This is an archive of the discontinued LLVM Phabricator instance.

Differential D157489

Added a testcase
AbandonedPublic

Authored by konradkusiak97 on Aug 9 2023, 3:46 AM.

Details

Reviewers
None

Diff Detail

Unit TestsFailed

TimeTest
330 msx64 debian > LLVM.CodeGen/AMDGPU::merge-image-load.mir
370 msx64 debian > LLVM.CodeGen/AMDGPU::merge-image-sample.mir

Event Timeline

konradkusiak97 created this revision.Aug 9 2023, 3:46 AM
Herald added a project: Restricted Project. · View Herald TranscriptAug 9 2023, 3:46 AM
Herald added subscribers: wenlei, kerbowa, jvesely. · View Herald Transcript
konradkusiak97 requested review of this revision.Aug 9 2023, 3:46 AM
Herald added a project: Restricted Project. · View Herald TranscriptAug 9 2023, 3:46 AM
Herald added a subscriber: llvm-commits. · View Herald Transcript
konradkusiak97 abandoned this revision.Aug 9 2023, 3:46 AM
Harbormaster completed remote builds in B251342: Diff 548552.Aug 9 2023, 6:30 AM

Revision Contents

PathSize
llvm/
test/
CodeGen/
AMDGPU/
18 lines
18 lines

Diff 548552

llvm/test/CodeGen/AMDGPU/merge-image-load.mir

Show First 20 Lines • Show All 166 Lines • ▼ Show 20 Lines bb.0.entry:
%3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0
%4:vgpr_32 = COPY %2.sub3 %4:vgpr_32 = COPY %2.sub3
%5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128))
%6:vgpr_32 = IMAGE_LOAD_V1_V4 %5:vreg_128, %3:sgpr_256, 4, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) %6:vgpr_32 = IMAGE_LOAD_V1_V4 %5:vreg_128, %3:sgpr_256, 4, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4)
%7:vreg_96 = IMAGE_LOAD_V3_V4 %5:vreg_128, %3:sgpr_256, 7, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) %7:vreg_96 = IMAGE_LOAD_V3_V4 %5:vreg_128, %3:sgpr_256, 7, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4)
... ...
--- ---
# GFX9-LABEL: name: image_load_dmask_zero_not_merged
# GFX9: %{{[0-9]+}}:vgpr_32 = IMAGE_LOAD_V1_V4 %5, %3, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4)
# GFX9: %{{[0-9]+}}:vreg_96 = IMAGE_LOAD_V3_V4 %5, %3, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4)
name: image_load_dmask_zero_not_merged
body: |
bb.0.entry:
%0:sgpr_64 = COPY $sgpr0_sgpr1
%1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0
%2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
%3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0
%4:vgpr_32 = COPY %2.sub3
%5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128))
%6:vgpr_32 = IMAGE_LOAD_V1_V4 %5:vreg_128, %3:sgpr_256, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4)
%7:vreg_96 = IMAGE_LOAD_V3_V4 %5:vreg_128, %3:sgpr_256, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4)
...
---
# GFX9-LABEL: name: image_load_dmask_not_disjoint_not_merged # GFX9-LABEL: name: image_load_dmask_not_disjoint_not_merged
# GFX9: %{{[0-9]+}}:vgpr_32 = IMAGE_LOAD_V1_V4 %5, %3, 4, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) # GFX9: %{{[0-9]+}}:vgpr_32 = IMAGE_LOAD_V1_V4 %5, %3, 4, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4)
# GFX9: %{{[0-9]+}}:vreg_96 = IMAGE_LOAD_V3_V4 %5, %3, 11, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) # GFX9: %{{[0-9]+}}:vreg_96 = IMAGE_LOAD_V3_V4 %5, %3, 11, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4)
name: image_load_dmask_not_disjoint_not_merged name: image_load_dmask_not_disjoint_not_merged
body: | body: |
bb.0.entry: bb.0.entry:
%0:sgpr_64 = COPY $sgpr0_sgpr1 %0:sgpr_64 = COPY $sgpr0_sgpr1
▲ Show 20 Lines • Show All 287 Lines • Show Last 20 Lines

llvm/test/CodeGen/AMDGPU/merge-image-sample.mir

Show First 20 Lines • Show All 166 Lines • ▼ Show 20 Lines bb.0.entry:
%3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0 %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0
%4:vgpr_32 = COPY %2.sub3 %4:vgpr_32 = COPY %2.sub3
%5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128)) %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128))
%6:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 4, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 4, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4)
%7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) %7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4)
... ...
--- ---
# GFX9-LABEL: name: image_sample_l_dmask_zero_not_merged
# GFX9: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5, %3, %2, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4)
# GFX9: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5, %3, %2, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4)
name: image_sample_l_dmask_zero_not_merged
body: |
bb.0.entry:
%0:sgpr_64 = COPY $sgpr0_sgpr1
%1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0
%2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
%3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0
%4:vgpr_32 = COPY %2.sub3
%5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load (s128))
%6:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4)
%7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4)
...
---
# GFX9-LABEL: name: image_sample_l_dmask_not_disjoint_not_merged # GFX9-LABEL: name: image_sample_l_dmask_not_disjoint_not_merged
# GFX9: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5, %3, %2, 4, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4) # GFX9: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5, %3, %2, 4, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s32), addrspace 4)
# GFX9: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5, %3, %2, 11, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4) # GFX9: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5, %3, %2, 11, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load (s96), align 16, addrspace 4)
name: image_sample_l_dmask_not_disjoint_not_merged name: image_sample_l_dmask_not_disjoint_not_merged
body: | body: |
bb.0.entry: bb.0.entry:
%0:sgpr_64 = COPY $sgpr0_sgpr1 %0:sgpr_64 = COPY $sgpr0_sgpr1
▲ Show 20 Lines • Show All 951 Lines • Show Last 20 Lines