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

GlobalISel: Fix assertion on wide G_ZEXT sources 

It's possible to have a type that needs a mask greater than 64-bits.
This commit is contained in:
Matt Arsenault 2020-01-10 17:50:45 -05:00 committed by Matt Arsenault
parent a70b993239
commit d7d88b9d8b
2 changed files with 27 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/include/llvm/CodeGen/GlobalISel/LegalizationArtifactCombiner.h
View File

@ -113,7 +113,8 @@ public:
LLVM_DEBUG(dbgs() << ".. Combine MI: " << MI;);
LLT SrcTy = MRI.getType(SrcReg);
APInt Mask = APInt::getAllOnesValue(SrcTy.getScalarSizeInBits());
auto MIBMask = Builder.buildConstant(DstTy, Mask.getZExtValue());
auto MIBMask = Builder.buildConstant(
DstTy, Mask.zext(DstTy.getScalarSizeInBits()));
Builder.buildAnd(DstReg, Builder.buildAnyExtOrTrunc(DstTy, TruncSrc),
MIBMask);
markInstAndDefDead(MI, *MRI.getVRegDef(SrcReg), DeadInsts);

25
llvm/test/CodeGen/AMDGPU/GlobalISel/artifact-combiner-zext.mir
View File

@ -88,3 +88,28 @@ body: |
%2:_(<3 x s32>) = G_ZEXT %1
$vgpr0_vgpr1_vgpr2 = COPY %2
...
# Test for "Too many bits for uint64_t" assertion when combining
# zexts with wide sources.
---
name: test_zext_128_trunc_s128_merge
body: |
bb.0:
liveins: $vgpr0_vgpr1
; CHECK-LABEL: name: test_zext_128_trunc_s128_merge
; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; CHECK: [[C:%[0-9]+]]:_(s64) = G_CONSTANT i64 -1
; CHECK: [[C1:%[0-9]+]]:_(s64) = G_CONSTANT i64 4294967295
; CHECK: [[AND:%[0-9]+]]:_(s64) = G_AND [[COPY]], [[C]]
; CHECK: [[AND1:%[0-9]+]]:_(s64) = G_AND [[COPY1]], [[C1]]
; CHECK: [[MV:%[0-9]+]]:_(s128) = G_MERGE_VALUES [[AND]](s64), [[AND1]](s64)
; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[MV]](s128)
%0:_(s64) = COPY $vgpr0_vgpr1
%1:_(s64) = COPY $vgpr0_vgpr1
%2:_(s128) = G_MERGE_VALUES %0, %1
%3:_(s96) = G_TRUNC %2
%4:_(s128) = G_ZEXT %3
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %4
...