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

When emitting an instruction which depends on both a post-incremented 

induction variable value and a loop-variant value, don't force the
insert position to be at the post-increment position, because it may
not be dominated by the loop-variant value. This fixes a
use-before-def problem noticed on PPC.

llvm-svn: 96774
This commit is contained in:
Dan Gohman 2010-02-22 03:59:54 +00:00
parent 8064a5ba88
commit 4506fcb3c2
2 changed files with 36 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
View File

@ -2866,8 +2866,10 @@ Value *LSRInstance::Expand(const LSRFixup &LF,
if (AR->getLoop() == LF.PostIncLoop) {
Reg = SE.getAddExpr(Reg, AR->getStepRecurrence(SE));
// If the user is inside the loop, insert the code after the increment
// so that it is dominated by its operand.
if (L->contains(LF.UserInst))
// so that it is dominated by its operand. If the original insert point
// was already dominated by the increment, keep it, because there may
// be loop-variant operands that need to be respected also.
if (L->contains(LF.UserInst) && !DT.dominates(IVIncInsertPos, IP))
IP = IVIncInsertPos;
break;
}

32
llvm/test/CodeGen/PowerPC/lsr-postinc-pos.ll Normal file
View File

@ -0,0 +1,32 @@
; RUN: llc < %s -print-lsr-output |& FileCheck %s
; The icmp is a post-inc use, and the increment is in %bb11, but the
; scevgep needs to be inserted in %bb so that it is dominated by %t.
; CHECK: %t = load i8** undef
; CHECK: %scevgep = getelementptr i8* %t, i32 %lsr.iv.next
; CHECK: %c1 = icmp ult i8* %scevgep, undef
target datalayout = "E-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f128:64:128-n32"
target triple = "powerpc-apple-darwin9"
define void @foo() nounwind {
entry:
br label %bb11
bb11:
%i = phi i32 [ 0, %entry ], [ %i.next, %bb ] ; <i32> [#uses=3]
%ii = shl i32 %i, 2 ; <i32> [#uses=1]
%c0 = icmp eq i32 %i, undef ; <i1> [#uses=1]
br i1 %c0, label %bb13, label %bb
bb:
%t = load i8** undef, align 16 ; <i8*> [#uses=1]
%p = getelementptr i8* %t, i32 %ii ; <i8*> [#uses=1]
%c1 = icmp ult i8* %p, undef ; <i1> [#uses=1]
%i.next = add i32 %i, 1 ; <i32> [#uses=1]
br i1 %c1, label %bb11, label %bb13
bb13:
unreachable
}