mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2026-04-25 05:22:04 +00:00
Bruno Cardoso Lopes
cde4a1abd5
is the best we can do for these patterns. This fix PR10554. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@137161 91177308-0d34-0410-b5e6-96231b3b80d8
90 lines
3.5 KiB
LLVM
90 lines
3.5 KiB
LLVM
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s
|
|
|
|
; CHECK: vunpckhps
|
|
define <8 x float> @unpackhips(<8 x float> %src1, <8 x float> %src2) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <8 x float> %src1, <8 x float> %src2, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
|
|
ret <8 x float> %shuffle.i
|
|
}
|
|
|
|
; CHECK: vunpckhpd
|
|
define <4 x double> @unpackhipd(<4 x double> %src1, <4 x double> %src2) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <4 x double> %src1, <4 x double> %src2, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
|
|
ret <4 x double> %shuffle.i
|
|
}
|
|
|
|
; CHECK: vunpcklps
|
|
define <8 x float> @unpacklops(<8 x float> %src1, <8 x float> %src2) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <8 x float> %src1, <8 x float> %src2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
|
|
ret <8 x float> %shuffle.i
|
|
}
|
|
|
|
; CHECK: vunpcklpd
|
|
define <4 x double> @unpacklopd(<4 x double> %src1, <4 x double> %src2) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <4 x double> %src1, <4 x double> %src2, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
|
|
ret <4 x double> %shuffle.i
|
|
}
|
|
|
|
; CHECK-NOT: vunpcklps %ymm
|
|
define <8 x float> @unpacklops-not(<8 x float> %src1, <8 x float> %src2) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <8 x float> %src1, <8 x float> %src2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
|
|
ret <8 x float> %shuffle.i
|
|
}
|
|
|
|
; CHECK-NOT: vunpcklpd %ymm
|
|
define <4 x double> @unpacklopd-not(<4 x double> %src1, <4 x double> %src2) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <4 x double> %src1, <4 x double> %src2, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
|
|
ret <4 x double> %shuffle.i
|
|
}
|
|
|
|
; CHECK-NOT: vunpckhps %ymm
|
|
define <8 x float> @unpackhips-not(<8 x float> %src1, <8 x float> %src2) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <8 x float> %src1, <8 x float> %src2, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 4, i32 12, i32 5, i32 13>
|
|
ret <8 x float> %shuffle.i
|
|
}
|
|
|
|
; CHECK-NOT: vunpckhpd %ymm
|
|
define <4 x double> @unpackhipd-not(<4 x double> %src1, <4 x double> %src2) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <4 x double> %src1, <4 x double> %src2, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
|
|
ret <4 x double> %shuffle.i
|
|
}
|
|
|
|
;;;;
|
|
;;;; Unpack versions using the fp unit for int unpacking
|
|
;;;;
|
|
|
|
; CHECK: vunpckhps
|
|
define <8 x i32> @unpackhips1(<8 x i32> %src1, <8 x i32> %src2) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <8 x i32> %src1, <8 x i32> %src2, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
|
|
ret <8 x i32> %shuffle.i
|
|
}
|
|
|
|
; CHECK: vunpckhpd
|
|
define <4 x i64> @unpackhipd1(<4 x i64> %src1, <4 x i64> %src2) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <4 x i64> %src1, <4 x i64> %src2, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
|
|
ret <4 x i64> %shuffle.i
|
|
}
|
|
|
|
; CHECK: vunpcklps
|
|
define <8 x i32> @unpacklops1(<8 x i32> %src1, <8 x i32> %src2) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <8 x i32> %src1, <8 x i32> %src2, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
|
|
ret <8 x i32> %shuffle.i
|
|
}
|
|
|
|
; CHECK: vunpcklpd
|
|
define <4 x i64> @unpacklopd1(<4 x i64> %src1, <4 x i64> %src2) nounwind uwtable readnone ssp {
|
|
entry:
|
|
%shuffle.i = shufflevector <4 x i64> %src1, <4 x i64> %src2, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
|
|
ret <4 x i64> %shuffle.i
|
|
}
|