maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/PowerPC/vec_buildvector_loadstore.ll

38 lines
2.3 KiB
LLVM
Raw Normal View History

Enable ILP scheduling for all nodes by default on PPC. Over the entire test-suite, this has an insignificantly negative average performance impact, but reduces some of the worst slowdowns from the anti-dep. change (r158294). Largest speedups: SingleSource/Benchmarks/Stanford/Quicksort - 28% SingleSource/Benchmarks/Stanford/Towers - 24% SingleSource/Benchmarks/Shootout-C++/matrix - 23% MultiSource/Benchmarks/SciMark2-C/scimark2 - 19% MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount - 15% (matrix and automotive-bitcount were both in the top-5 slowdown list from the anti-dep. change) Largest slowdowns: MultiSource/Benchmarks/McCat/03-testtrie/testtrie - 28% MultiSource/Benchmarks/mediabench/gsm/toast/toast - 26% MultiSource/Benchmarks/MiBench/automotive-susan/automotive-susan - 21% SingleSource/Benchmarks/CoyoteBench/lpbench - 20% MultiSource/Applications/d/make_dparser - 16% llvm-svn: 158296
2012-06-11 03:32:29 +08:00
; RUN: llc < %s -march=ppc32 -mtriple=powerpc-apple-darwin -mattr=+altivec -disable-ppc-ilp-pref | FileCheck %s
When generating a vector the really slow way, via loads and stores, handle the case where the element size is not a valid target type correctly (PPC). llvm-svn: 89521
2009-11-21 08:53:23 +08:00
; Formerly this did byte loads and word stores.
@a = external global <16 x i8>
@b = external global <16 x i8>
@c = external global <16 x i8>
define void @foo() nounwind ssp {
; CHECK: _foo:
; CHECK-NOT: stw
entry:
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%tmp0 = load <16 x i8>, <16 x i8>* @a, align 16
When generating a vector the really slow way, via loads and stores, handle the case where the element size is not a valid target type correctly (PPC). llvm-svn: 89521
2009-11-21 08:53:23 +08:00
%tmp180.i = extractelement <16 x i8> %tmp0, i32 0 ; <i8> [#uses=1]
%tmp181.i = insertelement <16 x i8> <i8 0, i8 0, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef>, i8 %tmp180.i, i32 2 ; <<16 x i8>> [#uses=1]
%tmp182.i = extractelement <16 x i8> %tmp0, i32 1 ; <i8> [#uses=1]
%tmp183.i = insertelement <16 x i8> %tmp181.i, i8 %tmp182.i, i32 3 ; <<16 x i8>> [#uses=1]
%tmp184.i = insertelement <16 x i8> %tmp183.i, i8 0, i32 4 ; <<16 x i8>> [#uses=1]
%tmp185.i = insertelement <16 x i8> %tmp184.i, i8 0, i32 5 ; <<16 x i8>> [#uses=1]
%tmp186.i = extractelement <16 x i8> %tmp0, i32 4 ; <i8> [#uses=1]
%tmp187.i = insertelement <16 x i8> %tmp185.i, i8 %tmp186.i, i32 6 ; <<16 x i8>> [#uses=1]
%tmp188.i = extractelement <16 x i8> %tmp0, i32 5 ; <i8> [#uses=1]
%tmp189.i = insertelement <16 x i8> %tmp187.i, i8 %tmp188.i, i32 7 ; <<16 x i8>> [#uses=1]
%tmp190.i = insertelement <16 x i8> %tmp189.i, i8 0, i32 8 ; <<16 x i8>> [#uses=1]
%tmp191.i = insertelement <16 x i8> %tmp190.i, i8 0, i32 9 ; <<16 x i8>> [#uses=1]
%tmp192.i = extractelement <16 x i8> %tmp0, i32 8 ; <i8> [#uses=1]
%tmp193.i = insertelement <16 x i8> %tmp191.i, i8 %tmp192.i, i32 10 ; <<16 x i8>> [#uses=1]
%tmp194.i = extractelement <16 x i8> %tmp0, i32 9 ; <i8> [#uses=1]
%tmp195.i = insertelement <16 x i8> %tmp193.i, i8 %tmp194.i, i32 11 ; <<16 x i8>> [#uses=1]
%tmp196.i = insertelement <16 x i8> %tmp195.i, i8 0, i32 12 ; <<16 x i8>> [#uses=1]
%tmp197.i = insertelement <16 x i8> %tmp196.i, i8 0, i32 13 ; <<16 x i8>> [#uses=1]
%tmp201 = shufflevector <16 x i8> %tmp197.i, <16 x i8> %tmp0, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 28, i32 29>; ModuleID = 'try.c'
store <16 x i8> %tmp201, <16 x i8>* @c, align 16
br label %return
return: ; preds = %bb2
ret void
; CHECK: blr
}