aboutsummaryrefslogtreecommitdiff
path: root/tests/test-opt.c
blob: d001615ee353bfca5a02d3648f986ed636fb5fc7 (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
200
201
202
203
204
205
#include "ggml.h"

#include <math.h>
#include <stdio.h>
#include <stdlib.h>
#include <assert.h>

#define MAX_NARGS 2


//
// logging
//
#define GGML_DEBUG 0
#if (GGML_DEBUG >= 1)
#define GGML_PRINT_DEBUG(...) printf(__VA_ARGS__)
#else
#define GGML_PRINT_DEBUG(...)
#endif

#if (GGML_DEBUG >= 5)
#define GGML_PRINT_DEBUG_5(...) printf(__VA_ARGS__)
#else
#define GGML_PRINT_DEBUG_5(...)
#endif

#if (GGML_DEBUG >= 10)
#define GGML_PRINT_DEBUG_10(...) printf(__VA_ARGS__)
#else
#define GGML_PRINT_DEBUG_10(...)
#endif

#define GGML_PRINT(...) printf(__VA_ARGS__)


float frand() {
    return (float)rand()/(float)RAND_MAX;
}

int irand(int n) {
    return rand()%n;
}

void get_random_dims(int64_t * dims, int ndims) {
    dims[0] = dims[1] = dims[2] = dims[3] = 1;

    for (int i = 0; i < ndims; i++) {
        dims[i] = 1 + irand(4);
    }
}

void get_random_dims_minmax(int64_t * dims, int ndims, int min, int max) {
    dims[0] = dims[1] = dims[2] = dims[3] = 1;

    for (int i = 0; i < ndims; i++) {
        dims[i] = min + irand(max-min);
    }
}


struct ggml_tensor * get_random_tensor(
        struct ggml_context * ctx0,
        int ndims,
        int64_t ne[],
        float fmin,
        float fmax) {
    struct ggml_tensor * result = ggml_new_tensor(ctx0, GGML_TYPE_F32, ndims, ne);

    switch (ndims) {
        case 1:
            for (int i0 = 0; i0 < ne[0]; i0++) {
                ((float *)result->data)[i0] = frand()*(fmax - fmin) + fmin;
            }
            break;
        case 2:
            for (int i1 = 0; i1 < ne[1]; i1++) {
                for (int i0 = 0; i0 < ne[0]; i0++) {
                    ((float *)result->data)[i1*ne[0] + i0] = frand()*(fmax - fmin) + fmin;
                }
            }
            break;
        case 3:
            for (int i2 = 0; i2 < ne[2]; i2++) {
                for (int i1 = 0; i1 < ne[1]; i1++) {
                    for (int i0 = 0; i0 < ne[0]; i0++) {
                        ((float *)result->data)[i2*ne[1]*ne[0] + i1*ne[0] + i0] = frand()*(fmax - fmin) + fmin;
                    }
                }
            }
            break;
        case 4:
            for (int i3 = 0; i3 < ne[3]; i3++) {
                for (int i2 = 0; i2 < ne[2]; i2++) {
                    for (int i1 = 0; i1 < ne[1]; i1++) {
                        for (int i0 = 0; i0 < ne[0]; i0++) {
                            ((float *)result->data)[i3*ne[2]*ne[1]*ne[0] + i2*ne[1]*ne[0] + i1*ne[0] + i0] = frand()*(fmax - fmin) + fmin;
                        }
                    }
                }
            }
            break;
        default:
            assert(false);
    };

    return result;
}

float get_element(const struct ggml_tensor * t, int idx) {
    return ((float *)t->data)[idx];
}

void set_element(struct ggml_tensor * t, int idx, float value) {
    ((float *)t->data)[idx] = value;
}

int main(int argc, const char ** argv) {
    struct ggml_init_params params = {
        .mem_size   = 1024*1024*1024,
        .mem_buffer = NULL,
        .no_alloc   = false,
    };
    struct ggml_context * ctx = ggml_init(params);

    int64_t ne1[4] = {4, 1024, 1, 1};
    int64_t ne2[4] = {4, 2048, 1, 1};;
    int64_t ne3[4] = {1024, 2048, 1, 1};

    struct ggml_tensor * a = get_random_tensor(ctx, 2, ne1, -1, +1);
    struct ggml_tensor * b = get_random_tensor(ctx, 2, ne2, -1, +1);
    ggml_set_param(ctx, a);
    ggml_set_param(ctx, b);

    struct ggml_tensor * c = get_random_tensor(ctx, 2, ne3, -1, +1);

    struct ggml_tensor * ab = ggml_mul_mat(ctx, a, b);
    struct ggml_tensor * d  = ggml_sub(ctx, c, ab);
    struct ggml_tensor * e  = ggml_sum(ctx, ggml_sqr(ctx, d));


    struct ggml_cgraph ge = ggml_build_forward(e);
    ggml_graph_reset  (&ge);
    ggml_graph_compute(ctx, &ge);
    const float fe = ggml_get_f32_1d(e, 0);
    printf("%s: e = %.4f\n", __func__, fe);

    struct ggml_opt_params opt_params = ggml_opt_default_params(GGML_OPT_ADAM);

    ggml_opt(ctx, opt_params, e);

    ggml_graph_reset  (&ge);
    ggml_graph_compute(ctx, &ge);
    const float fe_opt = ggml_get_f32_1d(e, 0);
    printf("%s: original  e = %.4f\n", __func__, fe);
    printf("%s: optimized e = %.4f\n", __func__, fe_opt);

    const bool success = (fe_opt <= fe);
    assert(success);

    ggml_free(ctx);
    return success ? 0 : -1;
}
// int64_t ne1[4] = {4, 128, 1, 1};
// int64_t ne2[4] = {4, 256, 1, 1};;
// int64_t ne3[4] = {128, 256, 1, 1};
// main: original  e = 25890.9375
// main: optimized e = 10094.7031

// int64_t ne1[4] = {8, 128, 1, 1};
// int64_t ne2[4] = {8, 256, 1, 1};;
// int64_t ne3[4] = {128, 256, 1, 1};
// main: original  e = 39429.5078
// main: optimized e = 9275.8936

// int64_t ne1[4] = {16, 128, 1, 1};
// int64_t ne2[4] = {16, 256, 1, 1};;
// int64_t ne3[4] = {128, 256, 1, 1};
// main: original  e = 68371.1328
// main: optimized e = 7854.4502


// int64_t ne1[4] = {32, 128, 1, 1};
// int64_t ne2[4] = {32, 256, 1, 1};;
// int64_t ne3[4] = {128, 256, 1, 1};
// main: original  e = 126061.1953
// main: optimized e = 5451.0166

// int64_t ne1[4] = {4, 1024, 1, 1};
// int64_t ne2[4] = {4, 2048, 1, 1};;
// int64_t ne3[4] = {1024, 2048, 1, 1};
// main: original  e = 1620817.8750
// main: optimized e = 698387.6875

// another run on M1
// int64_t ne1[4] = {4, 1024, 1, 1};
// int64_t ne2[4] = {4, 2048, 1, 1};;
// int64_t ne3[4] = {1024, 2048, 1, 1};
// main: original  e = 1629595.6250
// main: optimized e = 698169.1250

// int64_t ne1[4] = {32, 1024, 1, 1};
// int64_t ne2[4] = {32, 2048, 1, 1};;
// int64_t ne3[4] = {1024, 2048, 1, 1};
// main: original  e = 8146770.5000
// main: optimized e = 651119.1250