From 9ce4f372067c0e2cb5844c4a8e52c8cacd6877c5 Mon Sep 17 00:00:00 2001 From: Jay Foad Date: Fri, 1 Oct 2021 13:30:42 +0100 Subject: [PATCH] [AMDGPU][GlobalISel] Fix legalization of G_UMULH Scalarize before narrowing because the narrowing implementation does not work on vectors. This matches what we do for regular G_MUL. Differential Revision: https://reviews.llvm.org/D111129 --- llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp | 2 +- .../CodeGen/AMDGPU/GlobalISel/legalize-umulh.mir | 126 ++++++++++++++- .../CodeGen/AMDGPU/GlobalISel/legalize-umulo.mir | 180 +++++++++++++++++++++ 3 files changed, 305 insertions(+), 3 deletions(-) diff --git a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp index c9230e1..92d2ecc 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp @@ -606,7 +606,7 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST_, auto &Mulh = getActionDefinitionsBuilder({G_UMULH, G_SMULH}) .legalFor({S32}) - .maxScalarOrElt(0, S32); + .maxScalar(0, S32); if (ST.hasVOP3PInsts()) { Mulh diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulh.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulh.mir index d081680..3c66fb4 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulh.mir +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulh.mir @@ -1,6 +1,6 @@ # NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py -# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -global-isel-abort=0 -O0 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=GFX8 -# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx906 -global-isel-abort=0 -O0 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=GFX9 +# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -O0 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=GFX8 +# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx906 -O0 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=GFX9 --- name: test_umulh_s32 @@ -123,6 +123,128 @@ body: | ... --- +name: test_umulh_v2s64 +body: | + bb.0: + liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7 + + ; GFX8-LABEL: name: test_umulh_v2s64 + ; GFX8: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX8: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX8: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>) + ; GFX8: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>) + ; GFX8: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV]](s64) + ; GFX8: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV2]](s64) + ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[UV5]], [[UV6]] + ; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[UV4]], [[UV7]] + ; GFX8: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[UV4]], [[UV6]] + ; GFX8: [[UADDO:%[0-9]+]]:_(s32), [[UADDO1:%[0-9]+]]:_(s1) = G_UADDO [[MUL]], [[MUL1]] + ; GFX8: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO1]](s1) + ; GFX8: [[UADDO2:%[0-9]+]]:_(s32), [[UADDO3:%[0-9]+]]:_(s1) = G_UADDO [[UADDO]], [[UMULH]] + ; GFX8: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO3]](s1) + ; GFX8: [[ADD:%[0-9]+]]:_(s32) = G_ADD [[ZEXT]], [[ZEXT1]] + ; GFX8: [[MUL2:%[0-9]+]]:_(s32) = G_MUL [[UV5]], [[UV7]] + ; GFX8: [[UMULH1:%[0-9]+]]:_(s32) = G_UMULH [[UV5]], [[UV6]] + ; GFX8: [[UMULH2:%[0-9]+]]:_(s32) = G_UMULH [[UV4]], [[UV7]] + ; GFX8: [[UADDO4:%[0-9]+]]:_(s32), [[UADDO5:%[0-9]+]]:_(s1) = G_UADDO [[MUL2]], [[UMULH1]] + ; GFX8: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO5]](s1) + ; GFX8: [[UADDO6:%[0-9]+]]:_(s32), [[UADDO7:%[0-9]+]]:_(s1) = G_UADDO [[UADDO4]], [[UMULH2]] + ; GFX8: [[ZEXT3:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO7]](s1) + ; GFX8: [[ADD1:%[0-9]+]]:_(s32) = G_ADD [[ZEXT2]], [[ZEXT3]] + ; GFX8: [[UADDO8:%[0-9]+]]:_(s32), [[UADDO9:%[0-9]+]]:_(s1) = G_UADDO [[UADDO6]], [[ADD]] + ; GFX8: [[ZEXT4:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO9]](s1) + ; GFX8: [[ADD2:%[0-9]+]]:_(s32) = G_ADD [[ADD1]], [[ZEXT4]] + ; GFX8: [[UMULH3:%[0-9]+]]:_(s32) = G_UMULH [[UV5]], [[UV7]] + ; GFX8: [[ADD3:%[0-9]+]]:_(s32) = G_ADD [[UMULH3]], [[ADD2]] + ; GFX8: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[UADDO8]](s32), [[ADD3]](s32) + ; GFX8: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV1]](s64) + ; GFX8: [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV3]](s64) + ; GFX8: [[MUL3:%[0-9]+]]:_(s32) = G_MUL [[UV9]], [[UV10]] + ; GFX8: [[MUL4:%[0-9]+]]:_(s32) = G_MUL [[UV8]], [[UV11]] + ; GFX8: [[UMULH4:%[0-9]+]]:_(s32) = G_UMULH [[UV8]], [[UV10]] + ; GFX8: [[UADDO10:%[0-9]+]]:_(s32), [[UADDO11:%[0-9]+]]:_(s1) = G_UADDO [[MUL3]], [[MUL4]] + ; GFX8: [[ZEXT5:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO11]](s1) + ; GFX8: [[UADDO12:%[0-9]+]]:_(s32), [[UADDO13:%[0-9]+]]:_(s1) = G_UADDO [[UADDO10]], [[UMULH4]] + ; GFX8: [[ZEXT6:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO13]](s1) + ; GFX8: [[ADD4:%[0-9]+]]:_(s32) = G_ADD [[ZEXT5]], [[ZEXT6]] + ; GFX8: [[MUL5:%[0-9]+]]:_(s32) = G_MUL [[UV9]], [[UV11]] + ; GFX8: [[UMULH5:%[0-9]+]]:_(s32) = G_UMULH [[UV9]], [[UV10]] + ; GFX8: [[UMULH6:%[0-9]+]]:_(s32) = G_UMULH [[UV8]], [[UV11]] + ; GFX8: [[UADDO14:%[0-9]+]]:_(s32), [[UADDO15:%[0-9]+]]:_(s1) = G_UADDO [[MUL5]], [[UMULH5]] + ; GFX8: [[ZEXT7:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO15]](s1) + ; GFX8: [[UADDO16:%[0-9]+]]:_(s32), [[UADDO17:%[0-9]+]]:_(s1) = G_UADDO [[UADDO14]], [[UMULH6]] + ; GFX8: [[ZEXT8:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO17]](s1) + ; GFX8: [[ADD5:%[0-9]+]]:_(s32) = G_ADD [[ZEXT7]], [[ZEXT8]] + ; GFX8: [[UADDO18:%[0-9]+]]:_(s32), [[UADDO19:%[0-9]+]]:_(s1) = G_UADDO [[UADDO16]], [[ADD4]] + ; GFX8: [[ZEXT9:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO19]](s1) + ; GFX8: [[ADD6:%[0-9]+]]:_(s32) = G_ADD [[ADD5]], [[ZEXT9]] + ; GFX8: [[UMULH7:%[0-9]+]]:_(s32) = G_UMULH [[UV9]], [[UV11]] + ; GFX8: [[ADD7:%[0-9]+]]:_(s32) = G_ADD [[UMULH7]], [[ADD6]] + ; GFX8: [[MV1:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[UADDO18]](s32), [[ADD7]](s32) + ; GFX8: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[MV]](s64), [[MV1]](s64) + ; GFX8: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>) + ; GFX9-LABEL: name: test_umulh_v2s64 + ; GFX9: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX9: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>) + ; GFX9: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>) + ; GFX9: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV]](s64) + ; GFX9: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV2]](s64) + ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[UV5]], [[UV6]] + ; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[UV4]], [[UV7]] + ; GFX9: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[UV4]], [[UV6]] + ; GFX9: [[UADDO:%[0-9]+]]:_(s32), [[UADDO1:%[0-9]+]]:_(s1) = G_UADDO [[MUL]], [[MUL1]] + ; GFX9: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO1]](s1) + ; GFX9: [[UADDO2:%[0-9]+]]:_(s32), [[UADDO3:%[0-9]+]]:_(s1) = G_UADDO [[UADDO]], [[UMULH]] + ; GFX9: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO3]](s1) + ; GFX9: [[ADD:%[0-9]+]]:_(s32) = G_ADD [[ZEXT]], [[ZEXT1]] + ; GFX9: [[MUL2:%[0-9]+]]:_(s32) = G_MUL [[UV5]], [[UV7]] + ; GFX9: [[UMULH1:%[0-9]+]]:_(s32) = G_UMULH [[UV5]], [[UV6]] + ; GFX9: [[UMULH2:%[0-9]+]]:_(s32) = G_UMULH [[UV4]], [[UV7]] + ; GFX9: [[UADDO4:%[0-9]+]]:_(s32), [[UADDO5:%[0-9]+]]:_(s1) = G_UADDO [[MUL2]], [[UMULH1]] + ; GFX9: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO5]](s1) + ; GFX9: [[UADDO6:%[0-9]+]]:_(s32), [[UADDO7:%[0-9]+]]:_(s1) = G_UADDO [[UADDO4]], [[UMULH2]] + ; GFX9: [[ZEXT3:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO7]](s1) + ; GFX9: [[ADD1:%[0-9]+]]:_(s32) = G_ADD [[ZEXT2]], [[ZEXT3]] + ; GFX9: [[UADDO8:%[0-9]+]]:_(s32), [[UADDO9:%[0-9]+]]:_(s1) = G_UADDO [[UADDO6]], [[ADD]] + ; GFX9: [[ZEXT4:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO9]](s1) + ; GFX9: [[ADD2:%[0-9]+]]:_(s32) = G_ADD [[ADD1]], [[ZEXT4]] + ; GFX9: [[UMULH3:%[0-9]+]]:_(s32) = G_UMULH [[UV5]], [[UV7]] + ; GFX9: [[ADD3:%[0-9]+]]:_(s32) = G_ADD [[UMULH3]], [[ADD2]] + ; GFX9: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[UADDO8]](s32), [[ADD3]](s32) + ; GFX9: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV1]](s64) + ; GFX9: [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV3]](s64) + ; GFX9: [[MUL3:%[0-9]+]]:_(s32) = G_MUL [[UV9]], [[UV10]] + ; GFX9: [[MUL4:%[0-9]+]]:_(s32) = G_MUL [[UV8]], [[UV11]] + ; GFX9: [[UMULH4:%[0-9]+]]:_(s32) = G_UMULH [[UV8]], [[UV10]] + ; GFX9: [[UADDO10:%[0-9]+]]:_(s32), [[UADDO11:%[0-9]+]]:_(s1) = G_UADDO [[MUL3]], [[MUL4]] + ; GFX9: [[ZEXT5:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO11]](s1) + ; GFX9: [[UADDO12:%[0-9]+]]:_(s32), [[UADDO13:%[0-9]+]]:_(s1) = G_UADDO [[UADDO10]], [[UMULH4]] + ; GFX9: [[ZEXT6:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO13]](s1) + ; GFX9: [[ADD4:%[0-9]+]]:_(s32) = G_ADD [[ZEXT5]], [[ZEXT6]] + ; GFX9: [[MUL5:%[0-9]+]]:_(s32) = G_MUL [[UV9]], [[UV11]] + ; GFX9: [[UMULH5:%[0-9]+]]:_(s32) = G_UMULH [[UV9]], [[UV10]] + ; GFX9: [[UMULH6:%[0-9]+]]:_(s32) = G_UMULH [[UV8]], [[UV11]] + ; GFX9: [[UADDO14:%[0-9]+]]:_(s32), [[UADDO15:%[0-9]+]]:_(s1) = G_UADDO [[MUL5]], [[UMULH5]] + ; GFX9: [[ZEXT7:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO15]](s1) + ; GFX9: [[UADDO16:%[0-9]+]]:_(s32), [[UADDO17:%[0-9]+]]:_(s1) = G_UADDO [[UADDO14]], [[UMULH6]] + ; GFX9: [[ZEXT8:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO17]](s1) + ; GFX9: [[ADD5:%[0-9]+]]:_(s32) = G_ADD [[ZEXT7]], [[ZEXT8]] + ; GFX9: [[UADDO18:%[0-9]+]]:_(s32), [[UADDO19:%[0-9]+]]:_(s1) = G_UADDO [[UADDO16]], [[ADD4]] + ; GFX9: [[ZEXT9:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO19]](s1) + ; GFX9: [[ADD6:%[0-9]+]]:_(s32) = G_ADD [[ADD5]], [[ZEXT9]] + ; GFX9: [[UMULH7:%[0-9]+]]:_(s32) = G_UMULH [[UV9]], [[UV11]] + ; GFX9: [[ADD7:%[0-9]+]]:_(s32) = G_ADD [[UMULH7]], [[ADD6]] + ; GFX9: [[MV1:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[UADDO18]](s32), [[ADD7]](s32) + ; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[MV]](s64), [[MV1]](s64) + ; GFX9: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>) + %0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 + %1:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 + %2:_(<2 x s64>) = G_UMULH %0, %1 + $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %2 +... + +--- name: test_umulh_s16 body: | bb.0: diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulo.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulo.mir index ed5b2f4..47077c7 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulo.mir +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-umulo.mir @@ -189,6 +189,186 @@ body: | ... --- +name: test_umulo_v2s64 +body: | + bb.0: + liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7 + + ; GFX8-LABEL: name: test_umulo_v2s64 + ; GFX8: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX8: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX8: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>) + ; GFX8: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>) + ; GFX8: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV]](s64) + ; GFX8: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV2]](s64) + ; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[UV5]], [[UV6]] + ; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[UV4]], [[UV7]] + ; GFX8: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[UV4]], [[UV6]] + ; GFX8: [[UADDO:%[0-9]+]]:_(s32), [[UADDO1:%[0-9]+]]:_(s1) = G_UADDO [[MUL]], [[MUL1]] + ; GFX8: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO1]](s1) + ; GFX8: [[UADDO2:%[0-9]+]]:_(s32), [[UADDO3:%[0-9]+]]:_(s1) = G_UADDO [[UADDO]], [[UMULH]] + ; GFX8: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO3]](s1) + ; GFX8: [[ADD:%[0-9]+]]:_(s32) = G_ADD [[ZEXT]], [[ZEXT1]] + ; GFX8: [[MUL2:%[0-9]+]]:_(s32) = G_MUL [[UV5]], [[UV7]] + ; GFX8: [[UMULH1:%[0-9]+]]:_(s32) = G_UMULH [[UV5]], [[UV6]] + ; GFX8: [[UMULH2:%[0-9]+]]:_(s32) = G_UMULH [[UV4]], [[UV7]] + ; GFX8: [[UADDO4:%[0-9]+]]:_(s32), [[UADDO5:%[0-9]+]]:_(s1) = G_UADDO [[MUL2]], [[UMULH1]] + ; GFX8: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO5]](s1) + ; GFX8: [[UADDO6:%[0-9]+]]:_(s32), [[UADDO7:%[0-9]+]]:_(s1) = G_UADDO [[UADDO4]], [[UMULH2]] + ; GFX8: [[ZEXT3:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO7]](s1) + ; GFX8: [[ADD1:%[0-9]+]]:_(s32) = G_ADD [[ZEXT2]], [[ZEXT3]] + ; GFX8: [[UADDO8:%[0-9]+]]:_(s32), [[UADDO9:%[0-9]+]]:_(s1) = G_UADDO [[UADDO6]], [[ADD]] + ; GFX8: [[ZEXT4:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO9]](s1) + ; GFX8: [[ADD2:%[0-9]+]]:_(s32) = G_ADD [[ADD1]], [[ZEXT4]] + ; GFX8: [[UMULH3:%[0-9]+]]:_(s32) = G_UMULH [[UV5]], [[UV7]] + ; GFX8: [[ADD3:%[0-9]+]]:_(s32) = G_ADD [[UMULH3]], [[ADD2]] + ; GFX8: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[UADDO8]](s32), [[ADD3]](s32) + ; GFX8: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 0 + ; GFX8: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV]](s64) + ; GFX8: [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV2]](s64) + ; GFX8: [[MUL3:%[0-9]+]]:_(s32) = G_MUL [[UV8]], [[UV10]] + ; GFX8: [[MUL4:%[0-9]+]]:_(s32) = G_MUL [[UV9]], [[UV10]] + ; GFX8: [[MUL5:%[0-9]+]]:_(s32) = G_MUL [[UV8]], [[UV11]] + ; GFX8: [[UMULH4:%[0-9]+]]:_(s32) = G_UMULH [[UV8]], [[UV10]] + ; GFX8: [[ADD4:%[0-9]+]]:_(s32) = G_ADD [[MUL4]], [[MUL5]] + ; GFX8: [[ADD5:%[0-9]+]]:_(s32) = G_ADD [[ADD4]], [[UMULH4]] + ; GFX8: [[MV1:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[MUL3]](s32), [[ADD5]](s32) + ; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MV]](s64), [[C]] + ; GFX8: [[UV12:%[0-9]+]]:_(s32), [[UV13:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV1]](s64) + ; GFX8: [[UV14:%[0-9]+]]:_(s32), [[UV15:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV3]](s64) + ; GFX8: [[MUL6:%[0-9]+]]:_(s32) = G_MUL [[UV13]], [[UV14]] + ; GFX8: [[MUL7:%[0-9]+]]:_(s32) = G_MUL [[UV12]], [[UV15]] + ; GFX8: [[UMULH5:%[0-9]+]]:_(s32) = G_UMULH [[UV12]], [[UV14]] + ; GFX8: [[UADDO10:%[0-9]+]]:_(s32), [[UADDO11:%[0-9]+]]:_(s1) = G_UADDO [[MUL6]], [[MUL7]] + ; GFX8: [[ZEXT5:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO11]](s1) + ; GFX8: [[UADDO12:%[0-9]+]]:_(s32), [[UADDO13:%[0-9]+]]:_(s1) = G_UADDO [[UADDO10]], [[UMULH5]] + ; GFX8: [[ZEXT6:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO13]](s1) + ; GFX8: [[ADD6:%[0-9]+]]:_(s32) = G_ADD [[ZEXT5]], [[ZEXT6]] + ; GFX8: [[MUL8:%[0-9]+]]:_(s32) = G_MUL [[UV13]], [[UV15]] + ; GFX8: [[UMULH6:%[0-9]+]]:_(s32) = G_UMULH [[UV13]], [[UV14]] + ; GFX8: [[UMULH7:%[0-9]+]]:_(s32) = G_UMULH [[UV12]], [[UV15]] + ; GFX8: [[UADDO14:%[0-9]+]]:_(s32), [[UADDO15:%[0-9]+]]:_(s1) = G_UADDO [[MUL8]], [[UMULH6]] + ; GFX8: [[ZEXT7:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO15]](s1) + ; GFX8: [[UADDO16:%[0-9]+]]:_(s32), [[UADDO17:%[0-9]+]]:_(s1) = G_UADDO [[UADDO14]], [[UMULH7]] + ; GFX8: [[ZEXT8:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO17]](s1) + ; GFX8: [[ADD7:%[0-9]+]]:_(s32) = G_ADD [[ZEXT7]], [[ZEXT8]] + ; GFX8: [[UADDO18:%[0-9]+]]:_(s32), [[UADDO19:%[0-9]+]]:_(s1) = G_UADDO [[UADDO16]], [[ADD6]] + ; GFX8: [[ZEXT9:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO19]](s1) + ; GFX8: [[ADD8:%[0-9]+]]:_(s32) = G_ADD [[ADD7]], [[ZEXT9]] + ; GFX8: [[UMULH8:%[0-9]+]]:_(s32) = G_UMULH [[UV13]], [[UV15]] + ; GFX8: [[ADD9:%[0-9]+]]:_(s32) = G_ADD [[UMULH8]], [[ADD8]] + ; GFX8: [[MV2:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[UADDO18]](s32), [[ADD9]](s32) + ; GFX8: [[UV16:%[0-9]+]]:_(s32), [[UV17:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV1]](s64) + ; GFX8: [[UV18:%[0-9]+]]:_(s32), [[UV19:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV3]](s64) + ; GFX8: [[MUL9:%[0-9]+]]:_(s32) = G_MUL [[UV16]], [[UV18]] + ; GFX8: [[MUL10:%[0-9]+]]:_(s32) = G_MUL [[UV17]], [[UV18]] + ; GFX8: [[MUL11:%[0-9]+]]:_(s32) = G_MUL [[UV16]], [[UV19]] + ; GFX8: [[UMULH9:%[0-9]+]]:_(s32) = G_UMULH [[UV16]], [[UV18]] + ; GFX8: [[ADD10:%[0-9]+]]:_(s32) = G_ADD [[MUL10]], [[MUL11]] + ; GFX8: [[ADD11:%[0-9]+]]:_(s32) = G_ADD [[ADD10]], [[UMULH9]] + ; GFX8: [[MV3:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[MUL9]](s32), [[ADD11]](s32) + ; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MV2]](s64), [[C]] + ; GFX8: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[MV1]](s64), [[MV3]](s64) + ; GFX8: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 1 + ; GFX8: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[ICMP]](s1) + ; GFX8: [[AND:%[0-9]+]]:_(s64) = G_AND [[ANYEXT]], [[C1]] + ; GFX8: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[ICMP1]](s1) + ; GFX8: [[AND1:%[0-9]+]]:_(s64) = G_AND [[ANYEXT1]], [[C1]] + ; GFX8: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[AND]](s64), [[AND1]](s64) + ; GFX8: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>) + ; GFX8: $vgpr4_vgpr5_vgpr6_vgpr7 = COPY [[BUILD_VECTOR1]](<2 x s64>) + ; GFX9-LABEL: name: test_umulo_v2s64 + ; GFX9: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX9: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>) + ; GFX9: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>) + ; GFX9: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV]](s64) + ; GFX9: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV2]](s64) + ; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[UV5]], [[UV6]] + ; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[UV4]], [[UV7]] + ; GFX9: [[UMULH:%[0-9]+]]:_(s32) = G_UMULH [[UV4]], [[UV6]] + ; GFX9: [[UADDO:%[0-9]+]]:_(s32), [[UADDO1:%[0-9]+]]:_(s1) = G_UADDO [[MUL]], [[MUL1]] + ; GFX9: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO1]](s1) + ; GFX9: [[UADDO2:%[0-9]+]]:_(s32), [[UADDO3:%[0-9]+]]:_(s1) = G_UADDO [[UADDO]], [[UMULH]] + ; GFX9: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO3]](s1) + ; GFX9: [[ADD:%[0-9]+]]:_(s32) = G_ADD [[ZEXT]], [[ZEXT1]] + ; GFX9: [[MUL2:%[0-9]+]]:_(s32) = G_MUL [[UV5]], [[UV7]] + ; GFX9: [[UMULH1:%[0-9]+]]:_(s32) = G_UMULH [[UV5]], [[UV6]] + ; GFX9: [[UMULH2:%[0-9]+]]:_(s32) = G_UMULH [[UV4]], [[UV7]] + ; GFX9: [[UADDO4:%[0-9]+]]:_(s32), [[UADDO5:%[0-9]+]]:_(s1) = G_UADDO [[MUL2]], [[UMULH1]] + ; GFX9: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO5]](s1) + ; GFX9: [[UADDO6:%[0-9]+]]:_(s32), [[UADDO7:%[0-9]+]]:_(s1) = G_UADDO [[UADDO4]], [[UMULH2]] + ; GFX9: [[ZEXT3:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO7]](s1) + ; GFX9: [[ADD1:%[0-9]+]]:_(s32) = G_ADD [[ZEXT2]], [[ZEXT3]] + ; GFX9: [[UADDO8:%[0-9]+]]:_(s32), [[UADDO9:%[0-9]+]]:_(s1) = G_UADDO [[UADDO6]], [[ADD]] + ; GFX9: [[ZEXT4:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO9]](s1) + ; GFX9: [[ADD2:%[0-9]+]]:_(s32) = G_ADD [[ADD1]], [[ZEXT4]] + ; GFX9: [[UMULH3:%[0-9]+]]:_(s32) = G_UMULH [[UV5]], [[UV7]] + ; GFX9: [[ADD3:%[0-9]+]]:_(s32) = G_ADD [[UMULH3]], [[ADD2]] + ; GFX9: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[UADDO8]](s32), [[ADD3]](s32) + ; GFX9: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 0 + ; GFX9: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV]](s64) + ; GFX9: [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV2]](s64) + ; GFX9: [[MUL3:%[0-9]+]]:_(s32) = G_MUL [[UV8]], [[UV10]] + ; GFX9: [[MUL4:%[0-9]+]]:_(s32) = G_MUL [[UV9]], [[UV10]] + ; GFX9: [[MUL5:%[0-9]+]]:_(s32) = G_MUL [[UV8]], [[UV11]] + ; GFX9: [[UMULH4:%[0-9]+]]:_(s32) = G_UMULH [[UV8]], [[UV10]] + ; GFX9: [[ADD4:%[0-9]+]]:_(s32) = G_ADD [[MUL4]], [[MUL5]] + ; GFX9: [[ADD5:%[0-9]+]]:_(s32) = G_ADD [[ADD4]], [[UMULH4]] + ; GFX9: [[MV1:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[MUL3]](s32), [[ADD5]](s32) + ; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MV]](s64), [[C]] + ; GFX9: [[UV12:%[0-9]+]]:_(s32), [[UV13:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV1]](s64) + ; GFX9: [[UV14:%[0-9]+]]:_(s32), [[UV15:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV3]](s64) + ; GFX9: [[MUL6:%[0-9]+]]:_(s32) = G_MUL [[UV13]], [[UV14]] + ; GFX9: [[MUL7:%[0-9]+]]:_(s32) = G_MUL [[UV12]], [[UV15]] + ; GFX9: [[UMULH5:%[0-9]+]]:_(s32) = G_UMULH [[UV12]], [[UV14]] + ; GFX9: [[UADDO10:%[0-9]+]]:_(s32), [[UADDO11:%[0-9]+]]:_(s1) = G_UADDO [[MUL6]], [[MUL7]] + ; GFX9: [[ZEXT5:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO11]](s1) + ; GFX9: [[UADDO12:%[0-9]+]]:_(s32), [[UADDO13:%[0-9]+]]:_(s1) = G_UADDO [[UADDO10]], [[UMULH5]] + ; GFX9: [[ZEXT6:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO13]](s1) + ; GFX9: [[ADD6:%[0-9]+]]:_(s32) = G_ADD [[ZEXT5]], [[ZEXT6]] + ; GFX9: [[MUL8:%[0-9]+]]:_(s32) = G_MUL [[UV13]], [[UV15]] + ; GFX9: [[UMULH6:%[0-9]+]]:_(s32) = G_UMULH [[UV13]], [[UV14]] + ; GFX9: [[UMULH7:%[0-9]+]]:_(s32) = G_UMULH [[UV12]], [[UV15]] + ; GFX9: [[UADDO14:%[0-9]+]]:_(s32), [[UADDO15:%[0-9]+]]:_(s1) = G_UADDO [[MUL8]], [[UMULH6]] + ; GFX9: [[ZEXT7:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO15]](s1) + ; GFX9: [[UADDO16:%[0-9]+]]:_(s32), [[UADDO17:%[0-9]+]]:_(s1) = G_UADDO [[UADDO14]], [[UMULH7]] + ; GFX9: [[ZEXT8:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO17]](s1) + ; GFX9: [[ADD7:%[0-9]+]]:_(s32) = G_ADD [[ZEXT7]], [[ZEXT8]] + ; GFX9: [[UADDO18:%[0-9]+]]:_(s32), [[UADDO19:%[0-9]+]]:_(s1) = G_UADDO [[UADDO16]], [[ADD6]] + ; GFX9: [[ZEXT9:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO19]](s1) + ; GFX9: [[ADD8:%[0-9]+]]:_(s32) = G_ADD [[ADD7]], [[ZEXT9]] + ; GFX9: [[UMULH8:%[0-9]+]]:_(s32) = G_UMULH [[UV13]], [[UV15]] + ; GFX9: [[ADD9:%[0-9]+]]:_(s32) = G_ADD [[UMULH8]], [[ADD8]] + ; GFX9: [[MV2:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[UADDO18]](s32), [[ADD9]](s32) + ; GFX9: [[UV16:%[0-9]+]]:_(s32), [[UV17:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV1]](s64) + ; GFX9: [[UV18:%[0-9]+]]:_(s32), [[UV19:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV3]](s64) + ; GFX9: [[MUL9:%[0-9]+]]:_(s32) = G_MUL [[UV16]], [[UV18]] + ; GFX9: [[MUL10:%[0-9]+]]:_(s32) = G_MUL [[UV17]], [[UV18]] + ; GFX9: [[MUL11:%[0-9]+]]:_(s32) = G_MUL [[UV16]], [[UV19]] + ; GFX9: [[UMULH9:%[0-9]+]]:_(s32) = G_UMULH [[UV16]], [[UV18]] + ; GFX9: [[ADD10:%[0-9]+]]:_(s32) = G_ADD [[MUL10]], [[MUL11]] + ; GFX9: [[ADD11:%[0-9]+]]:_(s32) = G_ADD [[ADD10]], [[UMULH9]] + ; GFX9: [[MV3:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[MUL9]](s32), [[ADD11]](s32) + ; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MV2]](s64), [[C]] + ; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[MV1]](s64), [[MV3]](s64) + ; GFX9: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 1 + ; GFX9: [[ANYEXT:%[0-9]+]]:_(s64) = G_ANYEXT [[ICMP]](s1) + ; GFX9: [[AND:%[0-9]+]]:_(s64) = G_AND [[ANYEXT]], [[C1]] + ; GFX9: [[ANYEXT1:%[0-9]+]]:_(s64) = G_ANYEXT [[ICMP1]](s1) + ; GFX9: [[AND1:%[0-9]+]]:_(s64) = G_AND [[ANYEXT1]], [[C1]] + ; GFX9: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[AND]](s64), [[AND1]](s64) + ; GFX9: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>) + ; GFX9: $vgpr4_vgpr5_vgpr6_vgpr7 = COPY [[BUILD_VECTOR1]](<2 x s64>) + %0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 + %1:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 + %2:_(<2 x s64>), %3:_(<2 x s1>) = G_UMULO %0, %1 + %4:_(<2 x s64>) = G_ZEXT %3 + $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %2 + $vgpr4_vgpr5_vgpr6_vgpr7 = COPY %4 +... + +--- name: test_umulo_s24 body: | bb.0: -- 2.7.4