[AMDGPU] Fix for vectorizer crash with pointers of different size

When vectorizer strips pointers it can eventually end up with
pointers of two different sizes, then SCEV will crash.

Differential Revision: https://reviews.llvm.org/D65480

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@367443 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp b/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
index 4273080ddd918196d03ec5411efb5422842833e8..f799a45f567246a37416806da6fe5498824fccc9 100644 (file)
--- a/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
+++ b/lib/Transforms/Vectorize/LoadStoreVectorizer.cpp
@@ -339,11 +339,16 @@ bool Vectorizer::areConsecutivePointers(Value *PtrA, Value *PtrB,
                                         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

diff --git a/test/Transforms/LoadStoreVectorizer/AMDGPU/vect-ptr-ptr-size-mismatch.ll b/test/Transforms/LoadStoreVectorizer/AMDGPU/vect-ptr-ptr-size-mismatch.ll
new file mode 100644 (file)
index 0000000..197a439
--- /dev/null
+++ b/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
+}