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
|
// RUN: %clang_cc1 -fenable-matrix -triple x86_64-apple-darwin %s -emit-llvm -disable-llvm-passes -o - | FileCheck %s
#if !__has_extension(matrix_types)
#error Expected extension 'matrix_types' to be enabled
#endif
#if !__has_extension(matrix_types_scalar_division)
#error Expected extension 'matrix_types_scalar_division' to be enabled
#endif
typedef double dx5x5_t __attribute__((matrix_type(5, 5)));
// CHECK: %struct.Matrix = type { i8, [12 x float], float }
void load_store_double(dx5x5_t *a, dx5x5_t *b) {
// CHECK-LABEL: define{{.*}} void @load_store_double(
// CHECK-NEXT: entry:
// CHECK-NEXT: %a.addr = alloca ptr, align 8
// CHECK-NEXT: %b.addr = alloca ptr, align 8
// CHECK-NEXT: store ptr %a, ptr %a.addr, align 8
// CHECK-NEXT: store ptr %b, ptr %b.addr, align 8
// CHECK-NEXT: %0 = load ptr, ptr %b.addr, align 8
// CHECK-NEXT: %1 = load <25 x double>, ptr %0, align 8
// CHECK-NEXT: %2 = load ptr, ptr %a.addr, align 8
// CHECK-NEXT: store <25 x double> %1, ptr %2, align 8
// CHECK-NEXT: ret void
*a = *b;
}
typedef float fx3x4_t __attribute__((matrix_type(3, 4)));
void load_store_float(fx3x4_t *a, fx3x4_t *b) {
// CHECK-LABEL: define{{.*}} void @load_store_float(
// CHECK-NEXT: entry:
// CHECK-NEXT: %a.addr = alloca ptr, align 8
// CHECK-NEXT: %b.addr = alloca ptr, align 8
// CHECK-NEXT: store ptr %a, ptr %a.addr, align 8
// CHECK-NEXT: store ptr %b, ptr %b.addr, align 8
// CHECK-NEXT: %0 = load ptr, ptr %b.addr, align 8
// CHECK-NEXT: %1 = load <12 x float>, ptr %0, align 4
// CHECK-NEXT: %2 = load ptr, ptr %a.addr, align 8
// CHECK-NEXT: store <12 x float> %1, ptr %2, align 4
// CHECK-NEXT: ret void
*a = *b;
}
typedef int ix3x4_t __attribute__((matrix_type(4, 3)));
void load_store_int(ix3x4_t *a, ix3x4_t *b) {
// CHECK-LABEL: define{{.*}} void @load_store_int(
// CHECK-NEXT: entry:
// CHECK-NEXT: %a.addr = alloca ptr, align 8
// CHECK-NEXT: %b.addr = alloca ptr, align 8
// CHECK-NEXT: store ptr %a, ptr %a.addr, align 8
// CHECK-NEXT: store ptr %b, ptr %b.addr, align 8
// CHECK-NEXT: %0 = load ptr, ptr %b.addr, align 8
// CHECK-NEXT: %1 = load <12 x i32>, ptr %0, align 4
// CHECK-NEXT: %2 = load ptr, ptr %a.addr, align 8
// CHECK-NEXT: store <12 x i32> %1, ptr %2, align 4
// CHECK-NEXT: ret void
*a = *b;
}
typedef unsigned long long ullx3x4_t __attribute__((matrix_type(4, 3)));
void load_store_ull(ullx3x4_t *a, ullx3x4_t *b) {
// CHECK-LABEL: define{{.*}} void @load_store_ull(
// CHECK-NEXT: entry:
// CHECK-NEXT: %a.addr = alloca ptr, align 8
// CHECK-NEXT: %b.addr = alloca ptr, align 8
// CHECK-NEXT: store ptr %a, ptr %a.addr, align 8
// CHECK-NEXT: store ptr %b, ptr %b.addr, align 8
// CHECK-NEXT: %0 = load ptr, ptr %b.addr, align 8
// CHECK-NEXT: %1 = load <12 x i64>, ptr %0, align 8
// CHECK-NEXT: %2 = load ptr, ptr %a.addr, align 8
// CHECK-NEXT: store <12 x i64> %1, ptr %2, align 8
// CHECK-NEXT: ret void
*a = *b;
}
typedef __fp16 fp16x3x4_t __attribute__((matrix_type(4, 3)));
void load_store_fp16(fp16x3x4_t *a, fp16x3x4_t *b) {
// CHECK-LABEL: define{{.*}} void @load_store_fp16(
// CHECK-NEXT: entry:
// CHECK-NEXT: %a.addr = alloca ptr, align 8
// CHECK-NEXT: %b.addr = alloca ptr, align 8
// CHECK-NEXT: store ptr %a, ptr %a.addr, align 8
// CHECK-NEXT: store ptr %b, ptr %b.addr, align 8
// CHECK-NEXT: %0 = load ptr, ptr %b.addr, align 8
// CHECK-NEXT: %1 = load <12 x half>, ptr %0, align 2
// CHECK-NEXT: %2 = load ptr, ptr %a.addr, align 8
// CHECK-NEXT: store <12 x half> %1, ptr %2, align 2
// CHECK-NEXT: ret void
*a = *b;
}
typedef float fx3x3_t __attribute__((matrix_type(3, 3)));
void parameter_passing(fx3x3_t a, fx3x3_t *b) {
// CHECK-LABEL: define{{.*}} void @parameter_passing(
// CHECK-NEXT: entry:
// CHECK-NEXT: %a.addr = alloca [9 x float], align 4
// CHECK-NEXT: %b.addr = alloca ptr, align 8
// CHECK-NEXT: store <9 x float> %a, ptr %a.addr, align 4
// CHECK-NEXT: store ptr %b, ptr %b.addr, align 8
// CHECK-NEXT: %0 = load <9 x float>, ptr %a.addr, align 4
// CHECK-NEXT: %1 = load ptr, ptr %b.addr, align 8
// CHECK-NEXT: store <9 x float> %0, ptr %1, align 4
// CHECK-NEXT: ret void
*b = a;
}
fx3x3_t return_matrix(fx3x3_t *a) {
// CHECK-LABEL: define{{.*}} <9 x float> @return_matrix
// CHECK-NEXT: entry:
// CHECK-NEXT: %a.addr = alloca ptr, align 8
// CHECK-NEXT: store ptr %a, ptr %a.addr, align 8
// CHECK-NEXT: %0 = load ptr, ptr %a.addr, align 8
// CHECK-NEXT: %1 = load <9 x float>, ptr %0, align 4
// CHECK-NEXT: ret <9 x float> %1
return *a;
}
typedef struct {
char Tmp1;
fx3x4_t Data;
float Tmp2;
} Matrix;
void matrix_struct(Matrix *a, Matrix *b) {
// CHECK-LABEL: define{{.*}} void @matrix_struct(
// CHECK-NEXT: entry:
// CHECK-NEXT: %a.addr = alloca ptr, align 8
// CHECK-NEXT: %b.addr = alloca ptr, align 8
// CHECK-NEXT: store ptr %a, ptr %a.addr, align 8
// CHECK-NEXT: store ptr %b, ptr %b.addr, align 8
// CHECK-NEXT: %0 = load ptr, ptr %a.addr, align 8
// CHECK-NEXT: %Data = getelementptr inbounds %struct.Matrix, ptr %0, i32 0, i32 1
// CHECK-NEXT: %1 = load <12 x float>, ptr %Data, align 4
// CHECK-NEXT: %2 = load ptr, ptr %b.addr, align 8
// CHECK-NEXT: %Data1 = getelementptr inbounds %struct.Matrix, ptr %2, i32 0, i32 1
// CHECK-NEXT: store <12 x float> %1, ptr %Data1, align 4
// CHECK-NEXT: ret void
b->Data = a->Data;
}
typedef double dx4x4_t __attribute__((matrix_type(4, 4)));
void matrix_inline_asm_memory_readwrite(void) {
// CHECK-LABEL: define{{.*}} void @matrix_inline_asm_memory_readwrite()
// CHECK-NEXT: entry:
// CHECK-NEXT: [[ALLOCA:%.+]] = alloca [16 x double], align 8
// CHECK-NEXT: [[VAL:%.+]] = load <16 x double>, ptr [[ALLOCA]], align 8
// CHECK-NEXT: call void asm sideeffect "", "=*r|m,0,~{memory},~{dirflag},~{fpsr},~{flags}"(ptr elementtype(<16 x double>) [[ALLOCA]], <16 x double> [[VAL]])
// CHECK-NEXT: ret void
dx4x4_t m;
asm volatile(""
: "+r,m"(m)
:
: "memory");
}
|
