RPCS3/llvm
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm.git synced 2025-02-25 21:33:25 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[LoopVectorize] Added address space check when analysing interleaved accesses

Browse Source 
Prevent memory objects of different address spaces to be part of
the same load/store groups when analysing interleaved accesses.

This is fixing pr31900.

Reviewers: HaoLiu, mssimpso, mkuper

Reviewed By: mssimpso, mkuper

Subscribers: llvm-commits, efriedma, mzolotukhin

Differential Revision: https://reviews.llvm.org/D29717

This reverts r295042 (re-applies r295038) with an additional fix for the
buildbot problem.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@295858 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Karl-Johan Karlsson 2017-02-22 18:37:36 +00:00
parent 2be1878c67
commit 29fec22c97
2 changed files with 56 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lib/Transforms/Vectorize/LoopVectorize.cpp
View File

@ -6025,6 +6025,11 @@ void InterleavedAccessInfo::analyzeInterleaving(
if (DesA.Stride != DesB.Stride || DesA.Size != DesB.Size)
continue;
// Ignore A if the memory object of A and B don't belong to the same
// address space
if (getMemInstAddressSpace(A) != getMemInstAddressSpace(B))
continue;
// Calculate the distance from A to B.
const SCEVConstant *DistToB = dyn_cast<SCEVConstant>(
PSE.getSE()->getMinusSCEV(DesA.Scev, DesB.Scev));

37
test/Transforms/LoopVectorize/AArch64/pr31900.ll Normal file
View File

@ -0,0 +1,37 @@
; RUN: opt -S -mtriple=aarch64-apple-ios -loop-vectorize -enable-interleaved-mem-accesses -force-vector-width=2 < %s | FileCheck %s
; Reproducer for address space fault in the LoopVectorizer (pr31900). Added
; different sized address space pointers (p:16:16-p4:32:16) to the aarch64
; datalayout to reproduce the fault.
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128-p:16:16-p4:32:16"
; Check that all the loads are scalarized
; CHECK: load i16, i16*
; CHECK: load i16, i16*
; CHECK: load i16, i16 addrspace(4)*
; CHECK: load i16, i16 addrspace(4)*
%rec1445 = type { i16, i16, i16, i16, i16 }
define void @foo() {
bb1:
br label %bb4
bb4:
%tmp1 = phi i16 [ undef, %bb1 ], [ %_tmp1013, %bb4 ]
%tmp2 = phi %rec1445* [ undef, %bb1 ], [ %_tmp1015, %bb4 ]
%tmp3 = phi %rec1445 addrspace(4)* [ undef, %bb1 ], [ %_tmp1017, %bb4 ]
%0 = getelementptr %rec1445, %rec1445* %tmp2, i16 0, i32 1
%_tmp987 = load i16, i16* %0, align 1
%1 = getelementptr %rec1445, %rec1445 addrspace(4)* %tmp3, i32 0, i32 1
%_tmp993 = load i16, i16 addrspace(4)* %1, align 1
%_tmp1013 = add i16 %tmp1, 1
%_tmp1015 = getelementptr %rec1445, %rec1445* %tmp2, i16 1
%_tmp1017 = getelementptr %rec1445, %rec1445 addrspace(4)* %tmp3, i32 1
%_tmp1019 = icmp ult i16 %_tmp1013, 24
br i1 %_tmp1019, label %bb4, label %bb16
bb16:
unreachable
}