1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 19:23:23 +01:00

[LLE] Add missed LoopSimplify dependence

The code assumed that we always had a preheader without making the pass
dependent on LoopSimplify.

Thanks to Mattias Eriksson V for reporting this.

llvm-svn: 263173
This commit is contained in:
Adam Nemet 2016-03-10 23:54:39 +00:00
parent 594e5f0364
commit 492139ffb6
2 changed files with 36 additions and 0 deletions

View File

@ -28,6 +28,7 @@
#include "llvm/IR/Module.h"
#include "llvm/Pass.h"
#include "llvm/Support/Debug.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils/LoopVersioning.h"
#include <forward_list>
@ -557,6 +558,7 @@ public:
}
void getAnalysisUsage(AnalysisUsage &AU) const override {
AU.addRequiredID(LoopSimplifyID);
AU.addRequired<LoopInfoWrapperPass>();
AU.addPreserved<LoopInfoWrapperPass>();
AU.addRequired<LoopAccessAnalysis>();
@ -577,6 +579,7 @@ INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopAccessAnalysis)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(ScalarEvolutionWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopSimplify)
INITIALIZE_PASS_END(LoopLoadElimination, LLE_OPTION, LLE_name, false, false)
namespace llvm {

View File

@ -0,0 +1,33 @@
; RUN: opt -loop-load-elim -S < %s | FileCheck %s
; Make sure we create a preheader if we dont' have one.
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
define void @f(i32* noalias nocapture %A, i32* noalias nocapture readonly %B, i64 %N, i1 %C) {
entry:
br i1 %C, label %for.body, label %for.end
; CHECK: for.body.preheader:
; CHECK-NEXT: %load_initial = load i32, i32* %A
; CHECK-NEXT: br label %for.body
; CHECK: for.body:
for.body:
; CHECK-NEXT: %store_forwarded = phi i32 [ %load_initial, %for.body.preheader ], [ %add, %for.body ]
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds i32, i32* %A, i64 %indvars.iv
%load = load i32, i32* %arrayidx, align 4
%arrayidx2 = getelementptr inbounds i32, i32* %B, i64 %indvars.iv
%load_1 = load i32, i32* %arrayidx2, align 4
; CHECK: %add = add i32 %load_1, %store_forwarded
%add = add i32 %load_1, %load
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%arrayidx_next = getelementptr inbounds i32, i32* %A, i64 %indvars.iv.next
store i32 %add, i32* %arrayidx_next, align 4
%exitcond = icmp eq i64 %indvars.iv.next, %N
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}