RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-20 03:23:01 +02:00
Code Issues Projects Releases Wiki Activity

[IRCE] Fix buggy behavior in Clamp

Browse Source 
Clamp function was too optimistic when choosing signed or unsigned min/max function for calculations.
In fact, `!IsSignedPredicate` guarantees us that `Smallest` and `Greatest` can be compared safely using unsigned
predicates, but we did not check this for `S` which can in theory be negative.

This patch makes Clamp use signed min/max for cases when it fails to prove `S` being non-negative,
and it adds a test where such situation may lead to incorrect conditions calculation.

Differential Revision: https://reviews.llvm.org/D36873

llvm-svn: 311205
This commit is contained in:
Max Kazantsev 2017-08-18 22:50:29 +00:00
parent c5397dbcdd
commit 1040ba2c7d
2 changed files with 63 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
lib/Transforms/Scalar/InductiveRangeCheckElimination.cpp
View File

@ -1085,7 +1085,8 @@ LoopConstrainer::calculateSubRanges(bool IsSignedPredicate) const {
}
auto Clamp = [this, Smallest, Greatest, IsSignedPredicate](const SCEV *S) {
return IsSignedPredicate
bool MaybeNegativeValues = IsSignedPredicate || !SE.isKnownNonNegative(S);
return MaybeNegativeValues
? SE.getSMaxExpr(Smallest, SE.getSMinExpr(Greatest, S))
: SE.getUMaxExpr(Smallest, SE.getUMinExpr(Greatest, S));
};

61
test/Transforms/IRCE/clamp.ll Normal file
View File

@ -0,0 +1,61 @@
; RUN: opt -verify-loop-info -irce-print-changed-loops -irce -S < %s 2>&1 | FileCheck %s
; The test demonstrates that incorrect behavior of Clamp may lead to incorrect
; calculation of post-loop exit condition.
; CHECK: irce: in function test: constrained Loop at depth 1 containing: %loop<header><exiting>,%in_bounds<exiting>,%not_zero<latch><exiting>
define void @test() {
entry:
%indvars.iv.next467 = add nuw nsw i64 2, 1
%length.i167 = load i32, i32 addrspace(1)* undef, align 8
%tmp21 = zext i32 %length.i167 to i64
%tmp34 = load atomic i32, i32 addrspace(1)* undef unordered, align 4
%tmp35 = add i32 %tmp34, -9581
%tmp36 = icmp ugt i32 %length.i167, 1
br i1 %tmp36, label %preheader, label %exit
exit: ; preds = %in_bounds, %loop, %not_zero, %entry
ret void
preheader: ; preds = %entry
; CHECK: preheader:
; CHECK-NEXT: %length_gep.i146 = getelementptr inbounds i8, i8 addrspace(1)* undef, i64 8
; CHECK-NEXT: %length_gep_typed.i147 = bitcast i8 addrspace(1)* undef to i32 addrspace(1)*
; CHECK-NEXT: %tmp43 = icmp ult i64 %indvars.iv.next467, %tmp21
; CHECK-NEXT: br i1 false, label %loop.preheader, label %main.pseudo.exit
%length_gep.i146 = getelementptr inbounds i8, i8 addrspace(1)* undef, i64 8
%length_gep_typed.i147 = bitcast i8 addrspace(1)* undef to i32 addrspace(1)*
%tmp43 = icmp ult i64 %indvars.iv.next467, %tmp21
br label %loop
not_zero: ; preds = %in_bounds
; CHECK: not_zero:
; CHECK: %tmp56 = icmp ult i64 %indvars.iv.next, %tmp21
; CHECK-NEXT: [[COND:%[^ ]+]] = icmp ult i64 %indvars.iv.next, 1
; CHECK-NEXT: br i1 [[COND]], label %loop, label %main.exit.selector
%tmp51 = trunc i64 %indvars.iv.next to i32
%tmp53 = mul i32 %tmp51, %tmp51
%tmp54 = add i32 %tmp53, -9582
%tmp55 = add i32 %tmp54, %tmp62
%tmp56 = icmp ult i64 %indvars.iv.next, %tmp21
br i1 %tmp56, label %loop, label %exit
loop: ; preds = %not_zero, %preheader
%tmp62 = phi i32 [ 1, %preheader ], [ %tmp55, %not_zero ]
%indvars.iv750 = phi i64 [ 1, %preheader ], [ %indvars.iv.next, %not_zero ]
%length.i148 = load i32, i32 addrspace(1)* %length_gep_typed.i147, align 8
%tmp68 = zext i32 %length.i148 to i64
%tmp97 = icmp ult i64 2, %tmp68
%or.cond = and i1 %tmp43, %tmp97
%tmp99 = icmp ult i64 %indvars.iv750, %tmp21
%or.cond1 = and i1 %or.cond, %tmp99
br i1 %or.cond1, label %in_bounds, label %exit
in_bounds: ; preds = %loop
%indvars.iv.next = add nuw nsw i64 %indvars.iv750, 3
%tmp107 = icmp ult i64 %indvars.iv.next, 2
br i1 %tmp107, label %not_zero, label %exit
}