RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 20:23:11 +01:00
Code Issues Projects Releases Wiki Activity

[LoopVectorize] Fix crash on "getNoopOrZeroExtend cannot truncate!" (PR45259)

Browse Source 
In InnerLoopVectorizer::getOrCreateTripCount, when the backedge taken
count is a SCEV add expression, its type is defined by the type of the
last operand of the add expression.

In the test case from PR45259, this last operand happens to be a
pointer, which (according to llvm::Type) does not have a primitive size
in bits. In this case, LoopVectorize fails to truncate the SCEV and
crashes as a result.

Uing ScalarEvolution::getTypeSizeInBits makes the truncation work as expected.

https://bugs.llvm.org/show_bug.cgi?id=45259

Differential Revision: https://reviews.llvm.org/D76669
This commit is contained in:
Vedant Kumar 2020-03-30 10:02:21 -07:00
parent 5676208119
commit 5db978be0e
2 changed files with 37 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -2583,7 +2583,7 @@ Value *InnerLoopVectorizer::getOrCreateTripCount(Loop *L) {
// compare. The only way that we get a backedge taken count is that the
// induction variable was signed and as such will not overflow. In such a case
// truncation is legal.
if (BackedgeTakenCount->getType()->getPrimitiveSizeInBits() >
if (SE->getTypeSizeInBits(BackedgeTakenCount->getType()) >
IdxTy->getPrimitiveSizeInBits())
BackedgeTakenCount = SE->getTruncateOrNoop(BackedgeTakenCount, IdxTy);
BackedgeTakenCount = SE->getNoopOrZeroExtend(BackedgeTakenCount, IdxTy);

36
test/Transforms/LoopVectorize/pr45259.ll Normal file
View File

@ -0,0 +1,36 @@
; RUN: opt < %s -S -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 | FileCheck %s
; Check that we can vectorize this loop without crashing.
; CHECK-LABEL: define {{.*}} @widget(
; CHECK: [[vecInd:%.*]] = phi <4 x i8> [ <i8 0, i8 1, i8 2, i8 3>
; CHECK-NEXT: add <4 x i8> [[vecInd]], <i8 1, i8 1, i8 1, i8 1>
define i8 @widget(i8* %arr, i8 %t9) {
bb:
br label %bb6
bb6:
%t1.0 = phi i8* [ %arr, %bb ], [ null, %bb6 ]
%c = call i1 @cond()
br i1 %c, label %for.preheader, label %bb6
for.preheader:
br label %for.body
for.body:
%iv = phi i8 [ %iv.next, %for.body ], [ 0, %for.preheader ]
%iv.next = add i8 %iv, 1
%ptr = getelementptr inbounds i8, i8* %arr, i8 %iv.next
%t3.i = icmp slt i8 %iv.next, %t9
%t3.i8 = zext i1 %t3.i to i8
store i8 %t3.i8, i8* %ptr
%ec = icmp eq i8* %t1.0, %ptr
br i1 %ec, label %for.exit, label %for.body
for.exit:
%iv.next.lcssa = phi i8 [ %iv.next, %for.body ]
ret i8 %iv.next.lcssa
}
declare i1 @cond()