mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-01 16:33:37 +01:00
e24a043703
using vextractf128. This will reduce the number of issued instruction for several avx codes. llvm-svn: 136323
48 lines
1.6 KiB
LLVM
48 lines
1.6 KiB
LLVM
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s
|
|
|
|
; CHECK: vxorps
|
|
; CHECK-NEXT: vinsertf128 $0
|
|
define <8 x float> @castA(<4 x float> %m) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <4 x float> %m, <4 x float> zeroinitializer, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 4, i32 4, i32 4>
|
|
ret <8 x float> %shuffle.i
|
|
}
|
|
|
|
; CHECK: vxorps
|
|
; CHECK-NEXT: vinsertf128 $0
|
|
define <4 x double> @castB(<2 x double> %m) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <2 x double> %m, <2 x double> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 2, i32 2>
|
|
ret <4 x double> %shuffle.i
|
|
}
|
|
|
|
; CHECK: vpxor
|
|
; CHECK-NEXT: vinsertf128 $0
|
|
define <4 x i64> @castC(<2 x i64> %m) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <2 x i64> %m, <2 x i64> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 2, i32 2>
|
|
ret <4 x i64> %shuffle.i
|
|
}
|
|
|
|
; CHECK-NOT: vextractf128 $0
|
|
define <4 x float> @castD(<8 x float> %m) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <8 x float> %m, <8 x float> %m, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
|
ret <4 x float> %shuffle.i
|
|
}
|
|
|
|
; CHECK-NOT: vextractf128 $0
|
|
define <2 x i64> @castE(<4 x i64> %m) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <4 x i64> %m, <4 x i64> %m, <2 x i32> <i32 0, i32 1>
|
|
ret <2 x i64> %shuffle.i
|
|
}
|
|
|
|
; CHECK-NOT: vextractf128 $0
|
|
define <2 x double> @castF(<4 x double> %m) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <4 x double> %m, <4 x double> %m, <2 x i32> <i32 0, i32 1>
|
|
ret <2 x double> %shuffle.i
|
|
}
|
|
|