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
207
208
209
210
211
212
213
214
215
216
217
218
219
| ; Verify that strict FP operations are not rescheduled
;
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z13 | FileCheck %s
declare float @llvm.experimental.constrained.sqrt.f32(float, metadata, metadata)
declare float @llvm.sqrt.f32(float)
declare void @llvm.s390.sfpc(i32)
; The basic assumption of all following tests is that on z13, we never
; want to see two square root instructions directly in a row, so the
; post-RA scheduler will always schedule something else in between
; whenever possible.
; We can move any FP operation across a (normal) store.
define void @f1(float %f1, float %f2, float *%ptr1, float *%ptr2) {
; CHECK-LABEL: f1:
; CHECK: sqebr
; CHECK: ste
; CHECK: sqebr
; CHECK: ste
; CHECK: br %r14
%sqrt1 = call float @llvm.sqrt.f32(float %f1)
%sqrt2 = call float @llvm.sqrt.f32(float %f2)
store float %sqrt1, float *%ptr1
store float %sqrt2, float *%ptr2
ret void
}
define void @f2(float %f1, float %f2, float *%ptr1, float *%ptr2) #0 {
; CHECK-LABEL: f2:
; CHECK: sqebr
; CHECK: ste
; CHECK: sqebr
; CHECK: ste
; CHECK: br %r14
%sqrt1 = call float @llvm.experimental.constrained.sqrt.f32(
float %f1,
metadata !"round.dynamic",
metadata !"fpexcept.ignore") #0
%sqrt2 = call float @llvm.experimental.constrained.sqrt.f32(
float %f2,
metadata !"round.dynamic",
metadata !"fpexcept.ignore") #0
store float %sqrt1, float *%ptr1
store float %sqrt2, float *%ptr2
ret void
}
define void @f3(float %f1, float %f2, float *%ptr1, float *%ptr2) #0 {
; CHECK-LABEL: f3:
; CHECK: sqebr
; CHECK: ste
; CHECK: sqebr
; CHECK: ste
; CHECK: br %r14
%sqrt1 = call float @llvm.experimental.constrained.sqrt.f32(
float %f1,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
%sqrt2 = call float @llvm.experimental.constrained.sqrt.f32(
float %f2,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
store float %sqrt1, float *%ptr1
store float %sqrt2, float *%ptr2
ret void
}
; We can move a non-strict FP operation or a fpexcept.ignore
; operation even across a volatile store, but not a fpexcept.strict
; operation.
define void @f4(float %f1, float %f2, float *%ptr1, float *%ptr2) {
; CHECK-LABEL: f4:
; CHECK: sqebr
; CHECK: ste
; CHECK: sqebr
; CHECK: ste
; CHECK: br %r14
%sqrt1 = call float @llvm.sqrt.f32(float %f1)
%sqrt2 = call float @llvm.sqrt.f32(float %f2)
store volatile float %sqrt1, float *%ptr1
store volatile float %sqrt2, float *%ptr2
ret void
}
define void @f5(float %f1, float %f2, float *%ptr1, float *%ptr2) #0 {
; CHECK-LABEL: f5:
; CHECK: sqebr
; CHECK: ste
; CHECK: sqebr
; CHECK: ste
; CHECK: br %r14
%sqrt1 = call float @llvm.experimental.constrained.sqrt.f32(
float %f1,
metadata !"round.dynamic",
metadata !"fpexcept.ignore") #0
%sqrt2 = call float @llvm.experimental.constrained.sqrt.f32(
float %f2,
metadata !"round.dynamic",
metadata !"fpexcept.ignore") #0
store volatile float %sqrt1, float *%ptr1
store volatile float %sqrt2, float *%ptr2
ret void
}
define void @f6(float %f1, float %f2, float *%ptr1, float *%ptr2) #0 {
; CHECK-LABEL: f6:
; CHECK: sqebr
; CHECK: sqebr
; CHECK: ste
; CHECK: ste
; CHECK: br %r14
%sqrt1 = call float @llvm.experimental.constrained.sqrt.f32(
float %f1,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
%sqrt2 = call float @llvm.experimental.constrained.sqrt.f32(
float %f2,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
store volatile float %sqrt1, float *%ptr1
store volatile float %sqrt2, float *%ptr2
ret void
}
; No variant of FP operations can be scheduled across a SPFC.
define void @f7(float %f1, float %f2, float *%ptr1, float *%ptr2) {
; CHECK-LABEL: f7:
; CHECK: sqebr
; CHECK: sqebr
; CHECK: ste
; CHECK: ste
; CHECK: br %r14
%sqrt1 = call float @llvm.sqrt.f32(float %f1)
%sqrt2 = call float @llvm.sqrt.f32(float %f2)
call void @llvm.s390.sfpc(i32 0)
store float %sqrt1, float *%ptr1
store float %sqrt2, float *%ptr2
ret void
}
define void @f8(float %f1, float %f2, float *%ptr1, float *%ptr2) #0 {
; CHECK-LABEL: f8:
; CHECK: sqebr
; CHECK: sqebr
; CHECK: ste
; CHECK: ste
; CHECK: br %r14
%sqrt1 = call float @llvm.experimental.constrained.sqrt.f32(
float %f1,
metadata !"round.dynamic",
metadata !"fpexcept.ignore") #0
%sqrt2 = call float @llvm.experimental.constrained.sqrt.f32(
float %f2,
metadata !"round.dynamic",
metadata !"fpexcept.ignore") #0
call void @llvm.s390.sfpc(i32 0) #0
store float %sqrt1, float *%ptr1
store float %sqrt2, float *%ptr2
ret void
}
define void @f9(float %f1, float %f2, float *%ptr1, float *%ptr2) #0 {
; CHECK-LABEL: f9:
; CHECK: sqebr
; CHECK: sqebr
; CHECK: ste
; CHECK: ste
; CHECK: br %r14
%sqrt1 = call float @llvm.experimental.constrained.sqrt.f32(
float %f1,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
%sqrt2 = call float @llvm.experimental.constrained.sqrt.f32(
float %f2,
metadata !"round.dynamic",
metadata !"fpexcept.strict") #0
call void @llvm.s390.sfpc(i32 0) #0
store float %sqrt1, float *%ptr1
store float %sqrt2, float *%ptr2
ret void
}
attributes #0 = { strictfp }
|