RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 02:52:53 +02:00
Code Issues Projects Releases Wiki Activity

[LV] Fix analyzeInterleaving when -pass-remarks enabled

Browse Source 
Summary:
If -pass-remarks=loop-vectorize, atomic ops will be seen by
analyzeInterleaving(), even though canVectorizeMemory() == false. This
is because we are requesting extra analysis instead of bailing out.

In such a case, we end up with a Group in both Load- and StoreGroups,
and then we'll try to access freed memory when traversing LoadGroups after having had released the Group when  iterating over StoreGroups.

The fix is to include mayWriteToMemory() when validating that two
instructions are the same kind of memory operation.

Reviewers: mssimpso, davidxl

Reviewed By: davidxl

Subscribers: hsaito, fhahn, llvm-commits

Differential Revision: https://reviews.llvm.org/D43064

llvm-svn: 324786
This commit is contained in:
Mircea Trofin 2018-02-10 00:07:45 +00:00
parent 44baaf322b
commit 46b3a67bda
2 changed files with 49 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -5926,7 +5926,12 @@ void InterleavedAccessInfo::analyzeInterleaving(
// Ignore A if it's already in a group or isn't the same kind of memory
// operation as B.
if (isInterleaved(A) || A->mayReadFromMemory() != B->mayReadFromMemory())
// Note that mayReadFromMemory() isn't mutually exclusive to mayWriteToMemory
// in the case of atomic loads. We shouldn't see those here, canVectorizeMemory()
// should have returned false - except for the case we asked for optimization
// remarks.
if (isInterleaved(A) || (A->mayReadFromMemory() != B->mayReadFromMemory())
|| (A->mayWriteToMemory() != B->mayWriteToMemory()))
continue;
// Check rules 1 and 2. Ignore A if its stride or size is different from

43
test/Transforms/LoopVectorize/interleaved-acess-with-remarks.ll Normal file
View File

@ -0,0 +1,43 @@
; RUN: opt -S -loop-vectorize -instcombine -force-vector-width=4 -force-vector-interleave=1 -enable-interleaved-mem-accesses=true -runtime-memory-check-threshold=24 --pass-remarks=loop-vectorize < %s | FileCheck %s
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
; This only tests that asking for remarks doesn't lead to compiler crashing
; (or timing out). We just check for output. To be sure, we also check we didn't
; vectorize.
; CHECK-LABEL: @atomicLoadsBothWriteAndReadMem
; CHECK-NOT: <{{[0-9]+}} x i8>
%"struct.std::__atomic_base" = type { i32 }
%"struct.std::atomic" = type { %"struct.std::__atomic_base" }
%union.anon = type { i64 }
%MyStruct = type { i32, %"struct.std::atomic", %union.anon }
define void @atomicLoadsBothWriteAndReadMem(%MyStruct *%a, %MyStruct *%b, %MyStruct *%lim) {
entry:
br label %loop
loop:
%0 = phi %MyStruct* [ %a, %entry ], [ %ainc, %loop ]
%1 = phi %MyStruct* [ %b, %entry ], [ %binc, %loop ]
%2 = getelementptr %MyStruct, %MyStruct* %1, i64 0, i32 0
%3 = load i32, i32* %2, align 8
%4 = getelementptr inbounds %MyStruct, %MyStruct* %0, i64 0, i32 0
store i32 %3, i32* %4, align 8
%5 = getelementptr inbounds %MyStruct, %MyStruct* %1, i64 0, i32 1, i32 0, i32 0
%6 = load atomic i32, i32* %5 monotonic, align 4
%7 = getelementptr inbounds %MyStruct, %MyStruct* %0, i64 0, i32 1, i32 0, i32 0
store atomic i32 %6, i32* %7 monotonic, align 4
%8 = getelementptr inbounds %MyStruct, %MyStruct* %1, i64 0, i32 2, i32 0
%9 = getelementptr inbounds %MyStruct, %MyStruct* %0, i64 0, i32 2, i32 0
%10 = load i64, i64* %8, align 8
store i64 %10, i64* %9, align 8
%binc = getelementptr inbounds %MyStruct, %MyStruct* %1, i64 1
%ainc = getelementptr inbounds %MyStruct, %MyStruct* %0, i64 1
%cond = icmp eq %MyStruct* %binc, %lim
br i1 %cond, label %exit, label %loop
exit:
ret void
}