1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-22 12:33:33 +02:00
llvm-mirror/test/Transforms/NewGVN/pr33305.ll
Daniel Berlin f723f3f577 Fix PR/33305. caused by trying to simplify expressions in phi of ops that should have no leaders.
Summary:
After a discussion with Rekka, i believe this (or a small variant)
should fix the remaining phi-of-ops problems.

Rekka's algorithm for completeness relies on looking up expressions
that should have no leader, and expecting it to fail (IE looking up
expressions that can't exist in a predecessor, and expecting it to
find nothing).

Unfortunately, sometimes these expressions can be simplified to
constants, but we need the lookup to fail anyway.  Additionally, our
simplifier outsmarts this by taking these "not quite right"
expressions, and simplifying them into other expressions or walking
through phis, etc.  In the past, we've sometimes been able to find
leaders for these expressions, incorrectly.

This change causes us to not to try to phi of ops such expressions.
We determine safety by seeing if they depend on a phi node in our
block.

This is not perfect, we can do a bit better, but this should be a
"correctness start" that we can then improve.  It also requires a
bunch of caching that i'll eventually like to eliminate.

The right solution, longer term, to the simplifier issues, is to make
the query interface for the instruction simplifier/constant folder
have the flags we need, so that we can keep most things going, but
turn off the possibly-invalid parts (threading through phis, etc).
This is an issue in another wrong code bug as well.

Reviewers: davide, mcrosier

Subscribers: sanjoy, llvm-commits

Differential Revision: https://reviews.llvm.org/D37175

llvm-svn: 312401
2017-09-02 02:18:44 +00:00

186 lines
9.8 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -newgvn -S %s | FileCheck %s
; Ensure we do not incorrect do phi of ops
source_filename = "/Users/dannyb/sources/llvm-clean/debug-build/pr33305.c"
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.12.0"
@a = common global i32 0, align 4
@b = local_unnamed_addr global i32* @a, align 8
@e = local_unnamed_addr global i32 -1, align 4
@g = local_unnamed_addr global i32 1, align 4
@c = common local_unnamed_addr global i32 0, align 4
@f = common local_unnamed_addr global i32 0, align 4
@h = common local_unnamed_addr global i32 0, align 4
@str = private unnamed_addr constant [5 x i8] c"fine\00"
@str.2 = private unnamed_addr constant [8 x i8] c"Screwed\00"
; Function Attrs: nounwind optsize ssp uwtable
define i32 @main() local_unnamed_addr #0 {
; CHECK-LABEL: @main(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[DOTPR_I:%.*]] = load i32, i32* @c, align 4, !tbaa !3
; CHECK-NEXT: [[CMP13_I:%.*]] = icmp slt i32 [[DOTPR_I]], 1
; CHECK-NEXT: br i1 [[CMP13_I]], label [[FOR_COND1_PREHEADER_LR_PH_I:%.*]], label [[ENTRY_FOR_END9_I_CRIT_EDGE:%.*]]
; CHECK: entry.for.end9.i_crit_edge:
; CHECK-NEXT: [[DOTPRE:%.*]] = load i32, i32* @h, align 4, !tbaa !3
; CHECK-NEXT: br label [[FOR_END9_I:%.*]]
; CHECK: for.cond1.preheader.lr.ph.i:
; CHECK-NEXT: [[G_PROMOTED14_I:%.*]] = load i32, i32* @g, align 4, !tbaa !3
; CHECK-NEXT: br label [[FOR_COND1_PREHEADER_I:%.*]]
; CHECK: for.cond1.preheader.i:
; CHECK-NEXT: [[INC816_I:%.*]] = phi i32 [ [[DOTPR_I]], [[FOR_COND1_PREHEADER_LR_PH_I]] ], [ [[INC8_I:%.*]], [[FOR_INC7_I:%.*]] ]
; CHECK-NEXT: [[TMP0:%.*]] = phi i32 [ [[G_PROMOTED14_I]], [[FOR_COND1_PREHEADER_LR_PH_I]] ], [ 0, [[FOR_INC7_I]] ]
; CHECK-NEXT: br label [[FOR_BODY3_I:%.*]]
; CHECK: for.body3.i:
; CHECK-NEXT: [[TMP1:%.*]] = phi i1 [ false, [[FOR_COND1_PREHEADER_I]] ], [ true, [[LOR_END_I:%.*]] ]
; CHECK-NEXT: [[INC12_I:%.*]] = phi i32 [ 0, [[FOR_COND1_PREHEADER_I]] ], [ [[INC_I:%.*]], [[LOR_END_I]] ]
; CHECK-NEXT: [[TMP2:%.*]] = phi i32 [ [[TMP0]], [[FOR_COND1_PREHEADER_I]] ], [ 0, [[LOR_END_I]] ]
; CHECK-NEXT: [[TOBOOL_I:%.*]] = icmp ne i32 [[TMP2]], 0
; CHECK-NEXT: [[OR_COND_I:%.*]] = and i1 [[TMP1]], [[TOBOOL_I]]
; CHECK-NEXT: br i1 [[OR_COND_I]], label [[LOR_END_I]], label [[LOR_RHS_I:%.*]]
; CHECK: lor.rhs.i:
; CHECK-NEXT: [[LNOT_I:%.*]] = xor i1 [[TOBOOL_I]], true
; CHECK-NEXT: [[LNOT_EXT_I:%.*]] = zext i1 [[LNOT_I]] to i32
; CHECK-NEXT: [[TMP3:%.*]] = load i32, i32* @e, align 4, !tbaa !3
; CHECK-NEXT: [[XOR_I:%.*]] = xor i32 [[TMP3]], [[LNOT_EXT_I]]
; CHECK-NEXT: store i32 [[XOR_I]], i32* @e, align 4, !tbaa !3
; CHECK-NEXT: br label [[LOR_END_I]]
; CHECK: lor.end.i:
; CHECK-NEXT: [[INC_I]] = add nuw nsw i32 [[INC12_I]], 1
; CHECK-NEXT: [[EXITCOND_I:%.*]] = icmp eq i32 [[INC_I]], 2
; CHECK-NEXT: br i1 [[EXITCOND_I]], label [[FOR_INC7_I]], label [[FOR_BODY3_I]]
; CHECK: for.inc7.i:
; CHECK-NEXT: [[INC8_I]] = add nsw i32 [[INC816_I]], 1
; CHECK-NEXT: [[CMP_I:%.*]] = icmp slt i32 [[INC816_I]], 0
; CHECK-NEXT: br i1 [[CMP_I]], label [[FOR_COND1_PREHEADER_I]], label [[FOR_COND_FOR_END9_CRIT_EDGE_I:%.*]]
; CHECK: for.cond.for.end9_crit_edge.i:
; CHECK-NEXT: store i32 0, i32* @g, align 4, !tbaa !3
; CHECK-NEXT: store i32 2, i32* @h, align 4, !tbaa !3
; CHECK-NEXT: store i32 [[INC8_I]], i32* @c, align 4, !tbaa !3
; CHECK-NEXT: br label [[FOR_END9_I]]
; CHECK: for.end9.i:
; CHECK-NEXT: [[TMP4:%.*]] = phi i32 [ [[DOTPRE]], [[ENTRY_FOR_END9_I_CRIT_EDGE]] ], [ 2, [[FOR_COND_FOR_END9_CRIT_EDGE_I]] ]
; CHECK-NEXT: [[TMP5:%.*]] = load i32*, i32** @b, align 8, !tbaa !7
; CHECK-NEXT: store i32 [[TMP4]], i32* [[TMP5]], align 4, !tbaa !3
; CHECK-NEXT: [[TMP6:%.*]] = load i32, i32* @e, align 4, !tbaa !3
; CHECK-NEXT: [[CMP10_I:%.*]] = icmp slt i32 [[TMP6]], -1
; CHECK-NEXT: br i1 [[CMP10_I]], label [[IF_THEN_I:%.*]], label [[FN1_EXIT:%.*]]
; CHECK: if.then.i:
; CHECK-NEXT: [[TMP7:%.*]] = load i32, i32* @f, align 4, !tbaa !3
; CHECK-NEXT: store i32 [[TMP7]], i32* [[TMP5]], align 4, !tbaa !3
; CHECK-NEXT: br label [[FN1_EXIT]]
; CHECK: fn1.exit:
; CHECK-NEXT: [[TMP8:%.*]] = load i32, i32* @a, align 4, !tbaa !3
; CHECK-NEXT: [[TOBOOL:%.*]] = icmp eq i32 [[TMP8]], 0
; CHECK-NEXT: br i1 [[TOBOOL]], label [[IF_END:%.*]], label [[IF_THEN:%.*]]
; CHECK: if.then:
; CHECK-NEXT: [[PUTS2:%.*]] = tail call i32 @puts(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @str.2, i64 0, i64 0))
; CHECK-NEXT: tail call void @abort() #4
; CHECK-NEXT: unreachable
; CHECK: if.end:
; CHECK-NEXT: [[PUTS:%.*]] = tail call i32 @puts(i8* getelementptr inbounds ([5 x i8], [5 x i8]* @str, i64 0, i64 0))
; CHECK-NEXT: ret i32 0
;
entry:
%.pr.i = load i32, i32* @c, align 4, !tbaa !3
%cmp13.i = icmp slt i32 %.pr.i, 1
br i1 %cmp13.i, label %for.cond1.preheader.lr.ph.i, label %entry.for.end9.i_crit_edge
entry.for.end9.i_crit_edge: ; preds = %entry
%.pre = load i32, i32* @h, align 4, !tbaa !3
br label %for.end9.i
for.cond1.preheader.lr.ph.i: ; preds = %entry
%g.promoted14.i = load i32, i32* @g, align 4, !tbaa !3
br label %for.cond1.preheader.i
for.cond1.preheader.i: ; preds = %for.inc7.i, %for.cond1.preheader.lr.ph.i
%inc816.i = phi i32 [ %.pr.i, %for.cond1.preheader.lr.ph.i ], [ %inc8.i, %for.inc7.i ]
%0 = phi i32 [ %g.promoted14.i, %for.cond1.preheader.lr.ph.i ], [ 0, %for.inc7.i ]
br label %for.body3.i
for.body3.i: ; preds = %lor.end.i, %for.cond1.preheader.i
%1 = phi i1 [ false, %for.cond1.preheader.i ], [ true, %lor.end.i ]
%inc12.i = phi i32 [ 0, %for.cond1.preheader.i ], [ %inc.i, %lor.end.i ]
%2 = phi i32 [ %0, %for.cond1.preheader.i ], [ 0, %lor.end.i ]
%tobool.i = icmp ne i32 %2, 0
%or.cond.i = and i1 %1, %tobool.i
br i1 %or.cond.i, label %lor.end.i, label %lor.rhs.i
lor.rhs.i: ; preds = %for.body3.i
%lnot.i = xor i1 %tobool.i, true
%lnot.ext.i = zext i1 %lnot.i to i32
%3 = load i32, i32* @e, align 4, !tbaa !3
%xor.i = xor i32 %3, %lnot.ext.i
store i32 %xor.i, i32* @e, align 4, !tbaa !3
br label %lor.end.i
lor.end.i: ; preds = %lor.rhs.i, %for.body3.i
%inc.i = add nuw nsw i32 %inc12.i, 1
%exitcond.i = icmp eq i32 %inc.i, 2
br i1 %exitcond.i, label %for.inc7.i, label %for.body3.i
for.inc7.i: ; preds = %lor.end.i
%inc8.i = add nsw i32 %inc816.i, 1
%cmp.i = icmp slt i32 %inc816.i, 0
br i1 %cmp.i, label %for.cond1.preheader.i, label %for.cond.for.end9_crit_edge.i
for.cond.for.end9_crit_edge.i: ; preds = %for.inc7.i
store i32 0, i32* @g, align 4, !tbaa !3
store i32 2, i32* @h, align 4, !tbaa !3
store i32 %inc8.i, i32* @c, align 4, !tbaa !3
br label %for.end9.i
for.end9.i: ; preds = %entry.for.end9.i_crit_edge, %for.cond.for.end9_crit_edge.i
%4 = phi i32 [ %.pre, %entry.for.end9.i_crit_edge ], [ 2, %for.cond.for.end9_crit_edge.i ]
%5 = load i32*, i32** @b, align 8, !tbaa !7
store i32 %4, i32* %5, align 4, !tbaa !3
%6 = load i32, i32* @e, align 4, !tbaa !3
%cmp10.i = icmp slt i32 %6, -1
br i1 %cmp10.i, label %if.then.i, label %fn1.exit
if.then.i: ; preds = %for.end9.i
%7 = load i32, i32* @f, align 4, !tbaa !3
store i32 %7, i32* %5, align 4, !tbaa !3
br label %fn1.exit
fn1.exit: ; preds = %if.then.i, %for.end9.i
%8 = load i32, i32* @a, align 4, !tbaa !3
%tobool = icmp eq i32 %8, 0
br i1 %tobool, label %if.end, label %if.then
if.then: ; preds = %fn1.exit
%puts2 = tail call i32 @puts(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @str.2, i64 0, i64 0))
tail call void @abort() #3
unreachable
if.end: ; preds = %fn1.exit
%puts = tail call i32 @puts(i8* getelementptr inbounds ([5 x i8], [5 x i8]* @str, i64 0, i64 0))
ret i32 0
}
; Function Attrs: noreturn nounwind optsize
declare void @abort() local_unnamed_addr #1
; Function Attrs: nounwind
declare i32 @puts(i8* nocapture readonly) local_unnamed_addr #2
attributes #0 = { nounwind optsize ssp uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="penryn" "target-features"="+cx16,+fxsr,+mmx,+sse,+sse2,+sse3,+sse4.1,+ssse3,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { noreturn nounwind optsize "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="penryn" "target-features"="+cx16,+fxsr,+mmx,+sse,+sse2,+sse3,+sse4.1,+ssse3,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #2 = { nounwind }
attributes #3 = { noreturn nounwind optsize }
!llvm.module.flags = !{!0, !1}
!llvm.ident = !{!2}
!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{i32 7, !"PIC Level", i32 2}
!2 = !{!"clang version 5.0.0 (http://llvm.org/git/clang.git e97b4dda83fd49e0218ea06ba4e37796a81b2027) (/Users/dannyb/sources/llvm-clean b38f051979e4ac2aa6513e40046d120fd472cb96)"}
!3 = !{!4, !4, i64 0}
!4 = !{!"int", !5, i64 0}
!5 = !{!"omnipotent char", !6, i64 0}
!6 = !{!"Simple C/C++ TBAA"}
!7 = !{!8, !8, i64 0}
!8 = !{!"any pointer", !5, i64 0}