File: neon-mla-mls.ll

package info (click to toggle)
llvm-toolchain-7 1%3A7.0.1-8~deb9u3
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 733,456 kB
  • sloc: cpp: 3,776,651; ansic: 633,271; asm: 350,301; python: 142,716; objc: 107,612; sh: 22,626; lisp: 11,056; perl: 7,999; pascal: 6,742; ml: 5,537; awk: 3,536; makefile: 2,557; cs: 2,027; xml: 841; ruby: 156
file content (88 lines) | stat: -rw-r--r-- 2,719 bytes parent folder | download | duplicates (14)
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
; RUN: llc < %s -verify-machineinstrs -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s


define <8 x i8> @mla8xi8(<8 x i8> %A, <8 x i8> %B, <8 x i8> %C) {
;CHECK: mla {{v[0-9]+}}.8b, {{v[0-9]+}}.8b, {{v[0-9]+}}.8b
	%tmp1 = mul <8 x i8> %A, %B;
	%tmp2 = add <8 x i8> %C, %tmp1;
	ret <8 x i8> %tmp2
}

define <16 x i8> @mla16xi8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C) {
;CHECK: mla {{v[0-9]+}}.16b, {{v[0-9]+}}.16b, {{v[0-9]+}}.16b
	%tmp1 = mul <16 x i8> %A, %B;
	%tmp2 = add <16 x i8> %C, %tmp1;
	ret <16 x i8> %tmp2
}

define <4 x i16> @mla4xi16(<4 x i16> %A, <4 x i16> %B, <4 x i16> %C) {
;CHECK: mla {{v[0-9]+}}.4h, {{v[0-9]+}}.4h, {{v[0-9]+}}.4h
	%tmp1 = mul <4 x i16> %A, %B;
	%tmp2 = add <4 x i16> %C, %tmp1;
	ret <4 x i16> %tmp2
}

define <8 x i16> @mla8xi16(<8 x i16> %A, <8 x i16> %B, <8 x i16> %C) {
;CHECK: mla {{v[0-9]+}}.8h, {{v[0-9]+}}.8h, {{v[0-9]+}}.8h
	%tmp1 = mul <8 x i16> %A, %B;
	%tmp2 = add <8 x i16> %C, %tmp1;
	ret <8 x i16> %tmp2
}

define <2 x i32> @mla2xi32(<2 x i32> %A, <2 x i32> %B, <2 x i32> %C) {
;CHECK: mla {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s
	%tmp1 = mul <2 x i32> %A, %B;
	%tmp2 = add <2 x i32> %C, %tmp1;
	ret <2 x i32> %tmp2
}

define <4 x i32> @mla4xi32(<4 x i32> %A, <4 x i32> %B, <4 x i32> %C) {
;CHECK: mla {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.4s
	%tmp1 = mul <4 x i32> %A, %B;
	%tmp2 = add <4 x i32> %C, %tmp1;
	ret <4 x i32> %tmp2
}

define <8 x i8> @mls8xi8(<8 x i8> %A, <8 x i8> %B, <8 x i8> %C) {
;CHECK: mls {{v[0-9]+}}.8b, {{v[0-9]+}}.8b, {{v[0-9]+}}.8b
	%tmp1 = mul <8 x i8> %A, %B;
	%tmp2 = sub <8 x i8> %C, %tmp1;
	ret <8 x i8> %tmp2
}

define <16 x i8> @mls16xi8(<16 x i8> %A, <16 x i8> %B, <16 x i8> %C) {
;CHECK: mls {{v[0-9]+}}.16b, {{v[0-9]+}}.16b, {{v[0-9]+}}.16b
	%tmp1 = mul <16 x i8> %A, %B;
	%tmp2 = sub <16 x i8> %C, %tmp1;
	ret <16 x i8> %tmp2
}

define <4 x i16> @mls4xi16(<4 x i16> %A, <4 x i16> %B, <4 x i16> %C) {
;CHECK: mls {{v[0-9]+}}.4h, {{v[0-9]+}}.4h, {{v[0-9]+}}.4h
	%tmp1 = mul <4 x i16> %A, %B;
	%tmp2 = sub <4 x i16> %C, %tmp1;
	ret <4 x i16> %tmp2
}

define <8 x i16> @mls8xi16(<8 x i16> %A, <8 x i16> %B, <8 x i16> %C) {
;CHECK: mls {{v[0-9]+}}.8h, {{v[0-9]+}}.8h, {{v[0-9]+}}.8h
	%tmp1 = mul <8 x i16> %A, %B;
	%tmp2 = sub <8 x i16> %C, %tmp1;
	ret <8 x i16> %tmp2
}

define <2 x i32> @mls2xi32(<2 x i32> %A, <2 x i32> %B, <2 x i32> %C) {
;CHECK: mls {{v[0-9]+}}.2s, {{v[0-9]+}}.2s, {{v[0-9]+}}.2s
	%tmp1 = mul <2 x i32> %A, %B;
	%tmp2 = sub <2 x i32> %C, %tmp1;
	ret <2 x i32> %tmp2
}

define <4 x i32> @mls4xi32(<4 x i32> %A, <4 x i32> %B, <4 x i32> %C) {
;CHECK: mls {{v[0-9]+}}.4s, {{v[0-9]+}}.4s, {{v[0-9]+}}.4s
	%tmp1 = mul <4 x i32> %A, %B;
	%tmp2 = sub <4 x i32> %C, %tmp1;
	ret <4 x i32> %tmp2
}