1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-30 07:22:55 +01:00
llvm-mirror/test/CodeGen/X86/2012-05-19-avx2-store.ll
Manman Ren 78b8d454cc X86 Peephole: fold loads to the source register operand if possible.
Machine CSE and other optimizations can remove instructions so folding
is possible at peephole while not possible at ISel.

This patch is a rework of r160919 and was tested on clang self-host on my local
machine.

rdar://10554090 and rdar://11873276

llvm-svn: 161152
2012-08-02 00:56:42 +00:00

14 lines
497 B
LLVM

; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx2 | FileCheck %s
define void @double_save(<4 x i32>* %Ap, <4 x i32>* %Bp, <8 x i32>* %P) nounwind ssp {
entry:
; CHECK: vmovaps
; CHECK: vinsertf128 $1, ([[A0:%rdi|%rsi]]),
; CHECK: vmovups
%A = load <4 x i32>* %Ap
%B = load <4 x i32>* %Bp
%Z = shufflevector <4 x i32>%A, <4 x i32>%B, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
store <8 x i32> %Z, <8 x i32>* %P, align 16
ret void
}