maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[GlobalISel]: Fix lowering of G_Shuffle_vector where we pick up the wrong source index 

https://reviews.llvm.org/D66182

llvm-svn: 368781
This commit is contained in:
Aditya Nandakumar 2019-08-14 01:23:33 +00:00
parent 21872bc9bf
commit c65ac865c3
2 changed files with 35 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/CodeGen/GlobalISel/LegalizerHelper.cpp
View File

@ -3824,7 +3824,6 @@ LegalizerHelper::lowerShuffleVector(MachineInstr &MI) {
LLT Src0Ty = MRI.getType(Src0Reg);
LLT DstTy = MRI.getType(DstReg);
LLT EltTy = DstTy.getElementType();
int NumElts = DstTy.getNumElements();
LLT IdxTy = LLT::scalar(32);
const Constant *ShufMask = MI.getOperand(3).getShuffleMask();
@ -3846,6 +3845,7 @@ LegalizerHelper::lowerShuffleVector(MachineInstr &MI) {
if (Src0Ty.isScalar()) {
BuildVec.push_back(Idx == 0 ? Src0Reg : Src1Reg);
} else {
int NumElts = Src0Ty.getNumElements();
Register SrcVec = Idx < NumElts ? Src0Reg : Src1Reg;
int ExtractIdx = Idx < NumElts ? Idx : Idx - NumElts;
auto IdxK = MIRBuilder.buildConstant(IdxTy, ExtractIdx);

41
llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-shuffle-vector.mir
View File

@ -182,6 +182,28 @@ body: |
...
---
name: shufflevector_v3s32_3_2_1_smaller
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2, $vgpr3_vgpr4_vgpr5
; CHECK-LABEL: name: shufflevector_v3s32_3_2_1_smaller
; CHECK: liveins: $vgpr0_vgpr1_vgpr2, $vgpr3_vgpr4_vgpr5
; CHECK: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; CHECK: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
; CHECK: [[EXTRACT:%[0-9]+]]:_(s32) = G_EXTRACT [[COPY]](<3 x s32>), 64
; CHECK: [[EXTRACT1:%[0-9]+]]:_(s32) = G_EXTRACT [[COPY]](<3 x s32>), 32
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[EXTRACT]](s32), [[EXTRACT1]](s32)
; CHECK: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
%0:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
%1:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
%2:_(<2 x s32>) = G_SHUFFLE_VECTOR %0, %1, shufflemask(2, 1)
$vgpr0_vgpr1 = COPY %2
...
---
name: shufflevector_v2s16_0_1
tracksRegLiveness: true
@ -247,7 +269,7 @@ body: |
; CHECK: [[SEXT1:%[0-9]+]]:_(s32) = G_SEXT [[UV1]](s16)
; CHECK: [[SEXT2:%[0-9]+]]:_(s32) = G_SEXT [[UV2]](s16)
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[SEXT]](s32), [[SEXT1]](s32), [[SEXT2]](s32)
; CHECK: [[EXTRACT2:%[0-9]+]]:_(s32) = G_EXTRACT [[BUILD_VECTOR]](<3 x s32>), 32
; CHECK: [[EXTRACT2:%[0-9]+]]:_(s32) = G_EXTRACT [[BUILD_VECTOR]](<3 x s32>), 64
; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[EXTRACT2]](s32)
; CHECK: [[UV3:%[0-9]+]]:_(s16), [[UV4:%[0-9]+]]:_(s16), [[UV5:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[EXTRACT]](<3 x s16>)
; CHECK: [[SEXT3:%[0-9]+]]:_(s32) = G_SEXT [[UV3]](s16)
@ -256,17 +278,22 @@ body: |
; CHECK: [[BUILD_VECTOR1:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[SEXT3]](s32), [[SEXT4]](s32), [[SEXT5]](s32)
; CHECK: [[EXTRACT3:%[0-9]+]]:_(s32) = G_EXTRACT [[BUILD_VECTOR1]](<3 x s32>), 32
; CHECK: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[EXTRACT3]](s32)
; CHECK: [[DEF:%[0-9]+]]:_(s32) = G_IMPLICIT_DEF
; CHECK: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[DEF]](s32)
; CHECK: [[UV6:%[0-9]+]]:_(s16), [[UV7:%[0-9]+]]:_(s16), [[UV8:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[EXTRACT]](<3 x s16>)
; CHECK: [[UV6:%[0-9]+]]:_(s16), [[UV7:%[0-9]+]]:_(s16), [[UV8:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[EXTRACT1]](<3 x s16>)
; CHECK: [[SEXT6:%[0-9]+]]:_(s32) = G_SEXT [[UV6]](s16)
; CHECK: [[SEXT7:%[0-9]+]]:_(s32) = G_SEXT [[UV7]](s16)
; CHECK: [[SEXT8:%[0-9]+]]:_(s32) = G_SEXT [[UV8]](s16)
; CHECK: [[BUILD_VECTOR2:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[SEXT6]](s32), [[SEXT7]](s32), [[SEXT8]](s32)
; CHECK: [[EXTRACT4:%[0-9]+]]:_(s32) = G_EXTRACT [[BUILD_VECTOR2]](<3 x s32>), 0
; CHECK: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[EXTRACT4]](s32)
; CHECK: [[BUILD_VECTOR3:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16), [[TRUNC2]](s16), [[TRUNC3]](s16)
; CHECK: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR3]](<4 x s16>)
; CHECK: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[EXTRACT4]](s32)
; CHECK: [[UV9:%[0-9]+]]:_(s16), [[UV10:%[0-9]+]]:_(s16), [[UV11:%[0-9]+]]:_(s16) = G_UNMERGE_VALUES [[EXTRACT]](<3 x s16>)
; CHECK: [[SEXT9:%[0-9]+]]:_(s32) = G_SEXT [[UV9]](s16)
; CHECK: [[SEXT10:%[0-9]+]]:_(s32) = G_SEXT [[UV10]](s16)
; CHECK: [[SEXT11:%[0-9]+]]:_(s32) = G_SEXT [[UV11]](s16)
; CHECK: [[BUILD_VECTOR3:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[SEXT9]](s32), [[SEXT10]](s32), [[SEXT11]](s32)
; CHECK: [[EXTRACT5:%[0-9]+]]:_(s32) = G_EXTRACT [[BUILD_VECTOR3]](<3 x s32>), 0
; CHECK: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[EXTRACT5]](s32)
; CHECK: [[BUILD_VECTOR4:%[0-9]+]]:_(<4 x s16>) = G_BUILD_VECTOR [[TRUNC]](s16), [[TRUNC1]](s16), [[TRUNC2]](s16), [[TRUNC3]](s16)
; CHECK: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR4]](<4 x s16>)
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
%1:_(<4 x s16>) = COPY $vgpr2_vgpr3
%2:_(<3 x s16>) = G_EXTRACT %0, 0