 = REG_SEQUENCE %2, %subreg.sub0, %3, %subreg.sub1
+ %6:vreg_128 = REG_SEQUENCE %4, %subreg.sub0_sub1, %5, %subreg.sub2_sub3
+ %7:vreg_64 = COPY %6.sub0_sub1
+ %8:vreg_64 = COPY %6.sub1_sub2
+ %9:vreg_64 = COPY %6.sub2_sub3
+ %10:vgpr_32 = COPY %6.sub2
+ %11:vgpr_32 = COPY %6.sub0
+ $vgpr0_vgpr1 = COPY %7
+ $vgpr2_vgpr3 = COPY %8
+ $vgpr4_vgpr5 = COPY %9
+ $vgpr6 = COPY %10
+ $vgpr6 = COPY %11
+...
More information about the llvm-commits
mailing list