Index: lib/Transforms/Scalar/Scalarizer.cpp =================================================================== --- lib/Transforms/Scalar/Scalarizer.cpp +++ lib/Transforms/Scalar/Scalarizer.cpp @@ -247,6 +247,7 @@ } bool Scalarizer::runOnFunction(Function &F) { + assert(Gathered.empty() && Scattered.empty()); for (Function::iterator BBI = F.begin(), BBE = F.end(); BBI != BBE; ++BBI) { BasicBlock *BB = BBI; for (BasicBlock::iterator II = BB->begin(), IE = BB->end(); II != IE;) { @@ -636,7 +637,9 @@ // Delete the instructions that we scalarized. If a full vector result // is still needed, recreate it using InsertElements. bool Scalarizer::finish() { - if (Gathered.empty()) + // The presence of data in Gathered or Scattered indicates changes + // made to the Function. + if (Gathered.empty() && Scattered.empty()) return false; for (GatherList::iterator GMI = Gathered.begin(), GME = Gathered.end(); GMI != GME; ++GMI) { Index: test/Transforms/Scalarizer/store-bug.ll =================================================================== --- /dev/null +++ test/Transforms/Scalarizer/store-bug.ll @@ -0,0 +1,25 @@ +; RUN: opt -scalarizer -scalarize-load-store -S < %s | FileCheck %s +target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128" + +; This input caused the scalarizer not to clear cached results +; properly. +; +; Any regressions should trigger an assert in the scalarizer. + +define void @func(<4 x float> %val, <4 x float> *%ptr) { + store <4 x float> %val, <4 x float> *%ptr + ret void +; CHECK: store float %val.i0, float* %ptr.i0, align 16 +; CHECK: store float %val.i1, float* %ptr.i1, align 4 +; CHECK: store float %val.i2, float* %ptr.i2, align 8 +; CHECK: store float %val.i3, float* %ptr.i3, align 4 +} + +define void @func.copy(<4 x float> %val, <4 x float> *%ptr) { + store <4 x float> %val, <4 x float> *%ptr + ret void +; CHECK: store float %val.i0, float* %ptr.i0, align 16 +; CHECK: store float %val.i1, float* %ptr.i1, align 4 +; CHECK: store float %val.i2, float* %ptr.i2, align 8 +; CHECK: store float %val.i3, float* %ptr.i3, align 4 +}