diff --git a/llvm/lib/Analysis/Loads.cpp b/llvm/lib/Analysis/Loads.cpp --- a/llvm/lib/Analysis/Loads.cpp +++ b/llvm/lib/Analysis/Loads.cpp @@ -199,7 +199,7 @@ Value *Ptr = LI->getPointerOperand(); APInt EltSize(DL.getIndexTypeSizeInBits(Ptr->getType()), - DL.getTypeStoreSize(LI->getType())); + DL.getTypeStoreSize(LI->getType()).getFixedSize()); const Align Alignment = LI->getAlign(); Instruction *HeaderFirstNonPHI = L->getHeader()->getFirstNonPHI(); diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp --- a/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp +++ b/llvm/lib/Transforms/Vectorize/LoopVectorizationLegality.cpp @@ -1009,8 +1009,15 @@ ScalarEvolution &SE = *PSE.getSE(); for (Instruction &I : *BB) { LoadInst *LI = dyn_cast(&I); - if (LI && !mustSuppressSpeculation(*LI) && - isDereferenceableAndAlignedInLoop(LI, TheLoop, SE, *DT)) + if (!LI) + continue; + // Don't consider vector loads; it does not make sense in the context of + // identifying scalar loads for vectorization. + if (LI->getType()->isVectorTy()) + continue; + if (mustSuppressSpeculation(*LI)) + continue; + if (isDereferenceableAndAlignedInLoop(LI, TheLoop, SE, *DT)) SafePointers.insert(LI->getPointerOperand()); } } diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-scalable-load-in-loop.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-scalable-load-in-loop.ll new file mode 100644 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-scalable-load-in-loop.ll @@ -0,0 +1,41 @@ +; RUN: opt -S -O2 -mtriple=aarch64-linux-gnu -mattr=+sve < %s 2>%t | FileCheck %s +; RUN: FileCheck --check-prefix=WARN --allow-empty %s <%t + +; If this check fails please read test/CodeGen/AArch64/README for instructions on how to resolve it. +; WARN-NOT: warning: {{.*}}TypeSize is not scalable + +; #include +; +; void scalable_load_in_loop(long n, int *a, int *b, svuint32_t *x, +; svuint32_t *y) { +; for (unsigned i = 0; i < n; i++) { +; if (i % 2 == 0) continue; +; a[i] = 2 * b[i]; +; *x = *y; +; } +; } + +; CHECK-LABEL: @scalable_load_in_loop +define void @scalable_load_in_loop(i64 %n, * %x, * %y) { +entry: + br label %for.body + +for.body: + %i = phi i32 [ %inc, %for.inc ], [ 0, %entry ] + %rem = and i32 %i, 1 + %cmp = icmp eq i32 %rem, 0 + br i1 %cmp, label %for.inc, label %if.end + +if.end: + %0 = load , * %y + store %0, * %x + br label %for.inc + +for.inc: + %inc = add i32 %i, 1 + %cmp2 = icmp slt i64 0, %n + br i1 %cmp2, label %for.body, label %for.cleanup + +for.cleanup: + ret void +}