From 3b805b8ffe39936830fd44f5eb2b2ce3679d3b76 Mon Sep 17 00:00:00 2001 From: Craig Topper Date: Thu, 26 Sep 2019 17:20:50 +0000 Subject: [PATCH] [InstCombine] Use m_Zero instead of isNullValue() when checking if a GEP index is all zeroes to prevent an infinite loop. The test case here previously infinite looped. Only one element from the GEP is used so SimplifyDemandedVectorElts would replace the other lanes in each index with undef leading to the first index being <0, undef, undef, undef>. But there's a GEP transform that tries to replace an index into a 0 sized type with a zero index. But the zero index check only works on ConstantInt 0 or ConstantAggregateZero so it would turn the index back to zeroinitializer. Resulting in a loop. The fix is to use m_Zero() to allow a vector of zeroes and undefs. Differential Revision: https://reviews.llvm.org/D67977 git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@373000 91177308-0d34-0410-b5e6-96231b3b80d8 --- .../InstCombine/InstructionCombining.cpp | 2 +- .../Transforms/InstCombine/vec_demanded_elts.ll | 17 +++++++++++++++++ 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/lib/Transforms/InstCombine/InstructionCombining.cpp b/lib/Transforms/InstCombine/InstructionCombining.cpp index 75774980996..ecb486c544e 100644 --- a/lib/Transforms/InstCombine/InstructionCombining.cpp +++ b/lib/Transforms/InstCombine/InstructionCombining.cpp @@ -1667,7 +1667,7 @@ Instruction *InstCombiner::visitGetElementPtrInst(GetElementPtrInst &GEP) { // to an index of zero, so replace it with zero if it is not zero already. Type *EltTy = GTI.getIndexedType(); if (EltTy->isSized() && DL.getTypeAllocSize(EltTy) == 0) - if (!isa(*I) || !cast(*I)->isNullValue()) { + if (!isa(*I) || !match(I->get(), m_Zero())) { *I = Constant::getNullValue(NewIndexType); MadeChange = true; } diff --git a/test/Transforms/InstCombine/vec_demanded_elts.ll b/test/Transforms/InstCombine/vec_demanded_elts.ll index 3f172be3d83..164061de511 100644 --- a/test/Transforms/InstCombine/vec_demanded_elts.ll +++ b/test/Transforms/InstCombine/vec_demanded_elts.ll @@ -651,3 +651,20 @@ define i32* @PR41624(<2 x { i32, i32 }*> %a) { %r = extractelement <2 x i32*> %w, i32 0 ret i32* %r } + +@global = external global [0 x i32], align 4 + +; Make sure we don't get stuck in a loop turning the zeroinitializer into +; <0, undef, undef, undef> and then changing it back. +define i32* @zero_sized_type_extract(<4 x i64> %arg, i64 %arg1) { +; CHECK-LABEL: @zero_sized_type_extract( +; CHECK-NEXT: bb: +; CHECK-NEXT: [[TMP:%.*]] = getelementptr inbounds [0 x i32], <4 x [0 x i32]*> <[0 x i32]* @global, [0 x i32]* undef, [0 x i32]* undef, [0 x i32]* undef>, <4 x i64> , <4 x i64> [[ARG:%.*]] +; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i32*> [[TMP]], i64 0 +; CHECK-NEXT: ret i32* [[TMP2]] +; +bb: + %tmp = getelementptr inbounds [0 x i32], <4 x [0 x i32]*> <[0 x i32]* @global, [0 x i32]* @global, [0 x i32]* @global, [0 x i32]* @global>, <4 x i64> zeroinitializer, <4 x i64> %arg + %tmp2 = extractelement <4 x i32*> %tmp, i64 0 + ret i32* %tmp2 +} -- 2.50.1