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
|
; RUN: llc -mtriple=aarch64-linux-gnu -stop-after=instruction-select < %s | FileCheck %s
declare void @llvm.aarch64.neon.st2.v4f32.p0f32(<4 x float>, <4 x float>, float*)
declare void @llvm.aarch64.neon.st3.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, float*)
declare void @llvm.aarch64.neon.st4.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, <4 x float>, float*)
declare void @llvm.aarch64.neon.st1x2.v4f32.p0f32(<4 x float>, <4 x float>, float*)
declare void @llvm.aarch64.neon.st1x3.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, float*)
declare void @llvm.aarch64.neon.st1x4.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, <4 x float>, float*)
declare void @llvm.aarch64.neon.st2lane.v4f32.p0f32(<4 x float>, <4 x float>, i64, float*)
declare void @llvm.aarch64.neon.st3lane.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, i64, float*)
declare void @llvm.aarch64.neon.st4lane.v4f32.p0f32(<4 x float>, <4 x float>, <4 x float>, <4 x float>, i64, float*)
define void @addstx(float* %res, <4 x float>* %a, <4 x float>* %b, <4 x float>* %c, <4 x float>* %d) {
%al = load <4 x float>, <4 x float>* %a
%bl = load <4 x float>, <4 x float>* %b
%cl = load <4 x float>, <4 x float>* %c
%dl = load <4 x float>, <4 x float>* %d
%ar = fadd <4 x float> %al, %bl
%br = fadd <4 x float> %bl, %cl
%cr = fadd <4 x float> %cl, %dl
%dr = fadd <4 x float> %dl, %al
; The sizes below are conservative. AArch64TargetLowering
; conservatively assumes the entire vector is stored.
tail call void @llvm.aarch64.neon.st2.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, float* %res)
; CHECK: ST2Twov4s {{.*}} :: (store 32 {{.*}})
tail call void @llvm.aarch64.neon.st3.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, float* %res)
; CHECK: ST3Threev4s {{.*}} :: (store 48 {{.*}})
tail call void @llvm.aarch64.neon.st4.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, <4 x float> %dr, float* %res)
; CHECK: ST4Fourv4s {{.*}} :: (store 64 {{.*}})
ret void
}
define void @addst1x(float* %res, <4 x float>* %a, <4 x float>* %b, <4 x float>* %c, <4 x float>* %d) {
%al = load <4 x float>, <4 x float>* %a
%bl = load <4 x float>, <4 x float>* %b
%cl = load <4 x float>, <4 x float>* %c
%dl = load <4 x float>, <4 x float>* %d
%ar = fadd <4 x float> %al, %bl
%br = fadd <4 x float> %bl, %cl
%cr = fadd <4 x float> %cl, %dl
%dr = fadd <4 x float> %dl, %al
; The sizes below are conservative. AArch64TargetLowering
; conservatively assumes the entire vector is stored.
tail call void @llvm.aarch64.neon.st1x2.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, float* %res)
; CHECK: ST1Twov4s {{.*}} :: (store 32 {{.*}})
tail call void @llvm.aarch64.neon.st1x3.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, float* %res)
; CHECK: ST1Threev4s {{.*}} :: (store 48 {{.*}})
tail call void @llvm.aarch64.neon.st1x4.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, <4 x float> %dr, float* %res)
; CHECK: ST1Fourv4s {{.*}} :: (store 64 {{.*}})
ret void
}
define void @addstxlane(float* %res, <4 x float>* %a, <4 x float>* %b, <4 x float>* %c, <4 x float>* %d) {
%al = load <4 x float>, <4 x float>* %a
%bl = load <4 x float>, <4 x float>* %b
%cl = load <4 x float>, <4 x float>* %c
%dl = load <4 x float>, <4 x float>* %d
%ar = fadd <4 x float> %al, %bl
%br = fadd <4 x float> %bl, %cl
%cr = fadd <4 x float> %cl, %dl
%dr = fadd <4 x float> %dl, %al
; The sizes below are conservative. AArch64TargetLowering
; conservatively assumes the entire vector is stored.
tail call void @llvm.aarch64.neon.st2lane.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, i64 1, float* %res)
; CHECK: ST2i32 {{.*}} :: (store 32 {{.*}})
tail call void @llvm.aarch64.neon.st3lane.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, i64 1, float* %res)
; CHECK: ST3i32 {{.*}} :: (store 48 {{.*}})
tail call void @llvm.aarch64.neon.st4lane.v4f32.p0f32(<4 x float> %ar, <4 x float> %br, <4 x float> %cr, <4 x float> %dr, i64 1, float* %res)
; CHECK: ST4i32 {{.*}} :: (store 64 {{.*}})
ret void
}
|
