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
|
#define(VARIANTS)
[
{
"DECLS": ["NOT_INPLACE"]
},
{
"SHADER_SUFFIX": "inplace",
"DECLS": ["INPLACE"]
},
]
#end(VARIANTS)
#define(DECLS)
#decl(NOT_INPLACE)
fn update(src_offset: u32, dst_offset: u32, scale: f32) {
dst[dst_offset] = scale * src[src_offset];
}
@group(0) @binding(1)
var<storage, read_write> dst: array<f32>;
@group(0) @binding(2)
var<uniform> params: Params;
#enddecl(NOT_INPLACE)
#decl(INPLACE)
fn update(src_offset: u32, dst_offset: u32, scale: f32) {
src[dst_offset] = scale * src[src_offset];
}
@group(0) @binding(1)
var<uniform> params: Params;
#enddecl(INPLACE)
#end(DECLS)
#define(SHADER)
struct Params {
offset_src: u32, // in elements
offset_dst: u32, // in elements
// Strides (in elements)
stride_src1: u32,
stride_src2: u32,
stride_src3: u32,
stride_dst1: u32,
stride_dst2: u32,
stride_dst3: u32,
// Shape of src/dst
ne0: u32,
ne1: u32,
ne2: u32,
ne3: u32,
eps: f32
};
@group(0) @binding(0)
var<storage, read_write> src: array<f32>;
DECLS
override wg_size: u32;
var<workgroup> scratch: array<f32, wg_size>;
@compute @workgroup_size(wg_size)
fn main(@builtin(workgroup_id) wid: vec3<u32>,
@builtin(local_invocation_id) lid: vec3<u32>) {
// one thread per row
var i = wid.x;
let i3 = i / (params.ne2 * params.ne1);
i = i % (params.ne2 * params.ne1);
let i2 = i / params.ne1;
let i1 = i % params.ne1;
let i_src_row = params.offset_src + i3 * params.stride_src3 + i2 * params.stride_src2 + i1 * params.stride_src1;
let i_dst_row = params.offset_dst + i3 * params.stride_dst3 + i2 * params.stride_dst2 + i1 * params.stride_dst1;
let elems = (params.ne0 + wg_size - 1) / wg_size;
var sum = 0.0f;
var col = lid.x;
for (var j: u32 = 0; j < elems; j++) {
if (col >= params.ne0) {
break;
}
sum += pow(src[i_src_row + col], 2.0);
col += wg_size;
}
scratch[lid.x] = sum;
workgroupBarrier();
var offset = wg_size / 2;
while (offset > 0) {
if (lid.x < offset) {
scratch[lid.x] += scratch[lid.x + offset];
}
offset = offset / 2;
workgroupBarrier();
}
sum = scratch[0];
let scale = 1.0/sqrt(sum/f32(params.ne0) + params.eps);
col = lid.x;
for (var j: u32 = 0; j < elems; j++) {
if (col >= params.ne0) {
break;
}
update(i_src_row + col, i_dst_row + col, scale);
col += wg_size;
}
}
#end(SHADER)
|
