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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
|
; RUN: llc < %s -march=nvptx -mcpu=sm_20 -nvptx-prec-divf32=0 -nvptx-prec-sqrtf32=0 \
; RUN: | FileCheck %s
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
declare float @llvm.sqrt.f32(float)
declare double @llvm.sqrt.f64(double)
; -- reciprocal sqrt --
; CHECK-LABEL: test_rsqrt32
define float @test_rsqrt32(float %a) #0 {
; CHECK: rsqrt.approx.f32
%val = tail call float @llvm.sqrt.f32(float %a)
%ret = fdiv float 1.0, %val
ret float %ret
}
; CHECK-LABEL: test_rsqrt_ftz
define float @test_rsqrt_ftz(float %a) #0 #1 {
; CHECK: rsqrt.approx.ftz.f32
%val = tail call float @llvm.sqrt.f32(float %a)
%ret = fdiv float 1.0, %val
ret float %ret
}
; CHECK-LABEL: test_rsqrt64
define double @test_rsqrt64(double %a) #0 {
; CHECK: rsqrt.approx.f64
%val = tail call double @llvm.sqrt.f64(double %a)
%ret = fdiv double 1.0, %val
ret double %ret
}
; CHECK-LABEL: test_rsqrt64_ftz
define double @test_rsqrt64_ftz(double %a) #0 #1 {
; There's no rsqrt.approx.ftz.f64 instruction; we just use the non-ftz version.
; CHECK: rsqrt.approx.f64
%val = tail call double @llvm.sqrt.f64(double %a)
%ret = fdiv double 1.0, %val
ret double %ret
}
; -- sqrt --
; CHECK-LABEL: test_sqrt32
define float @test_sqrt32(float %a) #0 {
; CHECK: sqrt.rn.f32
%ret = tail call float @llvm.sqrt.f32(float %a)
ret float %ret
}
; CHECK-LABEL: test_sqrt32_ninf
define float @test_sqrt32_ninf(float %a) #0 {
; CHECK: sqrt.approx.f32
%ret = tail call ninf afn float @llvm.sqrt.f32(float %a)
ret float %ret
}
; CHECK-LABEL: test_sqrt_ftz
define float @test_sqrt_ftz(float %a) #0 #1 {
; CHECK: sqrt.rn.ftz.f32
%ret = tail call float @llvm.sqrt.f32(float %a)
ret float %ret
}
; CHECK-LABEL: test_sqrt_ftz_ninf
define float @test_sqrt_ftz_ninf(float %a) #0 #1 {
; CHECK: sqrt.approx.ftz.f32
%ret = tail call ninf afn float @llvm.sqrt.f32(float %a)
ret float %ret
}
; CHECK-LABEL: test_sqrt64
define double @test_sqrt64(double %a) #0 {
; CHECK: sqrt.rn.f64
%ret = tail call double @llvm.sqrt.f64(double %a)
ret double %ret
}
; CHECK-LABEL: test_sqrt64_ninf
define double @test_sqrt64_ninf(double %a) #0 {
; There's no sqrt.approx.f64 instruction; we emit
; reciprocal(rsqrt.approx.f64(x)). There's no non-ftz approximate reciprocal,
; so we just use the ftz version.
; CHECK: rsqrt.approx.f64
; CHECK: rcp.approx.ftz.f64
%ret = tail call ninf afn double @llvm.sqrt.f64(double %a)
ret double %ret
}
; CHECK-LABEL: test_sqrt64_ftz
define double @test_sqrt64_ftz(double %a) #0 #1 {
; CHECK: sqrt.rn.f64
%ret = tail call double @llvm.sqrt.f64(double %a)
ret double %ret
}
; CHECK-LABEL: test_sqrt64_ftz_ninf
define double @test_sqrt64_ftz_ninf(double %a) #0 #1 {
; There's no sqrt.approx.ftz.f64 instruction; we just use the non-ftz version.
; CHECK: rsqrt.approx.f64
; CHECK: rcp.approx.ftz.f64
%ret = tail call ninf afn double @llvm.sqrt.f64(double %a)
ret double %ret
}
; -- refined sqrt and rsqrt --
;
; The sqrt and rsqrt refinement algorithms both emit an rsqrt.approx, followed
; by some math.
; CHECK-LABEL: test_rsqrt32_refined
define float @test_rsqrt32_refined(float %a) #0 #2 {
; CHECK: rsqrt.approx.f32
%val = tail call float @llvm.sqrt.f32(float %a)
%ret = fdiv float 1.0, %val
ret float %ret
}
; CHECK-LABEL: test_sqrt32_refined
define float @test_sqrt32_refined(float %a) #0 #2 {
; CHECK: sqrt.rn.f32
%ret = tail call float @llvm.sqrt.f32(float %a)
ret float %ret
}
; CHECK-LABEL: test_sqrt32_refined_ninf
define float @test_sqrt32_refined_ninf(float %a) #0 #2 {
; CHECK: rsqrt.approx.f32
%ret = tail call ninf afn float @llvm.sqrt.f32(float %a)
ret float %ret
}
; CHECK-LABEL: test_rsqrt64_refined
define double @test_rsqrt64_refined(double %a) #0 #2 {
; CHECK: rsqrt.approx.f64
%val = tail call double @llvm.sqrt.f64(double %a)
%ret = fdiv double 1.0, %val
ret double %ret
}
; CHECK-LABEL: test_sqrt64_refined
define double @test_sqrt64_refined(double %a) #0 #2 {
; CHECK: sqrt.rn.f64
%ret = tail call double @llvm.sqrt.f64(double %a)
ret double %ret
}
; CHECK-LABEL: test_sqrt64_refined_ninf
define double @test_sqrt64_refined_ninf(double %a) #0 #2 {
; CHECK: rsqrt.approx.f64
%ret = tail call ninf afn double @llvm.sqrt.f64(double %a)
ret double %ret
}
; -- refined sqrt and rsqrt with ftz enabled --
; CHECK-LABEL: test_rsqrt32_refined_ftz
define float @test_rsqrt32_refined_ftz(float %a) #0 #1 #2 {
; CHECK: rsqrt.approx.ftz.f32
%val = tail call float @llvm.sqrt.f32(float %a)
%ret = fdiv float 1.0, %val
ret float %ret
}
; CHECK-LABEL: test_sqrt32_refined_ftz
define float @test_sqrt32_refined_ftz(float %a) #0 #1 #2 {
; CHECK: sqrt.rn.ftz.f32
%ret = tail call float @llvm.sqrt.f32(float %a)
ret float %ret
}
; CHECK-LABEL: test_sqrt32_refined_ftz_ninf
define float @test_sqrt32_refined_ftz_ninf(float %a) #0 #1 #2 {
; CHECK: rsqrt.approx.ftz.f32
%ret = tail call ninf afn float @llvm.sqrt.f32(float %a)
ret float %ret
}
; CHECK-LABEL: test_rsqrt64_refined_ftz
define double @test_rsqrt64_refined_ftz(double %a) #0 #1 #2 {
; There's no rsqrt.approx.ftz.f64, so we just use the non-ftz version.
; CHECK: rsqrt.approx.f64
%val = tail call double @llvm.sqrt.f64(double %a)
%ret = fdiv double 1.0, %val
ret double %ret
}
; CHECK-LABEL: test_sqrt64_refined_ftz
define double @test_sqrt64_refined_ftz(double %a) #0 #1 #2 {
; CHECK: sqrt.rn.f64
%ret = tail call double @llvm.sqrt.f64(double %a)
ret double %ret
}
; CHECK-LABEL: test_sqrt64_refined_ftz_ninf
define double @test_sqrt64_refined_ftz_ninf(double %a) #0 #1 #2 {
; CHECK: rsqrt.approx.f64
%ret = tail call ninf afn double @llvm.sqrt.f64(double %a)
ret double %ret
}
attributes #0 = { "unsafe-fp-math" = "true" }
attributes #1 = { "denormal-fp-math-f32" = "preserve-sign,preserve-sign" }
attributes #2 = { "reciprocal-estimates" = "rsqrtf:1,rsqrtd:1,sqrtf:1,sqrtd:1" }
|
