diff options
| -rw-r--r-- | llvm/lib/Analysis/LoopCacheAnalysis.cpp | 3 | ||||
| -rw-r--r-- | llvm/test/Analysis/LoopCacheAnalysis/PowerPC/compute-cost.ll | 35 |
2 files changed, 38 insertions, 0 deletions
diff --git a/llvm/lib/Analysis/LoopCacheAnalysis.cpp b/llvm/lib/Analysis/LoopCacheAnalysis.cpp index 098bc6f6818..25325ec1be0 100644 --- a/llvm/lib/Analysis/LoopCacheAnalysis.cpp +++ b/llvm/lib/Analysis/LoopCacheAnalysis.cpp @@ -284,6 +284,9 @@ CacheCostTy IndexedReference::computeRefCost(const Loop &L, 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.getNoopOrSignExtend(Stride, WiderType); + TripCount = SE.getNoopOrAnyExtend(TripCount, WiderType); const SCEV *Numerator = SE.getMulExpr(Stride, TripCount); RefCost = SE.getUDivExpr(Numerator, CacheLineSize); LLVM_DEBUG(dbgs().indent(4) diff --git a/llvm/test/Analysis/LoopCacheAnalysis/PowerPC/compute-cost.ll b/llvm/test/Analysis/LoopCacheAnalysis/PowerPC/compute-cost.ll new file mode 100644 index 00000000000..8afde3697a4 --- /dev/null +++ b/llvm/test/Analysis/LoopCacheAnalysis/PowerPC/compute-cost.ll @@ -0,0 +1,35 @@ +; RUN: opt < %s -passes='print<loop-cache-cost>' -disable-output 2>&1 | FileCheck %s + +target datalayout = "e-m:e-i64:64-n32:64" +target triple = "powerpc64le-unknown-linux-gnu" + +; Check IndexedReference::computeRefCost can handle type differences between +; Stride and TripCount + +; CHECK: Loop 'for.cond' has cost = 64 + +%struct._Handleitem = type { %struct._Handleitem* } + +define void @handle_to_ptr(%struct._Handleitem** %blocks) { +; 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 + +} |
