maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/LoopRotate/simplifylatch.ll

77 lines
2.1 KiB
LLVM
Raw Normal View History

Rotate multi-exit loops even if the latch was simplified. Test case by Michele Scandale! Fixes PR10293: Load not hoisted out of loop with multiple exits. There are few regressions with this patch, now tracked by rdar:13817079, and a roughly equal number of improvements. The regressions are almost certainly back luck because LoopRotate has very little idea of whether rotation is profitable. Doing better requires a more comprehensive solution. This checkin is a quick fix that lacks generality (PR10293 has a counter-example). But it trivially fixes the case in PR10293 without interfering with other cases, and it does satify the criteria that LoopRotate is a loop canonicalization pass that should avoid heuristics and special cases. I can think of two approaches that would probably be better in the long run. Ultimately they may both make sense. (1) LoopRotate should check that the current header would make a good loop guard, and that the loop does not already has a sufficient guard. The artifical SimplifiedLoopLatch check would be unnecessary, and the design would be more general and canonical. Two difficulties: - We need a strong guarantee that we won't endlessly rotate, so the analysis would need to be precise in order to avoid the SimplifiedLoopLatch precondition. - Analysis like this are usually based on SCEV, which we don't want to rely on. (2) Rotate on-demand in late loop passes. This could even be done by shoving the loop back on the queue after the optimization that needs it. This could work well when we find LICM opportunities in multi-branch loops. This requires some work, and it doesn't really solve the problem of SCEV wanting a loop guard before the analysis. llvm-svn: 181230
2013-05-07 01:58:18 +08:00
; RUN: opt -S < %s -loop-rotate -licm -verify-dom-info -verify-loop-info | FileCheck %s
Add simplifyLoopLatch to LoopRotate pass. This folds a simple loop tail into a loop latch. It covers the common (in fortran) case of postincrement loops. It's a "free" way to expose this type of loop to downstream loop optimizations that bail out on non-canonical loops (getLoopLatch is a heavily used check). llvm-svn: 150439
2012-02-14 08:00:23 +08:00
; PR2624 unroll multiple exits
@mode_table = global [4 x i32] zeroinitializer ; <[4 x i32]*> [#uses=1]
Update Transforms tests to use CHECK-LABEL for easier debugging. No functionality change. This update was done with the following bash script: find test/Transforms -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_]*\):\( *\)@$FUNC\([( ]*\)\$/;\1\2-LABEL:\3@$FUNC(/g" $TEMP done mv $TEMP $NAME fi done llvm-svn: 186268
2013-07-14 09:42:54 +08:00
; CHECK-LABEL: @f(
Add simplifyLoopLatch to LoopRotate pass. This folds a simple loop tail into a loop latch. It covers the common (in fortran) case of postincrement loops. It's a "free" way to expose this type of loop to downstream loop optimizations that bail out on non-canonical loops (getLoopLatch is a heavily used check). llvm-svn: 150439
2012-02-14 08:00:23 +08:00
; CHECK-NOT: bb4
define i8 @f() {
entry:
tail call i32 @fegetround( ) ; <i32>:0 [#uses=1]
br label %bb
bb: ; preds = %bb4, %entry
%mode.0 = phi i8 [ 0, %entry ], [ %indvar.next, %bb4 ] ; <i8> [#uses=4]
zext i8 %mode.0 to i32 ; <i32>:1 [#uses=1]
getelementptr [4 x i32]* @mode_table, i32 0, i32 %1 ; <i32*>:2 [#uses=1]
load i32* %2, align 4 ; <i32>:3 [#uses=1]
icmp eq i32 %3, %0 ; <i1>:4 [#uses=1]
br i1 %4, label %bb1, label %bb2
bb1: ; preds = %bb
ret i8 %mode.0
bb2: ; preds = %bb
icmp eq i8 %mode.0, 1 ; <i1>:5 [#uses=1]
br i1 %5, label %bb5, label %bb4
bb4: ; preds = %bb2
%indvar.next = add i8 %mode.0, 1 ; <i8> [#uses=1]
br label %bb
bb5: ; preds = %bb2
tail call void @raise_exception( ) noreturn
unreachable
}
declare i32 @fegetround()
declare void @raise_exception() noreturn
Rotate multi-exit loops even if the latch was simplified. Test case by Michele Scandale! Fixes PR10293: Load not hoisted out of loop with multiple exits. There are few regressions with this patch, now tracked by rdar:13817079, and a roughly equal number of improvements. The regressions are almost certainly back luck because LoopRotate has very little idea of whether rotation is profitable. Doing better requires a more comprehensive solution. This checkin is a quick fix that lacks generality (PR10293 has a counter-example). But it trivially fixes the case in PR10293 without interfering with other cases, and it does satify the criteria that LoopRotate is a loop canonicalization pass that should avoid heuristics and special cases. I can think of two approaches that would probably be better in the long run. Ultimately they may both make sense. (1) LoopRotate should check that the current header would make a good loop guard, and that the loop does not already has a sufficient guard. The artifical SimplifiedLoopLatch check would be unnecessary, and the design would be more general and canonical. Two difficulties: - We need a strong guarantee that we won't endlessly rotate, so the analysis would need to be precise in order to avoid the SimplifiedLoopLatch precondition. - Analysis like this are usually based on SCEV, which we don't want to rely on. (2) Rotate on-demand in late loop passes. This could even be done by shoving the loop back on the queue after the optimization that needs it. This could work well when we find LICM opportunities in multi-branch loops. This requires some work, and it doesn't really solve the problem of SCEV wanting a loop guard before the analysis. llvm-svn: 181230
2013-05-07 01:58:18 +08:00
;CHECK: for.body.lr.ph:
;CHECK-NEXT: %arrayidx1 = getelementptr inbounds i8* %CurPtr, i64 0
;CHECK-NEXT: %0 = load i8* %arrayidx1, align 1
;CHECK-NEXT: %conv2 = sext i8 %0 to i32
;CHECK-NEXT: br label %for.body
define i32 @foo(i8* %CurPtr, i32 %a) #0 {
entry:
br label %for.cond
for.cond: ; preds = %for.inc, %entry
%i.0 = phi i32 [ 1, %entry ], [ %inc, %for.inc ]
%cmp = icmp ne i32 %i.0, %a
br i1 %cmp, label %for.body, label %return
for.body: ; preds = %for.cond
%idxprom = zext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i8* %CurPtr, i64 %idxprom
%0 = load i8* %arrayidx, align 1
%conv = sext i8 %0 to i32
%arrayidx1 = getelementptr inbounds i8* %CurPtr, i64 0
%1 = load i8* %arrayidx1, align 1
%conv2 = sext i8 %1 to i32
%cmp3 = icmp ne i32 %conv, %conv2
br i1 %cmp3, label %return, label %for.inc
for.inc: ; preds = %for.body
%inc = add i32 %i.0, 1
br label %for.cond
return: ; preds = %for.cond, %for.body
%retval.0 = phi i32 [ 0, %for.body ], [ 1, %for.cond ]
ret i32 %retval.0
}
attributes #0 = { nounwind uwtable }