Index: lib/Transforms/Vectorize/LoadStoreVectorizer.cpp =================================================================== --- lib/Transforms/Vectorize/LoadStoreVectorizer.cpp +++ lib/Transforms/Vectorize/LoadStoreVectorizer.cpp @@ -283,8 +283,14 @@ // Look through GEPs after checking they're the same except for the last // index. - GetElementPtrInst *GEPA = dyn_cast(getPointerOperand(A)); - GetElementPtrInst *GEPB = dyn_cast(getPointerOperand(B)); + Value *SrcPTRA = getPointerOperand(A); + Value *SrcPTRB = getPointerOperand(B); + while (auto *C = dyn_cast(SrcPTRA)) + SrcPTRA = C->getOperand(0); + while (auto *C = dyn_cast(SrcPTRB)) + SrcPTRB = C->getOperand(0); + GetElementPtrInst *GEPA = dyn_cast(SrcPTRA); + GetElementPtrInst *GEPB = dyn_cast(SrcPTRB); if (!GEPA || !GEPB || GEPA->getNumOperands() != GEPB->getNumOperands()) return false; unsigned FinalIndex = GEPA->getNumOperands() - 1; Index: test/Transforms/LoadStoreVectorizer/AMDGPU/gep-bitcast.ll =================================================================== --- /dev/null +++ test/Transforms/LoadStoreVectorizer/AMDGPU/gep-bitcast.ll @@ -0,0 +1,27 @@ +; RUN: opt -S -mtriple=amdgcn--amdhsa -load-store-vectorizer < %s | FileCheck %s + +; Check that vectorizer can find a GEP through bitcast +; CHECK: load <4 x i32> +define void @vect_zext_bitcast_idx(float addrspace(1)* %arg1, i32 %base) { + %add1 = add nuw i32 %base, 0 + %zext1 = zext i32 %add1 to i64 + %gep1 = getelementptr inbounds float, float addrspace(1)* %arg1, i64 %zext1 + %f2i1 = bitcast float addrspace(1)* %gep1 to i32 addrspace(1)* + %load1 = load i32, i32 addrspace(1)* %f2i1, align 4 + %add2 = add nuw i32 %base, 1 + %zext2 = zext i32 %add2 to i64 + %gep2 = getelementptr inbounds float, float addrspace(1)* %arg1, i64 %zext2 + %f2i2 = bitcast float addrspace(1)* %gep2 to i32 addrspace(1)* + %load2 = load i32, i32 addrspace(1)* %f2i2, align 4 + %add3 = add nuw i32 %base, 2 + %zext3 = zext i32 %add3 to i64 + %gep3 = getelementptr inbounds float, float addrspace(1)* %arg1, i64 %zext3 + %f2i3 = bitcast float addrspace(1)* %gep3 to i32 addrspace(1)* + %load3 = load i32, i32 addrspace(1)* %f2i3, align 4 + %add4 = add nuw i32 %base, 3 + %zext4 = zext i32 %add4 to i64 + %gep4 = getelementptr inbounds float, float addrspace(1)* %arg1, i64 %zext4 + %f2i4 = bitcast float addrspace(1)* %gep4 to i32 addrspace(1)* + %load4 = load i32, i32 addrspace(1)* %f2i4, align 4 + ret void +}