1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -march=x86-64 -mtriple=x86_64-apple-darwin -mcpu=knl | FileCheck %s
define <16 x i32> @test2(<16 x i32> %x) {
; CHECK-LABEL: test2:
; CHECK: ## BB#0:
; CHECK-NEXT: vpternlogd $255, %zmm1, %zmm1, %zmm1
; CHECK-NEXT: vpaddd %zmm1, %zmm0, %zmm0
; CHECK-NEXT: retq
%res = add <16 x i32><i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>, %x
ret <16 x i32>%res
}
define <16 x float> @test3(<4 x float> %a) {
; CHECK-LABEL: test3:
; CHECK: ## BB#0:
; CHECK-NEXT: ## kill: %XMM0<def> %XMM0<kill> %ZMM0<def>
; CHECK-NEXT: vmovaps {{.*#+}} zmm2 = [0,1,2,3,4,18,16,7,8,9,10,11,12,13,14,15]
; CHECK-NEXT: vpxord %zmm1, %zmm1, %zmm1
; CHECK-NEXT: vpermt2ps %zmm0, %zmm2, %zmm1
; CHECK-NEXT: vmovaps %zmm1, %zmm0
; CHECK-NEXT: retq
%b = extractelement <4 x float> %a, i32 2
%c = insertelement <16 x float> <float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float undef, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00>, float %b, i32 5
%b1 = extractelement <4 x float> %a, i32 0
%c1 = insertelement <16 x float> %c, float %b1, i32 6
ret <16 x float>%c1
}
|
