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
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
|
; 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
declare double @__sqrt_finite(double)
declare float @__sqrtf_finite(float)
declare x86_fp80 @__sqrtl_finite(x86_fp80)
declare float @llvm.sqrt.f32(float)
declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
declare <8 x float> @llvm.sqrt.v8f32(<8 x float>)
define double @finite_f64_no_estimate(double %d) #0 {
; AVX-LABEL: finite_f64_no_estimate:
; AVX: # BB#0:
; AVX-NEXT: vsqrtsd %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
;
%call = tail call double @__sqrt_finite(double %d) #2
ret double %call
}
; No estimates for doubles.
define double @finite_f64_estimate(double %d) #1 {
; AVX-LABEL: finite_f64_estimate:
; AVX: # BB#0:
; AVX-NEXT: vsqrtsd %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
;
%call = tail call double @__sqrt_finite(double %d) #2
ret double %call
}
define float @finite_f32_no_estimate(float %f) #0 {
; AVX-LABEL: finite_f32_no_estimate:
; AVX: # BB#0:
; AVX-NEXT: vsqrtss %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
;
%call = tail call float @__sqrtf_finite(float %f) #2
ret float %call
}
define float @finite_f32_estimate(float %f) #1 {
; AVX-LABEL: finite_f32_estimate:
; AVX: # BB#0:
; AVX-NEXT: vrsqrtss %xmm0, %xmm0, %xmm1
; AVX-NEXT: vmulss %xmm1, %xmm0, %xmm2
; AVX-NEXT: vmulss %xmm1, %xmm2, %xmm1
; AVX-NEXT: vaddss {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT: vmulss {{.*}}(%rip), %xmm2, %xmm2
; AVX-NEXT: vmulss %xmm1, %xmm2, %xmm1
; AVX-NEXT: vxorps %xmm2, %xmm2, %xmm2
; AVX-NEXT: vcmpeqss %xmm2, %xmm0, %xmm0
; AVX-NEXT: vandnps %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
;
%call = tail call float @__sqrtf_finite(float %f) #2
ret float %call
}
define x86_fp80 @finite_f80_no_estimate(x86_fp80 %ld) #0 {
; AVX-LABEL: finite_f80_no_estimate:
; AVX: # BB#0:
; AVX-NEXT: fldt {{[0-9]+}}(%rsp)
; AVX-NEXT: fsqrt
; AVX-NEXT: retq
;
%call = tail call x86_fp80 @__sqrtl_finite(x86_fp80 %ld) #2
ret x86_fp80 %call
}
; Don't die on the impossible.
define x86_fp80 @finite_f80_estimate_but_no(x86_fp80 %ld) #1 {
; AVX-LABEL: finite_f80_estimate_but_no:
; AVX: # BB#0:
; AVX-NEXT: fldt {{[0-9]+}}(%rsp)
; AVX-NEXT: fsqrt
; AVX-NEXT: retq
;
%call = tail call x86_fp80 @__sqrtl_finite(x86_fp80 %ld) #2
ret x86_fp80 %call
}
define float @f32_no_estimate(float %x) #0 {
; AVX-LABEL: f32_no_estimate:
; AVX: # BB#0:
; AVX-NEXT: vsqrtss %xmm0, %xmm0, %xmm0
; AVX-NEXT: vmovss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; AVX-NEXT: vdivss %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
;
%sqrt = tail call float @llvm.sqrt.f32(float %x)
%div = fdiv fast float 1.0, %sqrt
ret float %div
}
define float @f32_estimate(float %x) #1 {
; AVX-LABEL: f32_estimate:
; AVX: # BB#0:
; AVX-NEXT: vrsqrtss %xmm0, %xmm0, %xmm1
; AVX-NEXT: vmulss %xmm1, %xmm1, %xmm2
; AVX-NEXT: vmulss %xmm2, %xmm0, %xmm0
; AVX-NEXT: vaddss {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vmulss {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT: vmulss %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
;
%sqrt = tail call float @llvm.sqrt.f32(float %x)
%div = fdiv fast float 1.0, %sqrt
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: vsqrtps %xmm0, %xmm0
; 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
;
%sqrt = tail call <4 x float> @llvm.sqrt.v4f32(<4 x float> %x)
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt
ret <4 x float> %div
}
define <4 x float> @v4f32_estimate(<4 x float> %x) #1 {
; AVX-LABEL: v4f32_estimate:
; AVX: # BB#0:
; AVX-NEXT: vrsqrtps %xmm0, %xmm1
; AVX-NEXT: vmulps %xmm1, %xmm1, %xmm2
; AVX-NEXT: vmulps %xmm2, %xmm0, %xmm0
; AVX-NEXT: vaddps {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vmulps {{.*}}(%rip), %xmm1, %xmm1
; AVX-NEXT: vmulps %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
;
%sqrt = tail call <4 x float> @llvm.sqrt.v4f32(<4 x float> %x)
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt
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: vsqrtps %ymm0, %ymm0
; 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
;
%sqrt = tail call <8 x float> @llvm.sqrt.v8f32(<8 x float> %x)
%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>, %sqrt
ret <8 x float> %div
}
define <8 x float> @v8f32_estimate(<8 x float> %x) #1 {
; AVX-LABEL: v8f32_estimate:
; AVX: # BB#0:
; AVX-NEXT: vrsqrtps %ymm0, %ymm1
; AVX-NEXT: vmulps %ymm1, %ymm1, %ymm2
; AVX-NEXT: vmulps %ymm2, %ymm0, %ymm0
; AVX-NEXT: vaddps {{.*}}(%rip), %ymm0, %ymm0
; AVX-NEXT: vmulps {{.*}}(%rip), %ymm1, %ymm1
; AVX-NEXT: vmulps %ymm0, %ymm1, %ymm0
; AVX-NEXT: retq
;
%sqrt = tail call <8 x float> @llvm.sqrt.v8f32(<8 x float> %x)
%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>, %sqrt
ret <8 x float> %div
}
attributes #0 = { "unsafe-fp-math"="true" "reciprocal-estimates"="!sqrtf,!vec-sqrtf,!divf,!vec-divf" }
attributes #1 = { "unsafe-fp-math"="true" "reciprocal-estimates"="sqrt,vec-sqrt" }
attributes #2 = { nounwind readnone }
|
