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/X86/peephole-multiple-folds.ll

30 lines
1.2 KiB
LLVM
Raw Normal View History

[CodeGen] Teach the peephole optimizer to remember (and exploit) all folding opportunities in the current basic block, rather than just the last one seen. <rdar://problem/16478629> llvm-svn: 205481
2014-04-03 06:59:58 +08:00
; 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:
Fix test case. llvm-svn: 205492
2014-04-03 08:14:18 +08:00
; CHECK: test_peephole_multi_fold:
llvm/test/CodeGen/X86/peephole-multiple-folds.ll: Relax expressions to satisfy win32. llvm-svn: 205559
2014-04-04 04:07:51 +08:00
; CHECK: vfmadd231ps ({{%rdi|%rcx}}),
; CHECK: vfmadd231ps ({{%rsi|%rdx}}),
[CodeGen] Teach the peephole optimizer to remember (and exploit) all folding opportunities in the current basic block, rather than just the last one seen. <rdar://problem/16478629> llvm-svn: 205481
2014-04-03 06:59:58 +08:00
%vsum1 = phi <8 x float> [ %vsum1.next, %loopbody ], [ zeroinitializer, %entry ]
%vsum2 = phi <8 x float> [ %vsum2.next, %loopbody ], [ zeroinitializer, %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
%m1 = load <8 x float>, <8 x float>* %p1, align 1
%m2 = load <8 x float>, <8 x float>* %p2, align 1
[CodeGen] Teach the peephole optimizer to remember (and exploit) all folding opportunities in the current basic block, rather than just the last one seen. <rdar://problem/16478629> llvm-svn: 205481
2014-04-03 06:59:58 +08:00
%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>)