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
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx | FileCheck %s --check-prefix=AVX
; If the target's divss/divps instructions are substantially
; slower than rcpss/rcpps with a Newton-Raphson refinement,
; we should generate the estimate sequence.
; See PR21385 ( http://llvm.org/bugs/show_bug.cgi?id=21385 )
; for details about the accuracy, speed, and implementation
; differences of x86 reciprocal estimates.
define float @f32_no_estimate(float %x) #0 {
; AVX-LABEL: f32_no_estimate:
; AVX: # BB#0:
; AVX-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT: vdivss %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
;
%div = fdiv fast float 1.0, %x
ret float %div
}
define float @f32_one_step(float %x) #1 {
; AVX-LABEL: f32_one_step:
; AVX: # BB#0:
; AVX-NEXT: vrcpss %xmm0, %xmm0, %xmm1
; AVX-NEXT: vmulss %xmm1, %xmm0, %xmm0
; AVX-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; AVX-NEXT: vsubss %xmm0, %xmm2, %xmm0
; AVX-NEXT: vmulss %xmm0, %xmm1, %xmm0
; AVX-NEXT: vaddss %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
;
%div = fdiv fast float 1.0, %x
ret float %div
}
define float @f32_two_step(float %x) #2 {
; AVX-LABEL: f32_two_step:
; AVX: # BB#0:
; AVX-NEXT: vrcpss %xmm0, %xmm0, %xmm1
; AVX-NEXT: vmulss %xmm1, %xmm0, %xmm2
; AVX-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; AVX-NEXT: vsubss %xmm2, %xmm3, %xmm2
; AVX-NEXT: vmulss %xmm2, %xmm1, %xmm2
; AVX-NEXT: vaddss %xmm2, %xmm1, %xmm1
; AVX-NEXT: vmulss %xmm1, %xmm0, %xmm0
; AVX-NEXT: vsubss %xmm0, %xmm3, %xmm0
; AVX-NEXT: vmulss %xmm0, %xmm1, %xmm0
; AVX-NEXT: vaddss %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
;
%div = fdiv fast float 1.0, %x
ret float %div
}
define <4 x float> @v4f32_no_estimate(<4 x float> %x) #0 {
; AVX-LABEL: v4f32_no_estimate:
; AVX: # BB#0:
; AVX-NEXT: vmovaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; AVX-NEXT: vdivps %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
;
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
ret <4 x float> %div
}
define <4 x float> @v4f32_one_step(<4 x float> %x) #1 {
; AVX-LABEL: v4f32_one_step:
; AVX: # BB#0:
; AVX-NEXT: vrcpps %xmm0, %xmm1
; AVX-NEXT: vmulps %xmm1, %xmm0, %xmm0
; AVX-NEXT: vmovaps {{.*#+}} xmm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; AVX-NEXT: vsubps %xmm0, %xmm2, %xmm0
; AVX-NEXT: vmulps %xmm0, %xmm1, %xmm0
; AVX-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
;
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
ret <4 x float> %div
}
define <4 x float> @v4f32_two_step(<4 x float> %x) #2 {
; AVX-LABEL: v4f32_two_step:
; AVX: # BB#0:
; AVX-NEXT: vrcpps %xmm0, %xmm1
; AVX-NEXT: vmulps %xmm1, %xmm0, %xmm2
; AVX-NEXT: vmovaps {{.*#+}} xmm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; AVX-NEXT: vsubps %xmm2, %xmm3, %xmm2
; AVX-NEXT: vmulps %xmm2, %xmm1, %xmm2
; AVX-NEXT: vaddps %xmm2, %xmm1, %xmm1
; AVX-NEXT: vmulps %xmm1, %xmm0, %xmm0
; AVX-NEXT: vsubps %xmm0, %xmm3, %xmm0
; AVX-NEXT: vmulps %xmm0, %xmm1, %xmm0
; AVX-NEXT: vaddps %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
;
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
ret <4 x float> %div
}
define <8 x float> @v8f32_no_estimate(<8 x float> %x) #0 {
; AVX-LABEL: v8f32_no_estimate:
; AVX: # BB#0:
; AVX-NEXT: vmovaps {{.*#+}} ymm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; AVX-NEXT: vdivps %ymm0, %ymm1, %ymm0
; AVX-NEXT: retq
;
%div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
ret <8 x float> %div
}
define <8 x float> @v8f32_one_step(<8 x float> %x) #1 {
; AVX-LABEL: v8f32_one_step:
; AVX: # BB#0:
; AVX-NEXT: vrcpps %ymm0, %ymm1
; AVX-NEXT: vmulps %ymm1, %ymm0, %ymm0
; AVX-NEXT: vmovaps {{.*#+}} ymm2 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; AVX-NEXT: vsubps %ymm0, %ymm2, %ymm0
; AVX-NEXT: vmulps %ymm0, %ymm1, %ymm0
; AVX-NEXT: vaddps %ymm0, %ymm1, %ymm0
; AVX-NEXT: retq
;
%div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
ret <8 x float> %div
}
define <8 x float> @v8f32_two_step(<8 x float> %x) #2 {
; AVX-LABEL: v8f32_two_step:
; AVX: # BB#0:
; AVX-NEXT: vrcpps %ymm0, %ymm1
; AVX-NEXT: vmulps %ymm1, %ymm0, %ymm2
; AVX-NEXT: vmovaps {{.*#+}} ymm3 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
; AVX-NEXT: vsubps %ymm2, %ymm3, %ymm2
; AVX-NEXT: vmulps %ymm2, %ymm1, %ymm2
; AVX-NEXT: vaddps %ymm2, %ymm1, %ymm1
; AVX-NEXT: vmulps %ymm1, %ymm0, %ymm0
; AVX-NEXT: vsubps %ymm0, %ymm3, %ymm0
; AVX-NEXT: vmulps %ymm0, %ymm1, %ymm0
; AVX-NEXT: vaddps %ymm0, %ymm1, %ymm0
; AVX-NEXT: retq
;
%div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
ret <8 x float> %div
}
attributes #0 = { "unsafe-fp-math"="true" "reciprocal-estimates"="!divf,!vec-divf" }
attributes #1 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf,vec-divf" }
attributes #2 = { "unsafe-fp-math"="true" "reciprocal-estimates"="divf:2,vec-divf:2" }
|
