llvm-project/llvm/test/CodeGen/X86/blend-msb.ll

40 lines
1.3 KiB
LLVM

; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7 -mattr=+sse41 | FileCheck %s
; In this test we check that sign-extend of the mask bit is performed by
; shifting the needed bit to the MSB, and not using shl+sra.
;CHECK-LABEL: vsel_float:
;CHECK: movl $-2147483648
;CHECK-NEXT: movd
;CHECK-NEXT: 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-LABEL: vsel_4xi8:
;CHECK: movl $-2147483648
;CHECK-NEXT: movd
;CHECK-NEXT: blendvps
;CHECK: ret
define <4 x i8> @vsel_4xi8(<4 x i8> %v1, <4 x i8> %v2) {
%vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x i8> %v1, <4 x i8> %v2
ret <4 x i8> %vsel
}
; We do not have native support for v8i16 blends and we have to use the
; blendvb instruction or a sequence of NAND/OR/AND. Make sure that we do not r
; reduce the mask in this case.
;CHECK-LABEL: vsel_8xi16:
;CHECK: psllw
;CHECK: psraw
;CHECK: pblendvb
;CHECK: ret
define <8 x i16> @vsel_8xi16(<8 x i16> %v1, <8 x i16> %v2) {
%vsel = select <8 x i1> <i1 true, i1 false, i1 false, i1 false, i1 true, i1 false, i1 false, i1 false>, <8 x i16> %v1, <8 x i16> %v2
ret <8 x i16> %vsel
}