RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-23 12:24:34 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[LSR] Check for signed overflow in NarrowSearchSpaceByDetectingSupersets.

Browse Source 
We are adding a sign extended IR value to an int64_t, which can cause
signed overflows, as in the attached test case, where we have a formula
with BaseOffset = -1 and a constant with numeric_limits<int64_t>::min().

If the addition would overflow, skip the simplification for this
formula. Note that the target triple is required to trigger the failure.

Reviewers: qcolombet, gilr, kparzysz, efriedma

Reviewed By: efriedma

Differential Revision: https://reviews.llvm.org/D59211

llvm-svn: 356256
This commit is contained in:
Florian Hahn 2019-03-15 12:17:36 +00:00
parent 30acd71a23
commit e9781212b4
2 changed files with 41 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/Transforms/Scalar/LoopStrengthReduce.cpp
View File

@ -4423,7 +4423,9 @@ void LSRInstance::NarrowSearchSpaceByDetectingSupersets() {
I = F.BaseRegs.begin(), E = F.BaseRegs.end(); I != E; ++I) {
if (const SCEVConstant *C = dyn_cast<SCEVConstant>(*I)) {
Formula NewF = F;
NewF.BaseOffset += C->getValue()->getSExtValue();
//FIXME: Formulas should store bitwidth to do wrapping properly.
// See PR41034.
NewF.BaseOffset += (uint64_t)C->getValue()->getSExtValue();
NewF.BaseRegs.erase(NewF.BaseRegs.begin() +
(I - F.BaseRegs.begin()));
if (LU.HasFormulaWithSameRegs(NewF)) {

38
test/Transforms/LoopStrengthReduce/X86/lsr-overflow.ll Normal file
View File

@ -0,0 +1,38 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -lsr-complexity-limit=50 -loop-reduce -S %s | FileCheck %s
target triple = "x86_64-apple-macosx10.14.0"
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
define void @overflow1(i64 %a) {
; CHECK-LABEL: @overflow1(
; CHECK-NEXT: bb:
; CHECK-NEXT: br label [[BB1:%.*]]
; CHECK: bb1:
; CHECK-NEXT: [[TMP:%.*]] = phi i64 [ [[A:%.*]], [[BB:%.*]] ], [ [[TMP6:%.*]], [[BB1]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[TMP]], -9223372036854775808
; CHECK-NEXT: [[TMP4:%.*]] = icmp ne i64 [[TMP0]], 0
; CHECK-NEXT: [[TMP5:%.*]] = and i1 [[TMP4]], true
; CHECK-NEXT: [[TMP6]] = add i64 [[TMP]], 1
; CHECK-NEXT: br i1 [[TMP5]], label [[BB1]], label [[BB7:%.*]]
; CHECK: bb7:
; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[TMP6]], -1
; CHECK-NEXT: [[TMP9:%.*]] = and i64 [[TMP1]], 1
; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[TMP9]], 0
; CHECK-NEXT: unreachable
;
bb:
br label %bb1
bb1: ; preds = %bb1, %bb
%tmp = phi i64 [ %a, %bb ], [ %tmp6, %bb1 ]
%tmp4 = icmp ne i64 %tmp, -9223372036854775808
%tmp5 = and i1 %tmp4, 1
%tmp6 = add i64 %tmp, 1
br i1 %tmp5, label %bb1, label %bb7
bb7: ; preds = %bb1
%tmp9 = and i64 %tmp, 1
%tmp10 = icmp eq i64 %tmp9, 0
unreachable
}