llama-cpp-sys-4 0.2.46

Low Level Bindings to llama.cpp
Documentation 
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

#pragma clang diagnostic ignored "-Wunused-variable"
#pragma clang diagnostic ignored "-Wunused-function"
#pragma clang diagnostic ignored "-Wunused-but-set-variable"

#include <HAP_farf.h>
#include <HAP_perf.h>

#include <math.h>
#include <string.h>

#define GGML_COMMON_DECL_C
#include "ggml-common.h"
#include "htp-ctx.h"
#include "htp-ops.h"
#include "htp-ops.h"
#include "hvx-utils.h"

struct get_rows_context {
    struct htp_ops_context * octx;
    uint32_t src1_nrows_per_thread;
    struct fastdiv_values get_rows_div_ne10;
    struct fastdiv_values get_rows_div_ne10_ne11;
};

#define get_rows_preamble \
    const uint32_t ne00 = octx->src[0]->ne[0]; \
    const uint32_t ne01 = octx->src[0]->ne[1]; \
    const uint32_t ne02 = octx->src[0]->ne[2]; \
    const uint32_t ne03 = octx->src[0]->ne[3]; \
                                               \
    const uint32_t ne10 = octx->src[1]->ne[0]; \
    const uint32_t ne11 = octx->src[1]->ne[1]; \
    const uint32_t ne12 = octx->src[1]->ne[2]; \
    const uint32_t ne13 = octx->src[1]->ne[3]; \
                                               \
    const uint32_t ne0 = octx->dst->ne[0];     \
    const uint32_t ne1 = octx->dst->ne[1];     \
    const uint32_t ne2 = octx->dst->ne[2];     \
    const uint32_t ne3 = octx->dst->ne[3];     \
                                               \
    const uint32_t nb01 = octx->src[0]->nb[1]; \
    const uint32_t nb02 = octx->src[0]->nb[2]; \
    const uint32_t nb03 = octx->src[0]->nb[3]; \
                                               \
    const uint32_t nb10 = octx->src[1]->nb[0]; \
    const uint32_t nb11 = octx->src[1]->nb[1]; \
    const uint32_t nb12 = octx->src[1]->nb[2]; \
                                               \
    const uint32_t nb1 = octx->dst->nb[1];     \
    const uint32_t nb2 = octx->dst->nb[2];     \
    const uint32_t nb3 = octx->dst->nb[3];     \
                                               \
    const uint32_t nr = ne10 * ne11 * ne12;

static void get_rows_thread_f32_f32(unsigned int nth, unsigned int ith, void *data) {
    struct get_rows_context * grctx = (struct get_rows_context *)data;
    struct htp_ops_context * octx = grctx->octx;
    get_rows_preamble;

    uint64_t qt = HAP_perf_get_qtimer_count();

    // parallelize by src1 elements (which correspond to dst rows)
    const uint32_t dr  = grctx->src1_nrows_per_thread;
    const uint32_t ir0 = dr * ith;
    const uint32_t ir1 = (ir0 + dr < nr) ? (ir0 + dr) : nr;

    const bool is_i32 = (octx->src[1]->type == HTP_TYPE_I32);

    for (uint32_t i = ir0; i < ir1; ++i) {
        const uint32_t i12 = fastdiv(i, &grctx->get_rows_div_ne10_ne11);
        const uint32_t rem = i - i12 * ne11 * ne10;
        const uint32_t i11 = fastdiv(rem, &grctx->get_rows_div_ne10);
        const uint32_t i10 = rem - i11 * ne10;

        const uintptr_t src1_addr = octx->src[1]->data + i10*nb10 + i11*nb11 + i12*nb12;

        uint32_t i01 = is_i32 ? *(int32_t *)src1_addr : *(int64_t *)src1_addr;

        if (i01 >= ne01) {
            // invalid index, skip for now to avoid crash
            continue;
        }

        const uintptr_t src0_ptr = octx->src[0]->data + i01*nb01 + i11*nb02 + i12*nb03;
        const uintptr_t dst_ptr  = octx->dst->data    + i10*nb1  + i11*nb2  + i12*nb3;
        hvx_copy_f32_uu((uint8_t *)dst_ptr, (const uint8_t *)src0_ptr, ne00);
    }

    qt = HAP_perf_qtimer_count_to_us(HAP_perf_get_qtimer_count() - qt);
    FARF(HIGH, "get-rows-f32-f32 %d/%d: %ux%ux%ux%u (%u:%u) x %ux%ux%ux%u -> %ux%ux%ux%u usec %u\n", ith, nth,
         ne00, ne01, ne02, ne03, ir0, ir1, ne10, ne11, ne12, ne13, ne0, ne1, ne2, ne3, (unsigned) qt);
}

int op_get_rows(struct htp_ops_context * octx) {
    get_rows_preamble;

    const uint32_t n_threads = MIN(nr, octx->n_threads);

    if (octx->src[0]->type != HTP_TYPE_F32) {
        return HTP_STATUS_NO_SUPPORT;
    }

    if (octx->dst->type != HTP_TYPE_F32) {
        return HTP_STATUS_NO_SUPPORT;
    }

    if (octx->src[1]->type != HTP_TYPE_I32 && octx->src[1]->type != HTP_TYPE_I64) {
        return HTP_STATUS_NO_SUPPORT;
    }

    if (octx->flags & HTP_OPFLAGS_SKIP_COMPUTE) {
        return HTP_STATUS_OK;
    }

    struct get_rows_context grctx;
    grctx.octx = octx;
    grctx.get_rows_div_ne10      = init_fastdiv_values(octx->src[1]->ne[0]);
    grctx.get_rows_div_ne10_ne11 = init_fastdiv_values(octx->src[1]->ne[0] * octx->src[1]->ne[1]);

    grctx.src1_nrows_per_thread = (nr + n_threads - 1) / n_threads;

    worker_pool_run_func(octx->ctx->worker_pool, get_rows_thread_f32_f32, &grctx, n_threads);
    return HTP_STATUS_OK;
}