[llvm] [AMDGPU][NFC] Replace gfx940 and gfx941 with gfx942 in llvm/test (PR #125711)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Feb 4 08:34:02 PST 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Fabian Ritter (ritter-x2a)
<details>
<summary>Changes</summary>
[AMDGPU][NFC] Replace gfx940 and gfx941 with gfx942 in llvm/test
gfx940 and gfx941 are no longer supported. This is one of a series of PRs to remove them from the code base.
This PR uses gfx942 instead of gfx940 and gfx941 in the test RUN-lines (unless there is already a RUN-line for gfx942).
The only notable difference in the test output is that gfx942 does not force the use of sc0 and sc1 on stores while gfx940 and gfx941 do (cf. https://reviews.llvm.org/D149986).
---
Patch is 31.19 MiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/125711.diff
276 Files Affected:
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/atomicrmw_fmax.ll (+224-224)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/atomicrmw_fmin.ll (+224-224)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/buffer-atomic-fadd.f32-no-rtn.ll (+116-116)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/buffer-atomic-fadd.f32-rtn.ll (+124-124)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/buffer-atomic-fadd.f64.ll (+310-310)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/buffer-atomic-fadd.v2f16-no-rtn.ll (+116-116)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/buffer-atomic-fadd.v2f16-rtn.ll (+124-124)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/flat-atomic-fadd.f32.ll (+43-43)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/flat-atomic-fadd.f64.ll (+32-32)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/flat-atomic-fadd.v2f16.ll (+45-45)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/flat-scratch-init.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/flat-scratch.ll (+736-736)
- (removed) llvm/test/CodeGen/AMDGPU/GlobalISel/fp-atomics-gfx940.ll (-132)
- (added) llvm/test/CodeGen/AMDGPU/GlobalISel/fp-atomics-gfx942.ll (+132)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/fp64-atomics-gfx90a.ll (+629-629)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/global-atomic-fadd.f32-no-rtn.ll (+82-82)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/global-atomic-fadd.f32-rtn.ll (+102-102)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/global-atomic-fadd.f64.ll (+64-64)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/global-atomic-fadd.v2f16-no-rtn.ll (+23-23)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/global-atomic-fadd.v2f16-rtn.ll (+25-25)
- (modified) llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-atomicrmw.ll (+1-1)
- (renamed) llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.mfma.gfx942.mir (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/accvgpr-copy.mir (+314-314)
- (modified) llvm/test/CodeGen/AMDGPU/amdhsa-kernarg-preload-num-sgprs.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/atomicrmw-expand.ll (+27-27)
- (modified) llvm/test/CodeGen/AMDGPU/back-off-barrier-subtarget-feature.ll (+20-20)
- (modified) llvm/test/CodeGen/AMDGPU/bf16-conversions.ll (+242-242)
- (modified) llvm/test/CodeGen/AMDGPU/buffer-atomic-fadd.f32-no-rtn.ll (+142-142)
- (modified) llvm/test/CodeGen/AMDGPU/buffer-atomic-fadd.f32-rtn.ll (+150-150)
- (modified) llvm/test/CodeGen/AMDGPU/buffer-atomic-fadd.f64.ll (+360-360)
- (modified) llvm/test/CodeGen/AMDGPU/buffer-atomic-fadd.v2f16-no-rtn.ll (+142-142)
- (modified) llvm/test/CodeGen/AMDGPU/buffer-atomic-fadd.v2f16-rtn.ll (+150-150)
- (modified) llvm/test/CodeGen/AMDGPU/buffer-fat-pointer-atomicrmw-fadd.ll (+914-914)
- (modified) llvm/test/CodeGen/AMDGPU/buffer-fat-pointer-atomicrmw-fmax.ll (+839-839)
- (modified) llvm/test/CodeGen/AMDGPU/buffer-fat-pointer-atomicrmw-fmin.ll (+839-839)
- (modified) llvm/test/CodeGen/AMDGPU/build_vector.ll (+51-51)
- (modified) llvm/test/CodeGen/AMDGPU/copy_phys_vgpr64.mir (+103-103)
- (modified) llvm/test/CodeGen/AMDGPU/directive-amdgcn-target.ll (-12)
- (modified) llvm/test/CodeGen/AMDGPU/dpp64_combine.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/dpp64_combine.mir (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/elf-header-flags-mach.ll (-4)
- (modified) llvm/test/CodeGen/AMDGPU/elf-header-flags-sramecc.ll (+6-6)
- (modified) llvm/test/CodeGen/AMDGPU/eliminate-frame-index-s-add-i32.mir (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/eliminate-frame-index-scalar-bit-ops.mir (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32.mir (+135-135)
- (modified) llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-u32.mir (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/flat-atomic-fadd.f32.ll (+48-48)
- (modified) llvm/test/CodeGen/AMDGPU/flat-atomic-fadd.f64.ll (+122-122)
- (modified) llvm/test/CodeGen/AMDGPU/flat-atomicrmw-fadd.ll (+1394-1394)
- (modified) llvm/test/CodeGen/AMDGPU/flat-atomicrmw-fmax.ll (+2044-2044)
- (modified) llvm/test/CodeGen/AMDGPU/flat-atomicrmw-fmin.ll (+2044-2044)
- (modified) llvm/test/CodeGen/AMDGPU/flat-atomicrmw-fsub.ll (+1904-1904)
- (modified) llvm/test/CodeGen/AMDGPU/flat-scratch-svs.ll (+394-394)
- (modified) llvm/test/CodeGen/AMDGPU/flat-scratch.ll (+438-438)
- (modified) llvm/test/CodeGen/AMDGPU/fmaximum3.ll (+1194-1194)
- (modified) llvm/test/CodeGen/AMDGPU/fminimum3.ll (+1194-1194)
- (modified) llvm/test/CodeGen/AMDGPU/fold-agpr-phis.mir (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/fold-zero-high-bits-clear-kill-flags.mir (+1-1)
- (renamed) llvm/test/CodeGen/AMDGPU/fp-atomics-gfx942.ll (+62-62)
- (modified) llvm/test/CodeGen/AMDGPU/fp64-atomics-gfx90a.ll (+583-583)
- (renamed) llvm/test/CodeGen/AMDGPU/gfx942-hazards.mir (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/global-atomic-fadd.f32-no-rtn.ll (+74-74)
- (modified) llvm/test/CodeGen/AMDGPU/global-atomic-fadd.f32-rtn.ll (+95-95)
- (modified) llvm/test/CodeGen/AMDGPU/global-atomic-fadd.f64.ll (+66-66)
- (modified) llvm/test/CodeGen/AMDGPU/global-atomic-fadd.v2f16-no-rtn.ll (+48-48)
- (modified) llvm/test/CodeGen/AMDGPU/global-atomic-fadd.v2f16-rtn.ll (+52-52)
- (modified) llvm/test/CodeGen/AMDGPU/global-atomicrmw-fadd.ll (+1314-1314)
- (modified) llvm/test/CodeGen/AMDGPU/global-atomicrmw-fmax.ll (+1747-1747)
- (modified) llvm/test/CodeGen/AMDGPU/global-atomicrmw-fmin.ll (+1747-1747)
- (modified) llvm/test/CodeGen/AMDGPU/global-atomicrmw-fsub.ll (+1691-1691)
- (modified) llvm/test/CodeGen/AMDGPU/idemponent-atomics.ll (+97-97)
- (modified) llvm/test/CodeGen/AMDGPU/insert_vector_elt.v2bf16.ll (+318-318)
- (modified) llvm/test/CodeGen/AMDGPU/lds-dma-hazards.mir (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/lds-dma-waitcnt.mir (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/lds-limit-diagnostics.ll (-2)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.cvt.fp8.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.fdot2.ll (+3-3)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.global.load.lds.gfx950.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.global.load.lds.ll (+37-37)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx90a.ll (+13-13)
- (renamed) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.gfx942.ll (+54-54)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.ll (+52-52)
- (renamed) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.mfma.xf32.gfx942.ll (+12-12)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.permlane16.swap.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.permlane32.swap.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.ptr.buffer.atomic.fadd_rtn_errors.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.buffer.atomic.fadd_nortn.ll (+31-31)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.buffer.atomic.fadd_rtn.ll (+31-31)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.ptr.buffer.load.lds.gfx950.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.buffer.atomic.fadd_nortn.ll (+97-97)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.buffer.atomic.fadd_rtn.ll (+97-97)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.buffer.atomic.fmax.f64.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.buffer.atomic.fmin.f64.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.ptr.buffer.load.lds.gfx950.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.udot2.ll (+6-6)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.udot4.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/llvm.amdgcn.udot8.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/local-atomicrmw-fadd.ll (+650-650)
- (modified) llvm/test/CodeGen/AMDGPU/local-atomicrmw-fmax.ll (+689-689)
- (modified) llvm/test/CodeGen/AMDGPU/local-atomicrmw-fmin.ll (+689-689)
- (modified) llvm/test/CodeGen/AMDGPU/local-atomicrmw-fsub.ll (+796-796)
- (modified) llvm/test/CodeGen/AMDGPU/local-stack-alloc-add-references.gfx8.mir (+134-134)
- (modified) llvm/test/CodeGen/AMDGPU/local-stack-alloc-add-references.gfx9.mir (+70-70)
- (modified) llvm/test/CodeGen/AMDGPU/lower-buffer-fat-pointers-nontemporal-metadata.ll (+119-119)
- (modified) llvm/test/CodeGen/AMDGPU/lshl-add-u64.ll (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/madak.ll (+144-144)
- (renamed) llvm/test/CodeGen/AMDGPU/mai-hazards-gfx942.mir (+68-68)
- (modified) llvm/test/CodeGen/AMDGPU/materialize-frame-index-sgpr.gfx10.ll (+235-235)
- (modified) llvm/test/CodeGen/AMDGPU/materialize-frame-index-sgpr.ll (+264-264)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-fence-mmra-global.ll (+241-241)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-fence-mmra-local.ll (+158-158)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-fence.ll (+341-341)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-flat-agent.ll (+2932-2932)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-flat-nontemporal.ll (+149-149)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-flat-singlethread.ll (+2478-2478)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-flat-system.ll (+2932-2932)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-flat-wavefront.ll (+2445-2445)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-flat-workgroup.ll (+2574-2574)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-global-agent.ll (+2787-2787)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-global-nontemporal.ll (+124-124)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-global-singlethread.ll (+2390-2390)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-global-system.ll (+2647-2647)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-global-wavefront.ll (+2390-2390)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-global-workgroup.ll (+2577-2577)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-local-agent.ll (+2348-2348)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-local-nontemporal.ll (+135-135)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-local-singlethread.ll (+2238-2238)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-local-system.ll (+2348-2348)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-local-wavefront.ll (+2238-2238)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-local-workgroup.ll (+2348-2348)
- (modified) llvm/test/CodeGen/AMDGPU/memory-legalizer-private-nontemporal.ll (+124-124)
- (modified) llvm/test/CodeGen/AMDGPU/mfma-cd-select.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/mfma-loop.ll (+19-19)
- (modified) llvm/test/CodeGen/AMDGPU/mfma-no-register-aliasing.ll (+1-1)
- (renamed) llvm/test/CodeGen/AMDGPU/mfma-vgpr-cd-select-gfx942.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/mfma-vgpr-cd-select.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/neighboring-mfma-padding.mir (+233-233)
- (modified) llvm/test/CodeGen/AMDGPU/packed-fp32.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/peephole-fold-imm.mir (+1-1)
- (modified) llvm/test/CodeGen/AMDGPU/preload-implicit-kernargs-IR-lowering.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/preload-implicit-kernargs.ll (+333-333)
- (modified) llvm/test/CodeGen/AMDGPU/preload-kernargs-IR-lowering.ll (+4-4)
- (modified) llvm/test/CodeGen/AMDGPU/preload-kernargs.ll (+564-564)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2bf16.v2bf16.ll (+500-500)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2bf16.v3bf16.ll (+1103-1103)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2bf16.v4bf16.ll (+1937-1937)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2bf16.v8bf16.ll (+7427-7427)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2f16.v2f16.ll (+500-500)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2f16.v3f16.ll (+1103-1103)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2f16.v4f16.ll (+1937-1937)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2f16.v8f16.ll (+7427-7427)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2f32.v2f32.ll (+454-454)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2f32.v3f32.ll (+1012-1012)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2f32.v4f32.ll (+1788-1788)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2f32.v8f32.ll (+6783-6783)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2i16.v2i16.ll (+493-493)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2i16.v3i16.ll (+1092-1092)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2i16.v4i16.ll (+1899-1899)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2i16.v8i16.ll (+7255-7255)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2i32.v2i32.ll (+454-454)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2i32.v3i32.ll (+1012-1012)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2i32.v4i32.ll (+1788-1788)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2i32.v8i32.ll (+6783-6783)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2i64.v2i64.ll (+486-486)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2i64.v3i64.ll (+1076-1076)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2i64.v4i64.ll (+1775-1775)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2i64.v8i64.ll (+7513-7513)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2p0.v2p0.ll (+486-486)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2p0.v3p0.ll (+1076-1076)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2p0.v4p0.ll (+1775-1775)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2p3.v2p3.ll (+454-454)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2p3.v3p3.ll (+1012-1012)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2p3.v4p3.ll (+1788-1788)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v2p3.v8p3.ll (+6783-6783)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3bf16.v2bf16.ll (+1016-1016)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3bf16.v3bf16.ll (+2252-2252)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3bf16.v4bf16.ll (+4112-4112)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3f16.v2f16.ll (+1016-1016)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3f16.v3f16.ll (+2252-2252)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3f16.v4f16.ll (+4112-4112)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3f32.v2f32.ll (+990-990)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3f32.v3f32.ll (+2112-2112)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3f32.v4f32.ll (+3777-3777)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3i16.v2i16.ll (+987-987)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3i16.v3i16.ll (+2212-2212)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3i16.v4i16.ll (+4011-4011)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3i32.v2i32.ll (+990-990)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3i32.v3i32.ll (+2112-2112)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3i32.v4i32.ll (+3777-3777)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3i64.v2i64.ll (+1092-1092)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3i64.v3i64.ll (+2289-2289)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3i64.v4i64.ll (+4119-4119)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3p0.v2p0.ll (+1092-1092)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3p0.v3p0.ll (+2289-2289)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3p0.v4p0.ll (+4119-4119)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3p3.v2p3.ll (+990-990)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3p3.v3p3.ll (+2112-2112)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v3p3.v4p3.ll (+3777-3777)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4bf16.v2bf16.ll (+1757-1757)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4bf16.v3bf16.ll (+3745-3745)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4bf16.v4bf16.ll (+6649-6649)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4f16.v2f16.ll (+1757-1757)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4f16.v3f16.ll (+3745-3745)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4f16.v4f16.ll (+6649-6649)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4f32.v2f32.ll (+1279-1279)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4f32.v3f32.ll (+3531-3531)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4f32.v4f32.ll (+5984-5984)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4i16.v2i16.ll (+1621-1621)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4i16.v3i16.ll (+3640-3640)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4i16.v4i16.ll (+6339-6339)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4i32.v2i32.ll (+1281-1281)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4i32.v3i32.ll (+3531-3531)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4i32.v4i32.ll (+5984-5984)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4i64.v2i64.ll (+1526-1526)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4i64.v3i64.ll (+4091-4091)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4i64.v4i64.ll (+6967-6967)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4p0.v2p0.ll (+1526-1526)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4p0.v3p0.ll (+4091-4091)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4p0.v4p0.ll (+6967-6967)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4p3.v2p3.ll (+1281-1281)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4p3.v3p3.ll (+3531-3531)
- (modified) llvm/test/CodeGen/AMDGPU/shufflevector.v4p3.v4p3.ll (+5984-5984)
- (modified) llvm/test/CodeGen/AMDGPU/smfmac_no_agprs.ll (+24-24)
- (modified) llvm/test/CodeGen/AMDGPU/uniform-select.ll (+48-48)
- (modified) llvm/test/CodeGen/AMDGPU/unsupported-image-sample.ll (+2-2)
- (modified) llvm/test/CodeGen/AMDGPU/v_mov_b64_expansion.mir (+6-6)
- (modified) llvm/test/CodeGen/AMDGPU/vector_shuffle.packed.ll (+778-970)
- (modified) llvm/test/CodeGen/AMDGPU/verifier-sdwa-cvt.mir (+2-2)
- (modified) llvm/test/MC/AMDGPU/amdhsa-kd-kernarg-preload.s (+2-2)
- (modified) llvm/test/MC/AMDGPU/extrasgprs_mcexpr.s (+6-6)
- (renamed) llvm/test/MC/AMDGPU/flat-scratch-gfx942.s (+354-354)
- (removed) llvm/test/MC/AMDGPU/gfx940_err.s (-127)
- (renamed) llvm/test/MC/AMDGPU/gfx942_asm_features.s (+313-313)
- (added) llvm/test/MC/AMDGPU/gfx942_err.s (+127)
- (renamed) llvm/test/MC/AMDGPU/gfx942_err_pos.s (+1-1)
- (renamed) llvm/test/MC/AMDGPU/gfx942_unsupported.s (+1-1)
- (modified) llvm/test/MC/AMDGPU/gfx950_asm_features.s (+1-1)
- (modified) llvm/test/MC/AMDGPU/gfx950_asm_read_tr.s (+11-11)
- (modified) llvm/test/MC/AMDGPU/gfx950_asm_vop1.s (+33-33)
- (modified) llvm/test/MC/AMDGPU/gfx950_asm_vop3.s (+25-25)
- (renamed) llvm/test/MC/AMDGPU/mai-err-gfx942.s (+16-16)
- (renamed) llvm/test/MC/AMDGPU/mai-gfx942.s (+192-192)
- (modified) llvm/test/MC/AMDGPU/mai-gfx950.s (+1-1)
- (renamed) llvm/test/MC/AMDGPU/mimg-err-gfx942.s (+27-27)
- (modified) llvm/test/MC/AMDGPU/mubuf-gfx950.s (+1-1)
- (modified) llvm/test/MC/AMDGPU/writelane_m0.s (+1-1)
- (modified) llvm/test/MC/AMDGPU/xdl-insts-gfx908.s (+1-1)
- (modified) llvm/test/MC/Disassembler/AMDGPU/gfx908-xdl-insts.txt (+1-1)
- (renamed) llvm/test/MC/Disassembler/AMDGPU/gfx942_features.txt (+183-183)
- (renamed) llvm/test/MC/Disassembler/AMDGPU/gfx942_flat.txt (+353-353)
- (renamed) llvm/test/MC/Disassembler/AMDGPU/gfx942_mai.txt (+200-200)
- (modified) llvm/test/MachineVerifier/AMDGPU/writelane_m0.mir (+1-1)
- (modified) llvm/test/Object/AMDGPU/elf-header-flags-mach.yaml (-14)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-f32-agent.ll (+354-354)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-f32-system.ll (+274-274)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-f64-agent.ll (+58-58)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-f64-system.ll (+46-46)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i16.ll (+2-2)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i32-agent.ll (+3-3)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i32-system.ll (+3-3)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i64-agent.ll (+3-3)
``````````diff
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/atomicrmw_fmax.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/atomicrmw_fmax.ll
index 424388a30e99b41..d1a303b41deefe5 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/atomicrmw_fmax.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/atomicrmw_fmax.ll
@@ -1,6 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 < %s | FileCheck -check-prefix=GFX12 %s
-; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx940 < %s | FileCheck -check-prefix=GFX940 %s
+; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx942 < %s | FileCheck -check-prefix=GFX942 %s
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1100 < %s | FileCheck -check-prefix=GFX11 %s
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 < %s | FileCheck -check-prefix=GFX10 %s
; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx90a < %s | FileCheck -check-prefix=GFX90A %s
@@ -24,12 +24,12 @@ define float @local_atomic_fmax_ret_f32(ptr addrspace(3) %ptr, float %val) {
; GFX12-NEXT: global_inv scope:SCOPE_SE
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: local_atomic_fmax_ret_f32:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: ds_max_rtn_f32 v0, v0, v1
-; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: local_atomic_fmax_ret_f32:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: ds_max_rtn_f32 v0, v0, v1
+; GFX942-NEXT: s_waitcnt lgkmcnt(0)
+; GFX942-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: local_atomic_fmax_ret_f32:
; GFX11: ; %bb.0:
@@ -96,12 +96,12 @@ define void @local_atomic_fmax_noret_f32(ptr addrspace(3) %ptr, float %val) {
; GFX12-NEXT: global_inv scope:SCOPE_SE
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: local_atomic_fmax_noret_f32:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: ds_max_f32 v0, v1
-; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: local_atomic_fmax_noret_f32:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: ds_max_f32 v0, v1
+; GFX942-NEXT: s_waitcnt lgkmcnt(0)
+; GFX942-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: local_atomic_fmax_noret_f32:
; GFX11: ; %bb.0:
@@ -168,14 +168,14 @@ define double @local_atomic_fmax_ret_f64(ptr addrspace(3) %ptr, double %val) {
; GFX12-NEXT: global_inv scope:SCOPE_SE
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: local_atomic_fmax_ret_f64:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v4, v1
-; GFX940-NEXT: v_mov_b32_e32 v5, v2
-; GFX940-NEXT: ds_max_rtn_f64 v[0:1], v0, v[4:5]
-; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: local_atomic_fmax_ret_f64:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: v_mov_b32_e32 v4, v1
+; GFX942-NEXT: v_mov_b32_e32 v5, v2
+; GFX942-NEXT: ds_max_rtn_f64 v[0:1], v0, v[4:5]
+; GFX942-NEXT: s_waitcnt lgkmcnt(0)
+; GFX942-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: local_atomic_fmax_ret_f64:
; GFX11: ; %bb.0:
@@ -244,14 +244,14 @@ define void @local_atomic_fmax_noret_f64(ptr addrspace(3) %ptr, double %val) {
; GFX12-NEXT: global_inv scope:SCOPE_SE
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: local_atomic_fmax_noret_f64:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v4, v1
-; GFX940-NEXT: v_mov_b32_e32 v5, v2
-; GFX940-NEXT: ds_max_f64 v0, v[4:5]
-; GFX940-NEXT: s_waitcnt lgkmcnt(0)
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: local_atomic_fmax_noret_f64:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: v_mov_b32_e32 v4, v1
+; GFX942-NEXT: v_mov_b32_e32 v5, v2
+; GFX942-NEXT: ds_max_f64 v0, v[4:5]
+; GFX942-NEXT: s_waitcnt lgkmcnt(0)
+; GFX942-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: local_atomic_fmax_noret_f64:
; GFX11: ; %bb.0:
@@ -320,30 +320,30 @@ define float @global_agent_atomic_fmax_ret_f32__amdgpu_no_fine_grained_memory(pt
; GFX12-NEXT: global_inv scope:SCOPE_DEV
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: global_agent_atomic_fmax_ret_f32__amdgpu_no_fine_grained_memory:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: global_load_dword v3, v[0:1], off
-; GFX940-NEXT: s_mov_b64 s[0:1], 0
-; GFX940-NEXT: v_max_f32_e32 v2, v2, v2
-; GFX940-NEXT: .LBB4_1: ; %atomicrmw.start
-; GFX940-NEXT: ; =>This Inner Loop Header: Depth=1
-; GFX940-NEXT: s_waitcnt vmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v5, v3
-; GFX940-NEXT: v_max_f32_e32 v3, v5, v5
-; GFX940-NEXT: v_max_f32_e32 v4, v3, v2
-; GFX940-NEXT: buffer_wbl2 sc1
-; GFX940-NEXT: global_atomic_cmpswap v3, v[0:1], v[4:5], off sc0
-; GFX940-NEXT: s_waitcnt vmcnt(0)
-; GFX940-NEXT: buffer_inv sc1
-; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, v3, v5
-; GFX940-NEXT: s_or_b64 s[0:1], vcc, s[0:1]
-; GFX940-NEXT: s_andn2_b64 exec, exec, s[0:1]
-; GFX940-NEXT: s_cbranch_execnz .LBB4_1
-; GFX940-NEXT: ; %bb.2: ; %atomicrmw.end
-; GFX940-NEXT: s_or_b64 exec, exec, s[0:1]
-; GFX940-NEXT: v_mov_b32_e32 v0, v3
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: global_agent_atomic_fmax_ret_f32__amdgpu_no_fine_grained_memory:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: global_load_dword v3, v[0:1], off
+; GFX942-NEXT: s_mov_b64 s[0:1], 0
+; GFX942-NEXT: v_max_f32_e32 v2, v2, v2
+; GFX942-NEXT: .LBB4_1: ; %atomicrmw.start
+; GFX942-NEXT: ; =>This Inner Loop Header: Depth=1
+; GFX942-NEXT: s_waitcnt vmcnt(0)
+; GFX942-NEXT: v_mov_b32_e32 v5, v3
+; GFX942-NEXT: v_max_f32_e32 v3, v5, v5
+; GFX942-NEXT: v_max_f32_e32 v4, v3, v2
+; GFX942-NEXT: buffer_wbl2 sc1
+; GFX942-NEXT: global_atomic_cmpswap v3, v[0:1], v[4:5], off sc0
+; GFX942-NEXT: s_waitcnt vmcnt(0)
+; GFX942-NEXT: buffer_inv sc1
+; GFX942-NEXT: v_cmp_eq_u32_e32 vcc, v3, v5
+; GFX942-NEXT: s_or_b64 s[0:1], vcc, s[0:1]
+; GFX942-NEXT: s_andn2_b64 exec, exec, s[0:1]
+; GFX942-NEXT: s_cbranch_execnz .LBB4_1
+; GFX942-NEXT: ; %bb.2: ; %atomicrmw.end
+; GFX942-NEXT: s_or_b64 exec, exec, s[0:1]
+; GFX942-NEXT: v_mov_b32_e32 v0, v3
+; GFX942-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: global_agent_atomic_fmax_ret_f32__amdgpu_no_fine_grained_memory:
; GFX11: ; %bb.0:
@@ -466,29 +466,29 @@ define void @global_agent_atomic_fmax_noret_f32__amdgpu_no_fine_grained_memory(p
; GFX12-NEXT: global_inv scope:SCOPE_DEV
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: global_agent_atomic_fmax_noret_f32__amdgpu_no_fine_grained_memory:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: global_load_dword v3, v[0:1], off
-; GFX940-NEXT: s_mov_b64 s[0:1], 0
-; GFX940-NEXT: v_max_f32_e32 v4, v2, v2
-; GFX940-NEXT: .LBB5_1: ; %atomicrmw.start
-; GFX940-NEXT: ; =>This Inner Loop Header: Depth=1
-; GFX940-NEXT: s_waitcnt vmcnt(0)
-; GFX940-NEXT: v_max_f32_e32 v2, v3, v3
-; GFX940-NEXT: v_max_f32_e32 v2, v2, v4
-; GFX940-NEXT: buffer_wbl2 sc1
-; GFX940-NEXT: global_atomic_cmpswap v2, v[0:1], v[2:3], off sc0
-; GFX940-NEXT: s_waitcnt vmcnt(0)
-; GFX940-NEXT: buffer_inv sc1
-; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, v2, v3
-; GFX940-NEXT: s_or_b64 s[0:1], vcc, s[0:1]
-; GFX940-NEXT: v_mov_b32_e32 v3, v2
-; GFX940-NEXT: s_andn2_b64 exec, exec, s[0:1]
-; GFX940-NEXT: s_cbranch_execnz .LBB5_1
-; GFX940-NEXT: ; %bb.2: ; %atomicrmw.end
-; GFX940-NEXT: s_or_b64 exec, exec, s[0:1]
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: global_agent_atomic_fmax_noret_f32__amdgpu_no_fine_grained_memory:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: global_load_dword v3, v[0:1], off
+; GFX942-NEXT: s_mov_b64 s[0:1], 0
+; GFX942-NEXT: v_max_f32_e32 v4, v2, v2
+; GFX942-NEXT: .LBB5_1: ; %atomicrmw.start
+; GFX942-NEXT: ; =>This Inner Loop Header: Depth=1
+; GFX942-NEXT: s_waitcnt vmcnt(0)
+; GFX942-NEXT: v_max_f32_e32 v2, v3, v3
+; GFX942-NEXT: v_max_f32_e32 v2, v2, v4
+; GFX942-NEXT: buffer_wbl2 sc1
+; GFX942-NEXT: global_atomic_cmpswap v2, v[0:1], v[2:3], off sc0
+; GFX942-NEXT: s_waitcnt vmcnt(0)
+; GFX942-NEXT: buffer_inv sc1
+; GFX942-NEXT: v_cmp_eq_u32_e32 vcc, v2, v3
+; GFX942-NEXT: s_or_b64 s[0:1], vcc, s[0:1]
+; GFX942-NEXT: v_mov_b32_e32 v3, v2
+; GFX942-NEXT: s_andn2_b64 exec, exec, s[0:1]
+; GFX942-NEXT: s_cbranch_execnz .LBB5_1
+; GFX942-NEXT: ; %bb.2: ; %atomicrmw.end
+; GFX942-NEXT: s_or_b64 exec, exec, s[0:1]
+; GFX942-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: global_agent_atomic_fmax_noret_f32__amdgpu_no_fine_grained_memory:
; GFX11: ; %bb.0:
@@ -626,14 +626,14 @@ define double @global_agent_atomic_fmax_ret_f64__amdgpu_no_fine_grained_memory(p
; GFX12-NEXT: v_dual_mov_b32 v0, v4 :: v_dual_mov_b32 v1, v5
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: global_agent_atomic_fmax_ret_f64__amdgpu_no_fine_grained_memory:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: buffer_wbl2 sc1
-; GFX940-NEXT: global_atomic_max_f64 v[0:1], v[0:1], v[2:3], off sc0
-; GFX940-NEXT: s_waitcnt vmcnt(0)
-; GFX940-NEXT: buffer_inv sc1
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: global_agent_atomic_fmax_ret_f64__amdgpu_no_fine_grained_memory:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: buffer_wbl2 sc1
+; GFX942-NEXT: global_atomic_max_f64 v[0:1], v[0:1], v[2:3], off sc0
+; GFX942-NEXT: s_waitcnt vmcnt(0)
+; GFX942-NEXT: buffer_inv sc1
+; GFX942-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: global_agent_atomic_fmax_ret_f64__amdgpu_no_fine_grained_memory:
; GFX11: ; %bb.0:
@@ -781,14 +781,14 @@ define void @global_agent_atomic_fmax_noret_f64__amdgpu_no_fine_grained_memory(p
; GFX12-NEXT: s_or_b32 exec_lo, exec_lo, s0
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: global_agent_atomic_fmax_noret_f64__amdgpu_no_fine_grained_memory:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: buffer_wbl2 sc1
-; GFX940-NEXT: global_atomic_max_f64 v[0:1], v[2:3], off
-; GFX940-NEXT: s_waitcnt vmcnt(0)
-; GFX940-NEXT: buffer_inv sc1
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: global_agent_atomic_fmax_noret_f64__amdgpu_no_fine_grained_memory:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: buffer_wbl2 sc1
+; GFX942-NEXT: global_atomic_max_f64 v[0:1], v[2:3], off
+; GFX942-NEXT: s_waitcnt vmcnt(0)
+; GFX942-NEXT: buffer_inv sc1
+; GFX942-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: global_agent_atomic_fmax_noret_f64__amdgpu_no_fine_grained_memory:
; GFX11: ; %bb.0:
@@ -911,30 +911,30 @@ define float @flat_agent_atomic_fmax_ret_f32__amdgpu_no_fine_grained_memory(ptr
; GFX12-NEXT: global_inv scope:SCOPE_DEV
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: flat_agent_atomic_fmax_ret_f32__amdgpu_no_fine_grained_memory:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: flat_load_dword v3, v[0:1]
-; GFX940-NEXT: s_mov_b64 s[0:1], 0
-; GFX940-NEXT: v_max_f32_e32 v2, v2, v2
-; GFX940-NEXT: .LBB8_1: ; %atomicrmw.start
-; GFX940-NEXT: ; =>This Inner Loop Header: Depth=1
-; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v5, v3
-; GFX940-NEXT: v_max_f32_e32 v3, v5, v5
-; GFX940-NEXT: v_max_f32_e32 v4, v3, v2
-; GFX940-NEXT: buffer_wbl2 sc1
-; GFX940-NEXT: flat_atomic_cmpswap v3, v[0:1], v[4:5] sc0
-; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
-; GFX940-NEXT: buffer_inv sc1
-; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, v3, v5
-; GFX940-NEXT: s_or_b64 s[0:1], vcc, s[0:1]
-; GFX940-NEXT: s_andn2_b64 exec, exec, s[0:1]
-; GFX940-NEXT: s_cbranch_execnz .LBB8_1
-; GFX940-NEXT: ; %bb.2: ; %atomicrmw.end
-; GFX940-NEXT: s_or_b64 exec, exec, s[0:1]
-; GFX940-NEXT: v_mov_b32_e32 v0, v3
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: flat_agent_atomic_fmax_ret_f32__amdgpu_no_fine_grained_memory:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: flat_load_dword v3, v[0:1]
+; GFX942-NEXT: s_mov_b64 s[0:1], 0
+; GFX942-NEXT: v_max_f32_e32 v2, v2, v2
+; GFX942-NEXT: .LBB8_1: ; %atomicrmw.start
+; GFX942-NEXT: ; =>This Inner Loop Header: Depth=1
+; GFX942-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX942-NEXT: v_mov_b32_e32 v5, v3
+; GFX942-NEXT: v_max_f32_e32 v3, v5, v5
+; GFX942-NEXT: v_max_f32_e32 v4, v3, v2
+; GFX942-NEXT: buffer_wbl2 sc1
+; GFX942-NEXT: flat_atomic_cmpswap v3, v[0:1], v[4:5] sc0
+; GFX942-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX942-NEXT: buffer_inv sc1
+; GFX942-NEXT: v_cmp_eq_u32_e32 vcc, v3, v5
+; GFX942-NEXT: s_or_b64 s[0:1], vcc, s[0:1]
+; GFX942-NEXT: s_andn2_b64 exec, exec, s[0:1]
+; GFX942-NEXT: s_cbranch_execnz .LBB8_1
+; GFX942-NEXT: ; %bb.2: ; %atomicrmw.end
+; GFX942-NEXT: s_or_b64 exec, exec, s[0:1]
+; GFX942-NEXT: v_mov_b32_e32 v0, v3
+; GFX942-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: flat_agent_atomic_fmax_ret_f32__amdgpu_no_fine_grained_memory:
; GFX11: ; %bb.0:
@@ -1053,29 +1053,29 @@ define void @flat_agent_atomic_fmax_noret_f32__amdgpu_no_fine_grained_memory(ptr
; GFX12-NEXT: global_inv scope:SCOPE_DEV
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: flat_agent_atomic_fmax_noret_f32__amdgpu_no_fine_grained_memory:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: flat_load_dword v3, v[0:1]
-; GFX940-NEXT: s_mov_b64 s[0:1], 0
-; GFX940-NEXT: v_max_f32_e32 v4, v2, v2
-; GFX940-NEXT: .LBB9_1: ; %atomicrmw.start
-; GFX940-NEXT: ; =>This Inner Loop Header: Depth=1
-; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
-; GFX940-NEXT: v_max_f32_e32 v2, v3, v3
-; GFX940-NEXT: v_max_f32_e32 v2, v2, v4
-; GFX940-NEXT: buffer_wbl2 sc1
-; GFX940-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] sc0
-; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
-; GFX940-NEXT: buffer_inv sc1
-; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, v2, v3
-; GFX940-NEXT: s_or_b64 s[0:1], vcc, s[0:1]
-; GFX940-NEXT: v_mov_b32_e32 v3, v2
-; GFX940-NEXT: s_andn2_b64 exec, exec, s[0:1]
-; GFX940-NEXT: s_cbranch_execnz .LBB9_1
-; GFX940-NEXT: ; %bb.2: ; %atomicrmw.end
-; GFX940-NEXT: s_or_b64 exec, exec, s[0:1]
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: flat_agent_atomic_fmax_noret_f32__amdgpu_no_fine_grained_memory:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: flat_load_dword v3, v[0:1]
+; GFX942-NEXT: s_mov_b64 s[0:1], 0
+; GFX942-NEXT: v_max_f32_e32 v4, v2, v2
+; GFX942-NEXT: .LBB9_1: ; %atomicrmw.start
+; GFX942-NEXT: ; =>This Inner Loop Header: Depth=1
+; GFX942-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX942-NEXT: v_max_f32_e32 v2, v3, v3
+; GFX942-NEXT: v_max_f32_e32 v2, v2, v4
+; GFX942-NEXT: buffer_wbl2 sc1
+; GFX942-NEXT: flat_atomic_cmpswap v2, v[0:1], v[2:3] sc0
+; GFX942-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX942-NEXT: buffer_inv sc1
+; GFX942-NEXT: v_cmp_eq_u32_e32 vcc, v2, v3
+; GFX942-NEXT: s_or_b64 s[0:1], vcc, s[0:1]
+; GFX942-NEXT: v_mov_b32_e32 v3, v2
+; GFX942-NEXT: s_andn2_b64 exec, exec, s[0:1]
+; GFX942-NEXT: s_cbranch_execnz .LBB9_1
+; GFX942-NEXT: ; %bb.2: ; %atomicrmw.end
+; GFX942-NEXT: s_or_b64 exec, exec, s[0:1]
+; GFX942-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: flat_agent_atomic_fmax_noret_f32__amdgpu_no_fine_grained_memory:
; GFX11: ; %bb.0:
@@ -1212,14 +1212,14 @@ define double @flat_agent_atomic_fmax_ret_f64__amdgpu_no_fine_grained_memory(ptr
; GFX12-NEXT: v_dual_mov_b32 v0, v4 :: v_dual_mov_b32 v1, v5
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: flat_agent_atomic_fmax_ret_f64__amdgpu_no_fine_grained_memory:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: buffer_wbl2 sc1
-; GFX940-NEXT: flat_atomic_max_f64 v[0:1], v[0:1], v[2:3] sc0
-; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
-; GFX940-NEXT: buffer_inv sc1
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: flat_agent_atomic_fmax_ret_f64__amdgpu_no_fine_grained_memory:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: buffer_wbl2 sc1
+; GFX942-NEXT: flat_atomic_max_f64 v[0:1], v[0:1], v[2:3] sc0
+; GFX942-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX942-NEXT: buffer_inv sc1
+; GFX942-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: flat_agent_atomic_fmax_ret_f64__amdgpu_no_fine_grained_memory:
; GFX11: ; %bb.0:
@@ -1365,14 +1365,14 @@ define void @flat_agent_atomic_fmax_noret_f64__amdgpu_no_fine_grained_memory(ptr
; GFX12-NEXT: s_or_b32 exec_lo, exec_lo, s0
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: flat_agent_atomic_fmax_noret_f64__amdgpu_no_fine_grained_memory:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: buffer_wbl2 sc1
-; GFX940-NEXT: flat_atomic_max_f64 v[0:1], v[2:3]
-; GFX940-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
-; GFX940-NEXT: buffer_inv sc1
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: flat_agent_atomic_fmax_noret_f64__amdgpu_no_fine_grained_memory:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: buffer_wbl2 sc1
+; GFX942-NEXT: flat_atomic_max_f64 v[0:1], v[2:3]
+; GFX942-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GFX942-NEXT: buffer_inv sc1
+; GFX942-NEXT: s_setpc_b64 s[30:31]
;
; GFX11-LABEL: flat_agent_atomic_fmax_noret_f64__amdgpu_no_fine_grained_memory:
; GFX11: ; %bb.0:
@@ -1497,32 +1497,32 @@ define float @buffer_fat_ptr_agent_atomic_fmax_ret_f32__amdgpu_no_fine_grained_m
; GFX12-NEXT: global_inv scope:SCOPE_DEV
; GFX12-NEXT: s_setpc_b64 s[30:31]
;
-; GFX940-LABEL: buffer_fat_ptr_agent_atomic_fmax_ret_f32__amdgpu_no_fine_grained_memory:
-; GFX940: ; %bb.0:
-; GFX940-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v2, s16
-; GFX940-NEXT: v_mov_b32_e32 v1, v0
-; GFX940-NEXT: buffer_load_dword v0, v2, s[0:3], 0 offen
-; GFX940-NEXT: s_mov_b64 s[4:5], 0
-; GFX940-NEXT: v_max_f32_e32 v3, v1, v1
-; GFX940-NEXT: .LBB12_1: ; %atomicrmw.start
-; GFX940-NEXT: ; =>This Inner Loop Header: Depth=1
-; GFX940-NEXT: s_waitcnt vmcnt(0)
-; GFX940-NEXT: v_mov_b32_e32 v5, v0
-; GFX940-NEXT: v_max_f32_e32 v0, v5, v5
-; GFX940-NEXT: v_max_f32_e32 v4, v0, v3
-; GFX940-NEXT: v_mov_b64_e32 v[0:1], v[4:5]
-; GFX940-NEXT: buffer_wbl2 sc1
-; GFX940-NEXT: buffer_atomic_cmpswap v[0:1], v2, s[0:3], 0 offen sc0
-; GFX940-NEXT: s_waitcnt vmcnt(0)
-; GFX940-NEXT: buffer_inv sc1
-; GFX940-NEXT: v_cmp_eq_u32_e32 vcc, v0, v5
-; GFX940-NEXT: s_or_b64 s[4:5], vcc, s[4:5]
-; GFX940-NEXT: s_andn2_b64 exec, exec, s[4:5]
-; GFX940-NEXT: s_cbranch_execnz .LBB12_1
-; GFX940-NEXT: ; %bb.2: ; %atomicrmw.end
-; GFX940-NEXT: s_or_b64 exec, exec, s[4:5]
-; GFX940-NEXT: s_setpc_b64 s[30:31]
+; GFX942-LABEL: buffer_fat_ptr_agent_atomic_fmax_ret_f32__amdgpu_no_fine_grained_memory:
+; GFX942: ; %bb.0:
+; GFX942-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX942-NEXT: v_mov_b32_e32 v2, s16
+; GFX942-NEXT: v_mov_b32_e32 v1, v0
+; GFX942-NEXT: buffer_load_dword v0, v2, s[0:3], 0 offen
+; GFX942-NEXT: s_mov_b64 s[4:5], 0
+; GFX942-NEXT: v_max_f32_e32 v3, v1, v1
+; GFX942-NEXT: .LBB12_1: ; %...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/125711
More information about the llvm-commits
mailing list