maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

LoopIdiom: Fix a serious missed optimization: we only turned top-level loops into memmove. 

Thanks to Preston Briggs for catching this!

llvm-svn: 167045
This commit is contained in:
Benjamin Kramer 2012-10-30 19:49:39 +00:00
parent 2eaadd1a2d
commit 48a6478242
2 changed files with 47 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
View File

@ -555,10 +555,11 @@ processLoopStoreOfLoopLoad(StoreInst *SI, unsigned StoreSize,
// can safely emit a memcpy.
OwningPtr<Dependence> Dep(DA.depends(SI, LI, true));
if (Dep) {
// If there is a dependence but the direction is positive we can still
// safely turn this into memmove.
if (Dep->getLevels() != 1 ||
Dep->getDirection(1) != Dependence::DVEntry::GT)
// If there is a dependence but the direction is positive (or none) we can
// still safely turn this into memmove.
unsigned Direction = Dep->getDirection(Dep->getLevels());
if (Direction != Dependence::DVEntry::NONE &&
Direction != Dependence::DVEntry::GT)
return false;
isMemcpySafe = false;
}

42
llvm/test/Transforms/LoopIdiom/memmove.ll Normal file
View File

@ -0,0 +1,42 @@
; RUN: opt -S -basicaa -loop-idiom < %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"
target triple = "x86_64-apple-macosx10.8.0"
declare i64 @foo() nounwind
; Nested loops
define void @test1(i8* nocapture %A, i64 %n) nounwind {
entry:
%call8 = tail call i64 @foo() nounwind
%tobool9 = icmp eq i64 %call8, 0
br i1 %tobool9, label %while.end, label %for.cond.preheader.lr.ph
for.cond.preheader.lr.ph: ; preds = %entry
%cmp6 = icmp eq i64 %n, 0
br label %for.cond.preheader
while.cond.loopexit: ; preds = %for.body, %for.cond.preheader
%call = tail call i64 @foo() nounwind
%tobool = icmp eq i64 %call, 0
br i1 %tobool, label %while.end, label %for.cond.preheader
for.cond.preheader: ; preds = %for.cond.preheader.lr.ph, %while.cond.loopexit
br i1 %cmp6, label %while.cond.loopexit, label %for.body
for.body: ; preds = %for.cond.preheader, %for.body
%i.07 = phi i64 [ %inc, %for.body ], [ 0, %for.cond.preheader ]
%add = add i64 %i.07, 10
%arrayidx = getelementptr inbounds i8* %A, i64 %add
%0 = load i8* %arrayidx, align 1
%arrayidx1 = getelementptr inbounds i8* %A, i64 %i.07
store i8 %0, i8* %arrayidx1, align 1
%inc = add i64 %i.07, 1
%exitcond = icmp eq i64 %inc, %n
br i1 %exitcond, label %while.cond.loopexit, label %for.body
while.end: ; preds = %while.cond.loopexit, %entry
ret void
; CHECK: @test1
; CHECK: call void @llvm.memmove.p0i8.p0i8.i64(
}