Index: llvm/trunk/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp =================================================================== --- llvm/trunk/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp +++ llvm/trunk/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp @@ -339,11 +339,16 @@ const APInt &PtrDelta, unsigned Depth) const { unsigned PtrBitWidth = DL.getPointerTypeSizeInBits(PtrA->getType()); + unsigned PtrAS = PtrA->getType()->getPointerAddressSpace(); APInt OffsetA(PtrBitWidth, 0); APInt OffsetB(PtrBitWidth, 0); PtrA = PtrA->stripAndAccumulateInBoundsConstantOffsets(DL, OffsetA); PtrB = PtrB->stripAndAccumulateInBoundsConstantOffsets(DL, OffsetB); + if (PtrA->getType()->getPointerAddressSpace() != PtrAS || + PtrB->getType()->getPointerAddressSpace() != PtrAS) + return false; + APInt OffsetDelta = OffsetB - OffsetA; // Check if they are based on the same pointer. That makes the offsets Index: llvm/trunk/test/Transforms/LoadStoreVectorizer/AMDGPU/vect-ptr-ptr-size-mismatch.ll =================================================================== --- llvm/trunk/test/Transforms/LoadStoreVectorizer/AMDGPU/vect-ptr-ptr-size-mismatch.ll +++ llvm/trunk/test/Transforms/LoadStoreVectorizer/AMDGPU/vect-ptr-ptr-size-mismatch.ll @@ -0,0 +1,18 @@ +; RUN: opt -mtriple=amdgcn-amd-amdhsa -load-store-vectorizer -S < %s | FileCheck %s + +target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32" + +; CHECK-LABEL: @test +; CHECK: store i32* undef, i32** %tmp9, align 8 +; CHECK: store i32* undef, i32** %tmp7, align 8 +define amdgpu_kernel void @test() { +entry: + %a10.ascast.i = addrspacecast i32* addrspace(5)* null to i32** + %tmp4 = icmp eq i32 undef, 0 + %tmp6 = select i1 false, i32** undef, i32** undef + %tmp7 = select i1 %tmp4, i32** null, i32** %tmp6 + %tmp9 = select i1 %tmp4, i32** %a10.ascast.i, i32** null + store i32* undef, i32** %tmp9, align 8 + store i32* undef, i32** %tmp7, align 8 + unreachable +}