mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-07-21 18:29:45 +00:00
7c9c6ed761
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
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230794 91177308-0d34-0410-b5e6-96231b3b80d8
30 lines
1.2 KiB
LLVM
30 lines
1.2 KiB
LLVM
; RUN: llc -march=x86-64 -mcpu=core-avx2 < %s | FileCheck %s
|
|
;
|
|
; Test multiple peephole-time folds in a single basic block.
|
|
; <rdar://problem/16478629>
|
|
|
|
define <8 x float> @test_peephole_multi_fold(<8 x float>* %p1, <8 x float>* %p2) {
|
|
entry:
|
|
br label %loopbody
|
|
|
|
loopbody:
|
|
; CHECK: test_peephole_multi_fold:
|
|
; CHECK: vfmadd231ps ({{%rdi|%rcx}}),
|
|
; CHECK: vfmadd231ps ({{%rsi|%rdx}}),
|
|
%vsum1 = phi <8 x float> [ %vsum1.next, %loopbody ], [ zeroinitializer, %entry ]
|
|
%vsum2 = phi <8 x float> [ %vsum2.next, %loopbody ], [ zeroinitializer, %entry ]
|
|
%m1 = load <8 x float>, <8 x float>* %p1, align 1
|
|
%m2 = load <8 x float>, <8 x float>* %p2, align 1
|
|
%vsum1.next = tail call <8 x float> @llvm.x86.fma.vfmadd.ps.256(<8 x float> %m1, <8 x float> zeroinitializer, <8 x float> %vsum1)
|
|
%vsum2.next = tail call <8 x float> @llvm.x86.fma.vfmadd.ps.256(<8 x float> %m2, <8 x float> zeroinitializer, <8 x float> %vsum2)
|
|
%vsum1.next.1 = extractelement <8 x float> %vsum1.next, i32 0
|
|
%c = fcmp oeq float %vsum1.next.1, 0.0
|
|
br i1 %c, label %loopbody, label %loopexit
|
|
|
|
loopexit:
|
|
%r = fadd <8 x float> %vsum1.next, %vsum2.next
|
|
ret <8 x float> %r
|
|
}
|
|
|
|
declare <8 x float> @llvm.x86.fma.vfmadd.ps.256(<8 x float>, <8 x float>, <8 x float>)
|