aboutsummaryrefslogtreecommitdiff
path: root/llvm/test/CodeGen/AArch64/fp16_fast_math.ll
blob: 7d9654d1ff8c0aabcbe43f48c63cf3ae105633fd (plain)
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
; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=aarch64 -mattr=-fullfp16 -stop-after=finalize-isel | FileCheck %s --check-prefixes=CHECK-CVT
; RUN: llc < %s -mtriple=aarch64 -mattr=+fullfp16 -stop-after=finalize-isel | FileCheck %s --check-prefixes=CHECK-FP16

; Check that the output instructions have the same fast math flags as the input
; fadd, even when fadd is promoted to float type.

define half @normal_fadd(half %x, half %y) {
  ; CHECK-CVT-LABEL: name: normal_fadd
  ; CHECK-CVT: bb.0.entry:
  ; CHECK-CVT-NEXT:   liveins: $h0, $h1
  ; CHECK-CVT-NEXT: {{  $}}
  ; CHECK-CVT-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-CVT-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-CVT-NEXT:   [[FCVTSHr:%[0-9]+]]:fpr32 = nofpexcept FCVTSHr [[COPY]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr1:%[0-9]+]]:fpr32 = nofpexcept FCVTSHr [[COPY1]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FADDSrr:%[0-9]+]]:fpr32 = nofpexcept FADDSrr killed [[FCVTSHr1]], killed [[FCVTSHr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTHSr:%[0-9]+]]:fpr16 = nofpexcept FCVTHSr killed [[FADDSrr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   $h0 = COPY [[FCVTHSr]]
  ; CHECK-CVT-NEXT:   RET_ReallyLR implicit $h0
  ;
  ; CHECK-FP16-LABEL: name: normal_fadd
  ; CHECK-FP16: bb.0.entry:
  ; CHECK-FP16-NEXT:   liveins: $h0, $h1
  ; CHECK-FP16-NEXT: {{  $}}
  ; CHECK-FP16-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-FP16-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-FP16-NEXT:   [[FADDHrr:%[0-9]+]]:fpr16 = nofpexcept FADDHrr [[COPY1]], [[COPY]], implicit $fpcr
  ; CHECK-FP16-NEXT:   $h0 = COPY [[FADDHrr]]
  ; CHECK-FP16-NEXT:   RET_ReallyLR implicit $h0
entry:
  %add = fadd half %x, %y
  ret half %add
}

define half @fast_fadd(half %x, half %y) {
  ; CHECK-CVT-LABEL: name: fast_fadd
  ; CHECK-CVT: bb.0.entry:
  ; CHECK-CVT-NEXT:   liveins: $h0, $h1
  ; CHECK-CVT-NEXT: {{  $}}
  ; CHECK-CVT-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-CVT-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-CVT-NEXT:   [[FCVTSHr:%[0-9]+]]:fpr32 = nnan ninf nsz arcp contract afn reassoc nofpexcept FCVTSHr [[COPY]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr1:%[0-9]+]]:fpr32 = nnan ninf nsz arcp contract afn reassoc nofpexcept FCVTSHr [[COPY1]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FADDSrr:%[0-9]+]]:fpr32 = nnan ninf nsz arcp contract afn reassoc nofpexcept FADDSrr killed [[FCVTSHr1]], killed [[FCVTSHr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTHSr:%[0-9]+]]:fpr16 = nnan ninf nsz arcp contract afn reassoc nofpexcept FCVTHSr killed [[FADDSrr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   $h0 = COPY [[FCVTHSr]]
  ; CHECK-CVT-NEXT:   RET_ReallyLR implicit $h0
  ;
  ; CHECK-FP16-LABEL: name: fast_fadd
  ; CHECK-FP16: bb.0.entry:
  ; CHECK-FP16-NEXT:   liveins: $h0, $h1
  ; CHECK-FP16-NEXT: {{  $}}
  ; CHECK-FP16-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-FP16-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-FP16-NEXT:   [[FADDHrr:%[0-9]+]]:fpr16 = nnan ninf nsz arcp contract afn reassoc nofpexcept FADDHrr [[COPY1]], [[COPY]], implicit $fpcr
  ; CHECK-FP16-NEXT:   $h0 = COPY [[FADDHrr]]
  ; CHECK-FP16-NEXT:   RET_ReallyLR implicit $h0
entry:
  %add = fadd fast half %x, %y
  ret half %add
}

define half @ninf_fadd(half %x, half %y) {
  ; CHECK-CVT-LABEL: name: ninf_fadd
  ; CHECK-CVT: bb.0.entry:
  ; CHECK-CVT-NEXT:   liveins: $h0, $h1
  ; CHECK-CVT-NEXT: {{  $}}
  ; CHECK-CVT-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-CVT-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-CVT-NEXT:   [[FCVTSHr:%[0-9]+]]:fpr32 = ninf nofpexcept FCVTSHr [[COPY]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr1:%[0-9]+]]:fpr32 = ninf nofpexcept FCVTSHr [[COPY1]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FADDSrr:%[0-9]+]]:fpr32 = ninf nofpexcept FADDSrr killed [[FCVTSHr1]], killed [[FCVTSHr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTHSr:%[0-9]+]]:fpr16 = ninf nofpexcept FCVTHSr killed [[FADDSrr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   $h0 = COPY [[FCVTHSr]]
  ; CHECK-CVT-NEXT:   RET_ReallyLR implicit $h0
  ;
  ; CHECK-FP16-LABEL: name: ninf_fadd
  ; CHECK-FP16: bb.0.entry:
  ; CHECK-FP16-NEXT:   liveins: $h0, $h1
  ; CHECK-FP16-NEXT: {{  $}}
  ; CHECK-FP16-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-FP16-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-FP16-NEXT:   [[FADDHrr:%[0-9]+]]:fpr16 = ninf nofpexcept FADDHrr [[COPY1]], [[COPY]], implicit $fpcr
  ; CHECK-FP16-NEXT:   $h0 = COPY [[FADDHrr]]
  ; CHECK-FP16-NEXT:   RET_ReallyLR implicit $h0
entry:
  %add = fadd ninf half %x, %y
  ret half %add
}

; Check that when we have the right fast math flags the converts in between the
; two fadds are removed.

define half @normal_fadd_sequence(half %x, half %y, half %z) {
  ; CHECK-CVT-LABEL: name: normal_fadd_sequence
  ; CHECK-CVT: bb.0.entry:
  ; CHECK-CVT-NEXT:   liveins: $h0, $h1, $h2
  ; CHECK-CVT-NEXT: {{  $}}
  ; CHECK-CVT-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h2
  ; CHECK-CVT-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-CVT-NEXT:   [[COPY2:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-CVT-NEXT:   [[FCVTSHr:%[0-9]+]]:fpr32 = nofpexcept FCVTSHr [[COPY1]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr1:%[0-9]+]]:fpr32 = nofpexcept FCVTSHr [[COPY2]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FADDSrr:%[0-9]+]]:fpr32 = nofpexcept FADDSrr killed [[FCVTSHr1]], killed [[FCVTSHr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTHSr:%[0-9]+]]:fpr16 = nofpexcept FCVTHSr killed [[FADDSrr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr2:%[0-9]+]]:fpr32 = nofpexcept FCVTSHr killed [[FCVTHSr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr3:%[0-9]+]]:fpr32 = nofpexcept FCVTSHr [[COPY]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FADDSrr1:%[0-9]+]]:fpr32 = nofpexcept FADDSrr killed [[FCVTSHr2]], killed [[FCVTSHr3]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTHSr1:%[0-9]+]]:fpr16 = nofpexcept FCVTHSr killed [[FADDSrr1]], implicit $fpcr
  ; CHECK-CVT-NEXT:   $h0 = COPY [[FCVTHSr1]]
  ; CHECK-CVT-NEXT:   RET_ReallyLR implicit $h0
  ;
  ; CHECK-FP16-LABEL: name: normal_fadd_sequence
  ; CHECK-FP16: bb.0.entry:
  ; CHECK-FP16-NEXT:   liveins: $h0, $h1, $h2
  ; CHECK-FP16-NEXT: {{  $}}
  ; CHECK-FP16-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h2
  ; CHECK-FP16-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-FP16-NEXT:   [[COPY2:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-FP16-NEXT:   [[FADDHrr:%[0-9]+]]:fpr16 = nofpexcept FADDHrr [[COPY2]], [[COPY1]], implicit $fpcr
  ; CHECK-FP16-NEXT:   [[FADDHrr1:%[0-9]+]]:fpr16 = nofpexcept FADDHrr killed [[FADDHrr]], [[COPY]], implicit $fpcr
  ; CHECK-FP16-NEXT:   $h0 = COPY [[FADDHrr1]]
  ; CHECK-FP16-NEXT:   RET_ReallyLR implicit $h0
entry:
  %add1 = fadd half %x, %y
  %add2 = fadd half %add1, %z
  ret half %add2
}

define half @nnan_ninf_contract_fadd_sequence(half %x, half %y, half %z) {
  ; CHECK-CVT-LABEL: name: nnan_ninf_contract_fadd_sequence
  ; CHECK-CVT: bb.0.entry:
  ; CHECK-CVT-NEXT:   liveins: $h0, $h1, $h2
  ; CHECK-CVT-NEXT: {{  $}}
  ; CHECK-CVT-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h2
  ; CHECK-CVT-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-CVT-NEXT:   [[COPY2:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-CVT-NEXT:   [[FCVTSHr:%[0-9]+]]:fpr32 = nnan ninf contract nofpexcept FCVTSHr [[COPY1]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr1:%[0-9]+]]:fpr32 = nnan ninf contract nofpexcept FCVTSHr [[COPY2]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FADDSrr:%[0-9]+]]:fpr32 = nnan ninf contract nofpexcept FADDSrr killed [[FCVTSHr1]], killed [[FCVTSHr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr2:%[0-9]+]]:fpr32 = nnan ninf contract nofpexcept FCVTSHr [[COPY]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FADDSrr1:%[0-9]+]]:fpr32 = nnan ninf contract nofpexcept FADDSrr killed [[FADDSrr]], killed [[FCVTSHr2]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTHSr:%[0-9]+]]:fpr16 = nnan ninf contract nofpexcept FCVTHSr killed [[FADDSrr1]], implicit $fpcr
  ; CHECK-CVT-NEXT:   $h0 = COPY [[FCVTHSr]]
  ; CHECK-CVT-NEXT:   RET_ReallyLR implicit $h0
  ;
  ; CHECK-FP16-LABEL: name: nnan_ninf_contract_fadd_sequence
  ; CHECK-FP16: bb.0.entry:
  ; CHECK-FP16-NEXT:   liveins: $h0, $h1, $h2
  ; CHECK-FP16-NEXT: {{  $}}
  ; CHECK-FP16-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h2
  ; CHECK-FP16-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-FP16-NEXT:   [[COPY2:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-FP16-NEXT:   [[FADDHrr:%[0-9]+]]:fpr16 = nnan ninf contract nofpexcept FADDHrr [[COPY2]], [[COPY1]], implicit $fpcr
  ; CHECK-FP16-NEXT:   [[FADDHrr1:%[0-9]+]]:fpr16 = nnan ninf contract nofpexcept FADDHrr killed [[FADDHrr]], [[COPY]], implicit $fpcr
  ; CHECK-FP16-NEXT:   $h0 = COPY [[FADDHrr1]]
  ; CHECK-FP16-NEXT:   RET_ReallyLR implicit $h0
entry:
  %add1 = fadd nnan ninf contract half %x, %y
  %add2 = fadd nnan ninf contract half %add1, %z
  ret half %add2
}

define half @ninf_fadd_sequence(half %x, half %y, half %z) {
  ; CHECK-CVT-LABEL: name: ninf_fadd_sequence
  ; CHECK-CVT: bb.0.entry:
  ; CHECK-CVT-NEXT:   liveins: $h0, $h1, $h2
  ; CHECK-CVT-NEXT: {{  $}}
  ; CHECK-CVT-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h2
  ; CHECK-CVT-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-CVT-NEXT:   [[COPY2:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-CVT-NEXT:   [[FCVTSHr:%[0-9]+]]:fpr32 = ninf nofpexcept FCVTSHr [[COPY1]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr1:%[0-9]+]]:fpr32 = ninf nofpexcept FCVTSHr [[COPY2]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FADDSrr:%[0-9]+]]:fpr32 = ninf nofpexcept FADDSrr killed [[FCVTSHr1]], killed [[FCVTSHr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTHSr:%[0-9]+]]:fpr16 = ninf nofpexcept FCVTHSr killed [[FADDSrr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr2:%[0-9]+]]:fpr32 = ninf nofpexcept FCVTSHr killed [[FCVTHSr]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTSHr3:%[0-9]+]]:fpr32 = ninf nofpexcept FCVTSHr [[COPY]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FADDSrr1:%[0-9]+]]:fpr32 = ninf nofpexcept FADDSrr killed [[FCVTSHr2]], killed [[FCVTSHr3]], implicit $fpcr
  ; CHECK-CVT-NEXT:   [[FCVTHSr1:%[0-9]+]]:fpr16 = ninf nofpexcept FCVTHSr killed [[FADDSrr1]], implicit $fpcr
  ; CHECK-CVT-NEXT:   $h0 = COPY [[FCVTHSr1]]
  ; CHECK-CVT-NEXT:   RET_ReallyLR implicit $h0
  ;
  ; CHECK-FP16-LABEL: name: ninf_fadd_sequence
  ; CHECK-FP16: bb.0.entry:
  ; CHECK-FP16-NEXT:   liveins: $h0, $h1, $h2
  ; CHECK-FP16-NEXT: {{  $}}
  ; CHECK-FP16-NEXT:   [[COPY:%[0-9]+]]:fpr16 = COPY $h2
  ; CHECK-FP16-NEXT:   [[COPY1:%[0-9]+]]:fpr16 = COPY $h1
  ; CHECK-FP16-NEXT:   [[COPY2:%[0-9]+]]:fpr16 = COPY $h0
  ; CHECK-FP16-NEXT:   [[FADDHrr:%[0-9]+]]:fpr16 = ninf nofpexcept FADDHrr [[COPY2]], [[COPY1]], implicit $fpcr
  ; CHECK-FP16-NEXT:   [[FADDHrr1:%[0-9]+]]:fpr16 = ninf nofpexcept FADDHrr killed [[FADDHrr]], [[COPY]], implicit $fpcr
  ; CHECK-FP16-NEXT:   $h0 = COPY [[FADDHrr1]]
  ; CHECK-FP16-NEXT:   RET_ReallyLR implicit $h0
entry:
  %add1 = fadd ninf half %x, %y
  %add2 = fadd ninf half %add1, %z
  ret half %add2
}