diff options
author | Karl-Johan Karlsson <karl-johan.karlsson@ericsson.com> | 2017-02-22 18:37:36 +0000 |
---|---|---|
committer | Karl-Johan Karlsson <karl-johan.karlsson@ericsson.com> | 2017-02-22 18:37:36 +0000 |
commit | 6eaed7aceb78f235b8e9e7690d3768937d4555a2 (patch) | |
tree | 7db53be153e337d5a371c42da8ff0424f5c01574 /llvm/test/Transforms/LoopVectorize/AArch64 | |
parent | 38b42b4a95886d63ef1b67fce7aa50f2e4943e3f (diff) | |
download | bcm5719-llvm-6eaed7aceb78f235b8e9e7690d3768937d4555a2.tar.gz bcm5719-llvm-6eaed7aceb78f235b8e9e7690d3768937d4555a2.zip |
[LoopVectorize] Added address space check when analysing interleaved accesses
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.
llvm-svn: 295858
Diffstat (limited to 'llvm/test/Transforms/LoopVectorize/AArch64')
-rw-r--r-- | llvm/test/Transforms/LoopVectorize/AArch64/pr31900.ll | 37 |
1 files changed, 37 insertions, 0 deletions
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/pr31900.ll b/llvm/test/Transforms/LoopVectorize/AArch64/pr31900.ll new file mode 100644 index 00000000000..5ea38a4a246 --- /dev/null +++ b/llvm/test/Transforms/LoopVectorize/AArch64/pr31900.ll @@ -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 +} |