6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-14 11:32:34 +00:00
Code Issues Projects Releases Wiki Activity

PR14574. Fix a bug in the code that calculates the mask the converted PHIs in if-conversion.

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@169916 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Nadav Rotem 2012-12-11 21:30:14 +00:00
parent f98f2ce29e
commit 655d2c5354
2 changed files with 45 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -954,7 +954,7 @@ InnerLoopVectorizer::vectorizeBlockInLoop(LoopVectorizationLegality *Legal,
// At this point we generate the predication tree. There may be // At this point we generate the predication tree. There may be
// duplications since this is a simple recursive scan, but future // duplications since this is a simple recursive scan, but future
// optimizations will clean it up. // optimizations will clean it up.
Value *Cond = createBlockInMask(P->getIncomingBlock(0)); Value *Cond = createEdgeMask(P->getIncomingBlock(0), P->getParent());
WidenMap[P] = WidenMap[P] =
Builder.CreateSelect(Cond, Builder.CreateSelect(Cond,
getVectorValue(P->getIncomingValue(0)), getVectorValue(P->getIncomingValue(0)),

44
test/Transforms/LoopVectorize/12-12-11-if-conv.ll Normal file
View File

@ -0,0 +1,44 @@
; RUN: opt < %s -loop-vectorize -force-vector-width=4 -enable-if-conversion -dce -instcombine -licm -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"
;CHECK: @foo
;CHECK: icmp eq <4 x i32>
;CHECK: select <4 x i1>
;CHECK: ret i32
define i32 @foo(i32 %x, i32 %t, i32* nocapture %A) nounwind uwtable ssp {
entry:
%cmp10 = icmp sgt i32 %x, 0
br i1 %cmp10, label %for.body, label %for.end
for.body: ; preds = %entry, %if.end
%indvars.iv = phi i64 [ %indvars.iv.next, %if.end ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32* %A, i64 %indvars.iv
%0 = load i32* %arrayidx, align 4, !tbaa !0
%tobool = icmp eq i32 %0, 0
br i1 %tobool, label %if.end, label %if.then
if.then: ; preds = %for.body
%1 = add nsw i64 %indvars.iv, 45
%2 = trunc i64 %indvars.iv to i32
%mul = mul nsw i32 %2, %t
%3 = trunc i64 %1 to i32
%add1 = add nsw i32 %3, %mul
br label %if.end
if.end: ; preds = %for.body, %if.then
%z.0 = phi i32 [ %add1, %if.then ], [ 9, %for.body ]
store i32 %z.0, i32* %arrayidx, align 4, !tbaa !0
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %x
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %if.end, %entry
ret i32 undef
}
!0 = metadata !{metadata !"int", metadata !1}
!1 = metadata !{metadata !"omnipotent char", metadata !2}
!2 = metadata !{metadata !"Simple C/C++ TBAA"}