Index: llvm/lib/Analysis/LoopCacheAnalysis.cpp =================================================================== --- llvm/lib/Analysis/LoopCacheAnalysis.cpp +++ llvm/lib/Analysis/LoopCacheAnalysis.cpp @@ -283,6 +283,9 @@ const SCEV *ElemSize = Sizes.back(); const SCEV *Stride = SE.getMulExpr(Coeff, ElemSize); const SCEV *CacheLineSize = SE.getConstant(Stride->getType(), CLS); + Type *WiderType = SE.getWiderType(Stride->getType(), TripCount->getType()); + Stride = SE.getNoopOrAnyExtend(Stride, WiderType); + TripCount = SE.getNoopOrAnyExtend(TripCount, WiderType); const SCEV *Numerator = SE.getMulExpr(Stride, TripCount); RefCost = SE.getUDivExpr(Numerator, CacheLineSize); LLVM_DEBUG(dbgs().indent(4) Index: llvm/test/Analysis/LoopCacheAnalysis/PowerPC/compute-cost.ll =================================================================== --- /dev/null +++ llvm/test/Analysis/LoopCacheAnalysis/PowerPC/compute-cost.ll @@ -0,0 +1,32 @@ +; RUN: opt < %s -passes='print' -disable-output 2>&1 | FileCheck %s + +target datalayout = "e-m:e-i64:64-n32:64" +target triple = "powerpc64le-unknown-linux-gnu" + +; CHECK: Loop 'for.cond' has cost = 64 + +%struct._Handleitem = type { %struct._Handleitem* } + +define dso_local void @handle_to_ptr(%struct._Handleitem** nocapture %blocks) local_unnamed_addr { +; Preheader: +entry: + br label %for.cond + +; Loop: +for.cond: ; preds = %for.body, %entry + %i.0 = phi i32 [ 1, %entry ], [ %inc, %for.body ] + %cmp = icmp ult i32 %i.0, 1024 + br i1 %cmp, label %for.body, label %for.end + +for.body: ; preds = %for.cond + %idxprom = zext i32 %i.0 to i64 + %arrayidx = getelementptr inbounds %struct._Handleitem*, %struct._Handleitem** %blocks, i64 %idxprom + store %struct._Handleitem* null, %struct._Handleitem** %arrayidx, align 8 + %inc = add nuw nsw i32 %i.0, 1 + br label %for.cond + +; Exit blocks +for.end: ; preds = %for.cond + ret void + +}