llvm-project/llvm/test/Transforms/NewGVN/pr33185.ll

120 lines
5.3 KiB
LLVM
Raw Normal View History

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -newgvn -S %s | FileCheck %s
@a = local_unnamed_addr global i32 9, align 4
@.str4 = private unnamed_addr constant [6 x i8] c"D:%d\0A\00", align 1
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 10:18:44 +08:00
define i32 @test1() local_unnamed_addr {
; CHECK-LABEL: @test1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP:%.*]] = load i32, i32* @a, align 4
; CHECK-NEXT: [[CMP1_I:%.*]] = icmp ne i32 [[TMP]], 0
; CHECK-NEXT: br label [[FOR_BODY_I:%.*]]
; CHECK: for.body.i:
; CHECK-NEXT: [[TMP1:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ false, [[COND_END_I:%.*]] ]
; CHECK-NEXT: [[F_08_I:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[INC_I:%.*]], [[COND_END_I]] ]
; CHECK-NEXT: [[MUL_I:%.*]] = select i1 [[CMP1_I]], i32 [[F_08_I]], i32 0
; CHECK-NEXT: br i1 [[TMP1]], label [[COND_END_I]], label [[COND_TRUE_I:%.*]]
; CHECK: cond.true.i:
; CHECK-NEXT: [[DIV_I:%.*]] = udiv i32 [[MUL_I]], [[F_08_I]]
; CHECK-NEXT: br label [[COND_END_I]]
; CHECK: cond.end.i:
; CHECK-NEXT: [[COND_I:%.*]] = phi i32 [ [[DIV_I]], [[COND_TRUE_I]] ], [ 0, [[FOR_BODY_I]] ]
; CHECK-NEXT: [[INC_I]] = add nuw nsw i32 [[F_08_I]], 1
; CHECK-NEXT: [[EXITCOND_I:%.*]] = icmp eq i32 [[INC_I]], 4
; CHECK-NEXT: br i1 [[EXITCOND_I]], label [[FN1_EXIT:%.*]], label [[FOR_BODY_I]]
; CHECK: fn1.exit:
; CHECK-NEXT: [[CALL4:%.*]] = tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str4, i64 0, i64 0), i32 [[COND_I]])
; CHECK-NEXT: ret i32 0
;
entry:
%tmp = load i32, i32* @a, align 4
%cmp1.i = icmp ne i32 %tmp, 0
br label %for.body.i
for.body.i:
%tmp1 = phi i1 [ true, %entry ], [ false, %cond.end.i ]
%f.08.i = phi i32 [ 0, %entry ], [ %inc.i, %cond.end.i ]
%mul.i = select i1 %cmp1.i, i32 %f.08.i, i32 0
br i1 %tmp1, label %cond.end.i, label %cond.true.i
cond.true.i:
;; Ensure we don't replace this divide with a phi of ops that merges the wrong loop iteration value
%div.i = udiv i32 %mul.i, %f.08.i
br label %cond.end.i
cond.end.i:
%cond.i = phi i32 [ %div.i, %cond.true.i ], [ 0, %for.body.i ]
%inc.i = add nuw nsw i32 %f.08.i, 1
%exitcond.i = icmp eq i32 %inc.i, 4
br i1 %exitcond.i, label %fn1.exit, label %for.body.i
fn1.exit:
%cond.i.lcssa = phi i32 [ %cond.i, %cond.end.i ]
%call4= tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str4, i64 0, i64 0), i32 %cond.i.lcssa)
ret i32 0
}
declare i32 @printf(i8* nocapture readonly, ...)
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 10:18:44 +08:00
;; Variant of the above where we have made the udiv available in each predecessor with the wrong values.
;; In the entry block, it is always 0, so we don't try to create a leader there, only in %cond.end.i.
;; We should not create a phi of ops for it using these leaders.
;; A correct phi of ops for this udiv would be phi(0, 1), which we are not smart enough to figure out.
;; If we reuse the incorrect leaders, we will get phi(0, 0).
define i32 @test2() local_unnamed_addr {
; CHECK-LABEL: @test2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP:%.*]] = load i32, i32* @a, align 4
; CHECK-NEXT: [[CMP1_I:%.*]] = icmp ne i32 [[TMP]], 0
; CHECK-NEXT: br label [[FOR_BODY_I:%.*]]
; CHECK: for.body.i:
; CHECK-NEXT: [[TMP1:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ false, [[COND_END_I:%.*]] ]
; CHECK-NEXT: [[F_08_I:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[INC_I:%.*]], [[COND_END_I]] ]
; CHECK-NEXT: [[MUL_I:%.*]] = select i1 [[CMP1_I]], i32 [[F_08_I]], i32 0
; CHECK-NEXT: br i1 [[TMP1]], label [[COND_END_I]], label [[COND_TRUE_I:%.*]]
; CHECK: cond.true.i:
; CHECK-NEXT: [[DIV_I:%.*]] = udiv i32 [[MUL_I]], [[F_08_I]]
; CHECK-NEXT: br label [[COND_END_I]]
; CHECK: cond.end.i:
; CHECK-NEXT: [[COND_I:%.*]] = phi i32 [ [[DIV_I]], [[COND_TRUE_I]] ], [ 0, [[FOR_BODY_I]] ]
; CHECK-NEXT: [[INC_I]] = add nuw nsw i32 [[F_08_I]], 1
; CHECK-NEXT: [[CALL5:%.*]] = tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str4, i64 0, i64 0), i32 0)
; CHECK-NEXT: [[EXITCOND_I:%.*]] = icmp eq i32 [[INC_I]], 4
; CHECK-NEXT: br i1 [[EXITCOND_I]], label [[FN1_EXIT:%.*]], label [[FOR_BODY_I]]
; CHECK: fn1.exit:
; CHECK-NEXT: [[CALL4:%.*]] = tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str4, i64 0, i64 0), i32 [[COND_I]])
; CHECK-NEXT: ret i32 0
;
entry:
%tmp = load i32, i32* @a, align 4
%cmp1.i = icmp ne i32 %tmp, 0
br label %for.body.i
for.body.i:
%tmp1 = phi i1 [ true, %entry ], [ false, %cond.end.i ]
%f.08.i = phi i32 [ 0, %entry ], [ %inc.i, %cond.end.i ]
%mul.i = select i1 %cmp1.i, i32 %f.08.i, i32 0
br i1 %tmp1, label %cond.end.i, label %cond.true.i
cond.true.i:
;; Ensure we don't replace this divide with a phi of ops that merges the wrong loop iteration value
%div.i = udiv i32 %mul.i, %f.08.i
br label %cond.end.i
cond.end.i:
%cond.i = phi i32 [ %div.i, %cond.true.i ], [ 0, %for.body.i ]
%inc.i = add nuw nsw i32 %f.08.i, 1
%test = udiv i32 %mul.i, %inc.i
%call5= tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str4, i64 0, i64 0), i32 %test)
%exitcond.i = icmp eq i32 %inc.i, 4
br i1 %exitcond.i, label %fn1.exit, label %for.body.i
fn1.exit:
%cond.i.lcssa = phi i32 [ %cond.i, %cond.end.i ]
%call4= tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([6 x i8], [6 x i8]* @.str4, i64 0, i64 0), i32 %cond.i.lcssa)
ret i32 0
}