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
|
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 2
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -target-feature +fullbf16 -S -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -S -emit-llvm %s -o - | FileCheck -check-prefix=CHECK-NBF16 %s
// CHECK-LABEL: define dso_local void @_Z11test_scalarDF16bDF16b
// CHECK-SAME: (bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-NEXT: [[C:%.*]] = alloca bfloat, align 2
// CHECK-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NEXT: [[ADD:%.*]] = fadd bfloat [[TMP0]], [[TMP1]]
// CHECK-NEXT: store bfloat [[ADD]], ptr [[C]], align 2
// CHECK-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NEXT: [[TMP3:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NEXT: [[SUB:%.*]] = fsub bfloat [[TMP2]], [[TMP3]]
// CHECK-NEXT: store bfloat [[SUB]], ptr [[C]], align 2
// CHECK-NEXT: [[TMP4:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NEXT: [[TMP5:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NEXT: [[MUL:%.*]] = fmul bfloat [[TMP4]], [[TMP5]]
// CHECK-NEXT: store bfloat [[MUL]], ptr [[C]], align 2
// CHECK-NEXT: [[TMP6:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NEXT: [[TMP7:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NEXT: [[DIV:%.*]] = fdiv bfloat [[TMP6]], [[TMP7]]
// CHECK-NEXT: store bfloat [[DIV]], ptr [[C]], align 2
// CHECK-NEXT: ret void
//
// CHECK-NBF16-LABEL: define dso_local void @_Z11test_scalarDF16bDF16b
// CHECK-NBF16-SAME: (bfloat noundef [[A:%.*]], bfloat noundef [[B:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NBF16: [[A_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-NBF16-NEXT: [[B_ADDR:%.*]] = alloca bfloat, align 2
// CHECK-NBF16-NEXT: [[C:%.*]] = alloca bfloat, align 2
// CHECK-NBF16-NEXT: store bfloat [[A]], ptr [[A_ADDR]], align 2
// CHECK-NBF16-NEXT: store bfloat [[B]], ptr [[B_ADDR]], align 2
// CHECK-NBF16-NEXT: [[TMP0:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NBF16-NEXT: [[EXT:%.*]] = fpext bfloat [[TMP0]] to float
// CHECK-NBF16-NEXT: [[TMP1:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NBF16-NEXT: [[EXT1:%.*]] = fpext bfloat [[TMP1]] to float
// CHECK-NBF16-NEXT: [[ADD:%.*]] = fadd float [[EXT]], [[EXT1]]
// CHECK-NBF16-NEXT: [[UNPROMOTION:%.*]] = fptrunc float [[ADD]] to bfloat
// CHECK-NBF16-NEXT: store bfloat [[UNPROMOTION]], ptr [[C]], align 2
// CHECK-NBF16-NEXT: [[TMP2:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NBF16-NEXT: [[EXT2:%.*]] = fpext bfloat [[TMP2]] to float
// CHECK-NBF16-NEXT: [[TMP3:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NBF16-NEXT: [[EXT3:%.*]] = fpext bfloat [[TMP3]] to float
// CHECK-NBF16-NEXT: [[SUB:%.*]] = fsub float [[EXT2]], [[EXT3]]
// CHECK-NBF16-NEXT: [[UNPROMOTION4:%.*]] = fptrunc float [[SUB]] to bfloat
// CHECK-NBF16-NEXT: store bfloat [[UNPROMOTION4]], ptr [[C]], align 2
// CHECK-NBF16-NEXT: [[TMP4:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NBF16-NEXT: [[EXT5:%.*]] = fpext bfloat [[TMP4]] to float
// CHECK-NBF16-NEXT: [[TMP5:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NBF16-NEXT: [[EXT6:%.*]] = fpext bfloat [[TMP5]] to float
// CHECK-NBF16-NEXT: [[MUL:%.*]] = fmul float [[EXT5]], [[EXT6]]
// CHECK-NBF16-NEXT: [[UNPROMOTION7:%.*]] = fptrunc float [[MUL]] to bfloat
// CHECK-NBF16-NEXT: store bfloat [[UNPROMOTION7]], ptr [[C]], align 2
// CHECK-NBF16-NEXT: [[TMP6:%.*]] = load bfloat, ptr [[A_ADDR]], align 2
// CHECK-NBF16-NEXT: [[EXT8:%.*]] = fpext bfloat [[TMP6]] to float
// CHECK-NBF16-NEXT: [[TMP7:%.*]] = load bfloat, ptr [[B_ADDR]], align 2
// CHECK-NBF16-NEXT: [[EXT9:%.*]] = fpext bfloat [[TMP7]] to float
// CHECK-NBF16-NEXT: [[DIV:%.*]] = fdiv float [[EXT8]], [[EXT9]]
// CHECK-NBF16-NEXT: [[UNPROMOTION10:%.*]] = fptrunc float [[DIV]] to bfloat
// CHECK-NBF16-NEXT: store bfloat [[UNPROMOTION10]], ptr [[C]], align 2
// CHECK-NBF16-NEXT: ret void
//
void test_scalar(__bf16 a, __bf16 b) {
__bf16 c;
c = a + b;
c = a - b;
c = a * b;
c = a / b;
}
typedef __bf16 v8bfloat16 __attribute__((__vector_size__(16)));
// CHECK-LABEL: define dso_local void @_Z11test_vectorDv8_DF16bS_
// CHECK-SAME: (<8 x bfloat> noundef [[A:%.*]], <8 x bfloat> noundef [[B:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK: [[A_ADDR:%.*]] = alloca <8 x bfloat>, align 16
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca <8 x bfloat>, align 16
// CHECK-NEXT: [[C:%.*]] = alloca <8 x bfloat>, align 16
// CHECK-NEXT: store <8 x bfloat> [[A]], ptr [[A_ADDR]], align 16
// CHECK-NEXT: store <8 x bfloat> [[B]], ptr [[B_ADDR]], align 16
// CHECK-NEXT: [[TMP0:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NEXT: [[TMP1:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NEXT: [[ADD:%.*]] = fadd <8 x bfloat> [[TMP0]], [[TMP1]]
// CHECK-NEXT: store <8 x bfloat> [[ADD]], ptr [[C]], align 16
// CHECK-NEXT: [[TMP2:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NEXT: [[TMP3:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NEXT: [[SUB:%.*]] = fsub <8 x bfloat> [[TMP2]], [[TMP3]]
// CHECK-NEXT: store <8 x bfloat> [[SUB]], ptr [[C]], align 16
// CHECK-NEXT: [[TMP4:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NEXT: [[TMP5:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NEXT: [[MUL:%.*]] = fmul <8 x bfloat> [[TMP4]], [[TMP5]]
// CHECK-NEXT: store <8 x bfloat> [[MUL]], ptr [[C]], align 16
// CHECK-NEXT: [[TMP6:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NEXT: [[TMP7:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NEXT: [[DIV:%.*]] = fdiv <8 x bfloat> [[TMP6]], [[TMP7]]
// CHECK-NEXT: store <8 x bfloat> [[DIV]], ptr [[C]], align 16
// CHECK-NEXT: ret void
//
// CHECK-NBF16-LABEL: define dso_local void @_Z11test_vectorDv8_DF16bS_
// CHECK-NBF16-SAME: (<8 x bfloat> noundef [[A:%.*]], <8 x bfloat> noundef [[B:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NBF16: [[A_ADDR:%.*]] = alloca <8 x bfloat>, align 16
// CHECK-NBF16-NEXT: [[B_ADDR:%.*]] = alloca <8 x bfloat>, align 16
// CHECK-NBF16-NEXT: [[C:%.*]] = alloca <8 x bfloat>, align 16
// CHECK-NBF16-NEXT: store <8 x bfloat> [[A]], ptr [[A_ADDR]], align 16
// CHECK-NBF16-NEXT: store <8 x bfloat> [[B]], ptr [[B_ADDR]], align 16
// CHECK-NBF16-NEXT: [[TMP0:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NBF16-NEXT: [[EXT:%.*]] = fpext <8 x bfloat> [[TMP0]] to <8 x float>
// CHECK-NBF16-NEXT: [[TMP1:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NBF16-NEXT: [[EXT1:%.*]] = fpext <8 x bfloat> [[TMP1]] to <8 x float>
// CHECK-NBF16-NEXT: [[ADD:%.*]] = fadd <8 x float> [[EXT]], [[EXT1]]
// CHECK-NBF16-NEXT: [[UNPROMOTION:%.*]] = fptrunc <8 x float> [[ADD]] to <8 x bfloat>
// CHECK-NBF16-NEXT: store <8 x bfloat> [[UNPROMOTION]], ptr [[C]], align 16
// CHECK-NBF16-NEXT: [[TMP2:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NBF16-NEXT: [[EXT2:%.*]] = fpext <8 x bfloat> [[TMP2]] to <8 x float>
// CHECK-NBF16-NEXT: [[TMP3:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NBF16-NEXT: [[EXT3:%.*]] = fpext <8 x bfloat> [[TMP3]] to <8 x float>
// CHECK-NBF16-NEXT: [[SUB:%.*]] = fsub <8 x float> [[EXT2]], [[EXT3]]
// CHECK-NBF16-NEXT: [[UNPROMOTION4:%.*]] = fptrunc <8 x float> [[SUB]] to <8 x bfloat>
// CHECK-NBF16-NEXT: store <8 x bfloat> [[UNPROMOTION4]], ptr [[C]], align 16
// CHECK-NBF16-NEXT: [[TMP4:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NBF16-NEXT: [[EXT5:%.*]] = fpext <8 x bfloat> [[TMP4]] to <8 x float>
// CHECK-NBF16-NEXT: [[TMP5:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NBF16-NEXT: [[EXT6:%.*]] = fpext <8 x bfloat> [[TMP5]] to <8 x float>
// CHECK-NBF16-NEXT: [[MUL:%.*]] = fmul <8 x float> [[EXT5]], [[EXT6]]
// CHECK-NBF16-NEXT: [[UNPROMOTION7:%.*]] = fptrunc <8 x float> [[MUL]] to <8 x bfloat>
// CHECK-NBF16-NEXT: store <8 x bfloat> [[UNPROMOTION7]], ptr [[C]], align 16
// CHECK-NBF16-NEXT: [[TMP6:%.*]] = load <8 x bfloat>, ptr [[A_ADDR]], align 16
// CHECK-NBF16-NEXT: [[EXT8:%.*]] = fpext <8 x bfloat> [[TMP6]] to <8 x float>
// CHECK-NBF16-NEXT: [[TMP7:%.*]] = load <8 x bfloat>, ptr [[B_ADDR]], align 16
// CHECK-NBF16-NEXT: [[EXT9:%.*]] = fpext <8 x bfloat> [[TMP7]] to <8 x float>
// CHECK-NBF16-NEXT: [[DIV:%.*]] = fdiv <8 x float> [[EXT8]], [[EXT9]]
// CHECK-NBF16-NEXT: [[UNPROMOTION10:%.*]] = fptrunc <8 x float> [[DIV]] to <8 x bfloat>
// CHECK-NBF16-NEXT: store <8 x bfloat> [[UNPROMOTION10]], ptr [[C]], align 16
// CHECK-NBF16-NEXT: ret void
//
void test_vector(v8bfloat16 a, v8bfloat16 b) {
v8bfloat16 c;
c = a + b;
c = a - b;
c = a * b;
c = a / b;
}
|
