mirror of
https://github.com/c64scene-ar/llvm-6502.git
synced 2024-12-24 22:32:47 +00:00
814c6ced85
in Nadav's r139285 and r139287 commits. 1) Rename vsel.ll to a more descriptive name 2) Change the order of BLEND operands to "Op1, Op2, Cond", this is necessary because PBLENDVB is already used in different places with this order, and it was being emitted in the wrong way for vselect 3) Add AVX patterns and tests for the same SSE41 instructions git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@139305 91177308-0d34-0410-b5e6-96231b3b80d8
48 lines
1.3 KiB
LLVM
48 lines
1.3 KiB
LLVM
; RUN: llc < %s -march=x86 -promote-elements -mattr=+sse41 | FileCheck %s
|
|
|
|
;CHECK: vsel_float
|
|
;CHECK: blendvps
|
|
;CHECK: ret
|
|
define <4 x float> @vsel_float(<4 x float> %v1, <4 x float> %v2) {
|
|
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x float> %v1, <4 x float> %v2
|
|
ret <4 x float> %vsel
|
|
}
|
|
|
|
|
|
;CHECK: vsel_i32
|
|
;CHECK: blendvps
|
|
;CHECK: ret
|
|
define <4 x i32> @vsel_i32(<4 x i32> %v1, <4 x i32> %v2) {
|
|
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x i32> %v1, <4 x i32> %v2
|
|
ret <4 x i32> %vsel
|
|
}
|
|
|
|
|
|
;CHECK: vsel_double
|
|
;CHECK: blendvpd
|
|
;CHECK: ret
|
|
define <4 x double> @vsel_double(<4 x double> %v1, <4 x double> %v2) {
|
|
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x double> %v1, <4 x double> %v2
|
|
ret <4 x double> %vsel
|
|
}
|
|
|
|
|
|
;CHECK: vsel_i64
|
|
;CHECK: blendvpd
|
|
;CHECK: ret
|
|
define <4 x i64> @vsel_i64(<4 x i64> %v1, <4 x i64> %v2) {
|
|
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x i64> %v1, <4 x i64> %v2
|
|
ret <4 x i64> %vsel
|
|
}
|
|
|
|
|
|
;CHECK: vsel_i8
|
|
;CHECK: pblendvb
|
|
;CHECK: ret
|
|
define <16 x i8> @vsel_i8(<16 x i8> %v1, <16 x i8> %v2) {
|
|
%vsel = select <16 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false>, <16 x i8> %v1, <16 x i8> %v2
|
|
ret <16 x i8> %vsel
|
|
}
|
|
|
|
|