File: neon-dot-product.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 (126 lines) | stat: -rw-r--r-- 5,510 bytes parent folder | download | duplicates (5)
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
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
; RUN: llc -mtriple aarch64-none-linux-gnu -mattr=+dotprod < %s | FileCheck %s

declare <2 x i32> @llvm.aarch64.neon.udot.v2i32.v8i8(<2 x i32>, <8 x i8>, <8 x i8>)
declare <4 x i32> @llvm.aarch64.neon.udot.v4i32.v16i8(<4 x i32>, <16 x i8>, <16 x i8>)
declare <2 x i32> @llvm.aarch64.neon.sdot.v2i32.v8i8(<2 x i32>, <8 x i8>, <8 x i8>)
declare <4 x i32> @llvm.aarch64.neon.sdot.v4i32.v16i8(<4 x i32>, <16 x i8>, <16 x i8>)

define <2 x i32> @test_vdot_u32(<2 x i32> %a, <8 x i8> %b, <8 x i8> %c) #0 {
entry:
; CHECK-LABEL: test_vdot_u32:
; CHECK: udot v0.2s, v1.8b, v2.8b
  %vdot1.i = call <2 x i32> @llvm.aarch64.neon.udot.v2i32.v8i8(<2 x i32> %a, <8 x i8> %b, <8 x i8> %c) #2
  ret <2 x i32> %vdot1.i
}

define <4 x i32> @test_vdotq_u32(<4 x i32> %a, <16 x i8> %b, <16 x i8> %c) #0 {
entry:
; CHECK-LABEL: test_vdotq_u32:
; CHECK: udot v0.4s, v1.16b, v2.16b
  %vdot1.i = call <4 x i32> @llvm.aarch64.neon.udot.v4i32.v16i8(<4 x i32> %a, <16 x i8> %b, <16 x i8> %c) #2
  ret <4 x i32> %vdot1.i
}

define <2 x i32> @test_vdot_s32(<2 x i32> %a, <8 x i8> %b, <8 x i8> %c) #0 {
entry:
; CHECK-LABEL: test_vdot_s32:
; CHECK: sdot v0.2s, v1.8b, v2.8b
  %vdot1.i = call <2 x i32> @llvm.aarch64.neon.sdot.v2i32.v8i8(<2 x i32> %a, <8 x i8> %b, <8 x i8> %c) #2
  ret <2 x i32> %vdot1.i
}

define <4 x i32> @test_vdotq_s32(<4 x i32> %a, <16 x i8> %b, <16 x i8> %c) #0 {
entry:
; CHECK-LABEL: test_vdotq_s32:
; CHECK: sdot v0.4s, v1.16b, v2.16b
  %vdot1.i = call <4 x i32> @llvm.aarch64.neon.sdot.v4i32.v16i8(<4 x i32> %a, <16 x i8> %b, <16 x i8> %c) #2
  ret <4 x i32> %vdot1.i
}

define <2 x i32> @test_vdot_lane_u32(<2 x i32> %a, <8 x i8> %b, <8 x i8> %c) {
entry:
; CHECK-LABEL: test_vdot_lane_u32:
; CHECK: udot v0.2s, v1.8b, v2.4b[1]
  %.cast = bitcast <8 x i8> %c to <2 x i32>
  %shuffle = shufflevector <2 x i32> %.cast, <2 x i32> undef, <2 x i32> <i32 1, i32 1>
  %.cast5 = bitcast <2 x i32> %shuffle to <8 x i8>
  %vdot1.i = call <2 x i32> @llvm.aarch64.neon.udot.v2i32.v8i8(<2 x i32> %a, <8 x i8> %b, <8 x i8> %.cast5) #2
  ret <2 x i32> %vdot1.i
}

define <4 x i32> @test_vdotq_lane_u32(<4 x i32> %a, <16 x i8> %b, <8 x i8> %c) {
entry:
; CHECK-LABEL: test_vdotq_lane_u32:
; CHECK:  udot v0.4s, v1.16b, v2.4b[1]
  %.cast = bitcast <8 x i8> %c to <2 x i32>
  %shuffle = shufflevector <2 x i32> %.cast, <2 x i32> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
  %.cast3 = bitcast <4 x i32> %shuffle to <16 x i8>
  %vdot1.i = call <4 x i32> @llvm.aarch64.neon.udot.v4i32.v16i8(<4 x i32> %a, <16 x i8> %b, <16 x i8> %.cast3) #2
  ret <4 x i32> %vdot1.i
}

define <2 x i32> @test_vdot_laneq_u32(<2 x i32> %a, <8 x i8> %b, <16 x i8> %c) {
entry:
; CHECK-LABEL: test_vdot_laneq_u32:
; CHECK:  udot v0.2s, v1.8b, v2.4b[1]
  %.cast = bitcast <16 x i8> %c to <4 x i32>
  %shuffle = shufflevector <4 x i32> %.cast, <4 x i32> undef, <2 x i32> <i32 1, i32 1>
  %.cast5 = bitcast <2 x i32> %shuffle to <8 x i8>
  %vdot1.i = call <2 x i32> @llvm.aarch64.neon.udot.v2i32.v8i8(<2 x i32> %a, <8 x i8> %b, <8 x i8> %.cast5) #2
  ret <2 x i32> %vdot1.i
}

define <4 x i32> @test_vdotq_laneq_u32(<4 x i32> %a, <16 x i8> %b, <16 x i8> %c) {
entry:
; CHECK-LABEL: test_vdotq_laneq_u32:
; CHECK:  udot v0.4s, v1.16b, v2.4b[1]
  %.cast = bitcast <16 x i8> %c to <4 x i32>
  %shuffle = shufflevector <4 x i32> %.cast, <4 x i32> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
  %.cast3 = bitcast <4 x i32> %shuffle to <16 x i8>
  %vdot1.i = call <4 x i32> @llvm.aarch64.neon.udot.v4i32.v16i8(<4 x i32> %a, <16 x i8> %b, <16 x i8> %.cast3) #2
  ret <4 x i32> %vdot1.i
}

define <2 x i32> @test_vdot_lane_s32(<2 x i32> %a, <8 x i8> %b, <8 x i8> %c) {
entry:
; CHECK-LABEL: test_vdot_lane_s32:
; CHECK: sdot v0.2s, v1.8b, v2.4b[1]
  %.cast = bitcast <8 x i8> %c to <2 x i32>
  %shuffle = shufflevector <2 x i32> %.cast, <2 x i32> undef, <2 x i32> <i32 1, i32 1>
  %.cast5 = bitcast <2 x i32> %shuffle to <8 x i8>
  %vdot1.i = call <2 x i32> @llvm.aarch64.neon.sdot.v2i32.v8i8(<2 x i32> %a, <8 x i8> %b, <8 x i8> %.cast5) #2
  ret <2 x i32> %vdot1.i
}

define <4 x i32> @test_vdotq_lane_s32(<4 x i32> %a, <16 x i8> %b, <8 x i8> %c) {
entry:
; CHECK-LABEL: test_vdotq_lane_s32:
; CHECK:  sdot v0.4s, v1.16b, v2.4b[1]
  %.cast = bitcast <8 x i8> %c to <2 x i32>
  %shuffle = shufflevector <2 x i32> %.cast, <2 x i32> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
  %.cast3 = bitcast <4 x i32> %shuffle to <16 x i8>
  %vdot1.i = call <4 x i32> @llvm.aarch64.neon.sdot.v4i32.v16i8(<4 x i32> %a, <16 x i8> %b, <16 x i8> %.cast3) #2
  ret <4 x i32> %vdot1.i
}

define <2 x i32> @test_vdot_laneq_s32(<2 x i32> %a, <8 x i8> %b, <16 x i8> %c) {
entry:
; CHECK-LABEL: test_vdot_laneq_s32:
; CHECK:  sdot v0.2s, v1.8b, v2.4b[1]
  %.cast = bitcast <16 x i8> %c to <4 x i32>
  %shuffle = shufflevector <4 x i32> %.cast, <4 x i32> undef, <2 x i32> <i32 1, i32 1>
  %.cast5 = bitcast <2 x i32> %shuffle to <8 x i8>
  %vdot1.i = call <2 x i32> @llvm.aarch64.neon.sdot.v2i32.v8i8(<2 x i32> %a, <8 x i8> %b, <8 x i8> %.cast5) #2
  ret <2 x i32> %vdot1.i
}

define <4 x i32> @test_vdotq_laneq_s32(<4 x i32> %a, <16 x i8> %b, <16 x i8> %c) {
entry:
; CHECK-LABEL: test_vdotq_laneq_s32:
; CHECK:  sdot v0.4s, v1.16b, v2.4b[1]
  %.cast = bitcast <16 x i8> %c to <4 x i32>
  %shuffle = shufflevector <4 x i32> %.cast, <4 x i32> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
  %.cast3 = bitcast <4 x i32> %shuffle to <16 x i8>
  %vdot1.i = call <4 x i32> @llvm.aarch64.neon.sdot.v4i32.v16i8(<4 x i32> %a, <16 x i8> %b, <16 x i8> %.cast3) #2
  ret <4 x i32> %vdot1.i
}