File: avx512-fma-commute.ll

package info (click to toggle)
llvm-toolchain-9 1%3A9.0.1-16
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 882,436 kB
  • sloc: cpp: 4,167,636; ansic: 714,256; asm: 457,610; python: 155,927; objc: 65,094; sh: 42,856; lisp: 26,908; perl: 7,786; pascal: 7,722; makefile: 6,881; ml: 5,581; awk: 3,648; cs: 2,027; xml: 888; javascript: 381; ruby: 156
file content (95 lines) | stat: -rw-r--r-- 4,688 bytes parent folder | download | duplicates (6)
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
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -disable-peephole -mtriple=x86_64-apple-darwin -mattr=avx512f | FileCheck %s

declare <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32)
declare <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double>, <2 x double>, <2 x double>, i8, i32)
declare <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float>, <4 x float>, <4 x float>, i8, i32)
declare <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double>, <2 x double>, <2 x double>, i8, i32)

define <4 x float> @test_int_x86_avx512_mask3_vfmadd_ss_load0(<4 x float>* %x0ptr, <4 x float> %x1, <4 x float> %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmadd_ss_load0:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd231ss (%rdi), %xmm0, %xmm1
; CHECK-NEXT:    vmovaps %xmm1, %xmm0
; CHECK-NEXT:    retq
  %x0 = load <4 x float>, <4 x float>* %x0ptr
  %res = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
  ret <4 x float> %res
}

define <4 x float> @test_int_x86_avx512_mask3_vfmadd_ss_load1(<4 x float> %x0, <4 x float>* %x1ptr, <4 x float> %x2){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmadd_ss_load1:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd231ss (%rdi), %xmm0, %xmm1
; CHECK-NEXT:    vmovaps %xmm1, %xmm0
; CHECK-NEXT:    retq
  %x1 = load <4 x float>, <4 x float>* %x1ptr
  %res = call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
  ret <4 x float> %res
}

define <2 x double> @test_int_x86_avx512_mask3_vfmadd_sd_load0(<2 x double>* %x0ptr, <2 x double> %x1, <2 x double> %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmadd_sd_load0:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd231sd (%rdi), %xmm0, %xmm1
; CHECK-NEXT:    vmovapd %xmm1, %xmm0
; CHECK-NEXT:    retq
  %x0 = load <2 x double>, <2 x double>* %x0ptr
  %res = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
  ret <2 x double> %res
}

define <2 x double> @test_int_x86_avx512_mask3_vfmadd_sd_load1(<2 x double> %x0, <2 x double>* %x1ptr, <2 x double> %x2){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmadd_sd_load1:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmadd231sd (%rdi), %xmm0, %xmm1
; CHECK-NEXT:    vmovapd %xmm1, %xmm0
; CHECK-NEXT:    retq
  %x1 = load <2 x double>, <2 x double>* %x1ptr
  %res = call <2 x double> @llvm.x86.avx512.mask3.vfmadd.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
  ret <2 x double> %res
}

define <4 x float> @test_int_x86_avx512_mask3_vfmsub_ss_load0(<4 x float>* %x0ptr, <4 x float> %x1, <4 x float> %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmsub_ss_load0:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmsub231ss (%rdi), %xmm0, %xmm1
; CHECK-NEXT:    vmovaps %xmm1, %xmm0
; CHECK-NEXT:    retq
  %x0 = load <4 x float>, <4 x float>* %x0ptr
  %res = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
  ret <4 x float> %res
}

define <4 x float> @test_int_x86_avx512_mask3_vfmsub_ss_load1(<4 x float> %x0, <4 x float>* %x1ptr, <4 x float> %x2){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmsub_ss_load1:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmsub231ss (%rdi), %xmm0, %xmm1
; CHECK-NEXT:    vmovaps %xmm1, %xmm0
; CHECK-NEXT:    retq
  %x1 = load <4 x float>, <4 x float>* %x1ptr
  %res = call <4 x float> @llvm.x86.avx512.mask3.vfmsub.ss(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, i8 -1, i32 4)
  ret <4 x float> %res
}

define <2 x double> @test_int_x86_avx512_mask3_vfmsub_sd_load0(<2 x double>* %x0ptr, <2 x double> %x1, <2 x double> %x2) {
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmsub_sd_load0:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmsub231sd (%rdi), %xmm0, %xmm1
; CHECK-NEXT:    vmovapd %xmm1, %xmm0
; CHECK-NEXT:    retq
  %x0 = load <2 x double>, <2 x double>* %x0ptr
  %res = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
  ret <2 x double> %res
}

define <2 x double> @test_int_x86_avx512_mask3_vfmsub_sd_load1(<2 x double> %x0, <2 x double>* %x1ptr, <2 x double> %x2){
; CHECK-LABEL: test_int_x86_avx512_mask3_vfmsub_sd_load1:
; CHECK:       ## %bb.0:
; CHECK-NEXT:    vfmsub231sd (%rdi), %xmm0, %xmm1
; CHECK-NEXT:    vmovapd %xmm1, %xmm0
; CHECK-NEXT:    retq
  %x1 = load <2 x double>, <2 x double>* %x1ptr
  %res = call <2 x double> @llvm.x86.avx512.mask3.vfmsub.sd(<2 x double> %x0, <2 x double> %x1, <2 x double> %x2, i8 -1, i32 4)
  ret <2 x double> %res
}