tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-09 10:32:38 -04:00
Code Issues Packages Projects Releases Wiki Activity

mat vec double buffer (#12188)

Browse Source
This commit is contained in:
Eve
2025-03-10 19:28:11 +00:00
committed by GitHub
parent 251364549f
commit 2c9f833d17
3 changed files with 43 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec_q3_k.comp
View File

@@ -5,20 +5,21 @@
layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
shared FLOAT_TYPE sccache[BLOCK_SIZE/16][2][8];
shared FLOAT_TYPE sccache[2][BLOCK_SIZE/16][2][8];
FLOAT_TYPE temp[NUM_COLS][NUM_ROWS];
uint csel = 0;
void calc_superblock(const uint a_offset, const uint b_offset, const uint ix, const uint itid8, const uint v_im, const uint v_im4, const uint v_in, const uint32_t hm_m[4], const uint q_offset, const uint y_offset, const uint s_shift, const uint i, const uint num_blocks_per_row, const uint first_row, const uint num_rows, const bool all_threads) {
const uint y_idx = i * QUANT_K + y_offset;
[[unroll]] for (uint n = 0; n < num_rows; ++n) {
const uint ib0 = a_offset / QUANT_K + (first_row+n)*num_blocks_per_row;
csel ^= 1;
if (!all_threads) { // when we don't have enough blocks to use all threads
barrier();
if (i < num_blocks_per_row)
sccache[ix][v_im][itid8] = FLOAT_TYPE(int8_t(((data_a[ib0+i].scales[itid8] >> v_im4) & 0xF) | (((data_a[ib0+i].scales[itid8%4+8] >> s_shift) & 3) << 4)) - 32);
sccache[csel][ix][v_im][itid8] = FLOAT_TYPE(int8_t(((data_a[ib0+i].scales[itid8] >> v_im4) & 0xF) | (((data_a[ib0+i].scales[itid8%4+8] >> s_shift) & 3) << 4)) - 32);
barrier();
if (i >= num_blocks_per_row)
@@ -40,8 +41,7 @@ void calc_superblock(const uint a_offset, const uint b_offset, const uint ix, co
const vec4 qs_u32_6 = vec4(unpack8((qs_u32 >> 6) & 0x03030303));
if (all_threads) {
barrier();
sccache[ix][v_im][itid8] = FLOAT_TYPE(int8_t(((data_a[ib0+i].scales[itid8] >> v_im4) & 0xF) | (((data_a[ib0+i].scales[itid8%4+8] >> s_shift) & 3) << 4)) - 32);
sccache[csel][ix][v_im][itid8] = FLOAT_TYPE(int8_t(((data_a[ib0+i].scales[itid8] >> v_im4) & 0xF) | (((data_a[ib0+i].scales[itid8%4+8] >> s_shift) & 3) << 4)) - 32);
barrier();
}
@@ -59,14 +59,14 @@ void calc_superblock(const uint a_offset, const uint b_offset, const uint ix, co
FLOAT_TYPE sum = FLOAT_TYPE(0.0);
[[unroll]] for (int l = 0; l < 2; ++l) {
sum = fma(FLOAT_TYPE( b0[l]) * sccache[ix][v_im][0], qs_u32_0[l ] - hmk_0[l ],
fma(FLOAT_TYPE( b16[l]) * sccache[ix][v_im][1], qs_u32_0[l+2] - hmk_0[l+2],
fma(FLOAT_TYPE( b32[l]) * sccache[ix][v_im][2], qs_u32_2[l ] - hmk_1[l ],
fma(FLOAT_TYPE( b48[l]) * sccache[ix][v_im][3], qs_u32_2[l+2] - hmk_1[l+2],
fma(FLOAT_TYPE( b64[l]) * sccache[ix][v_im][4], qs_u32_4[l ] - hmk_2[l ],
fma(FLOAT_TYPE( b80[l]) * sccache[ix][v_im][5], qs_u32_4[l+2] - hmk_2[l+2],
fma(FLOAT_TYPE( b96[l]) * sccache[ix][v_im][6], qs_u32_6[l ] - hmk_3[l ],
fma(FLOAT_TYPE(b112[l]) * sccache[ix][v_im][7], qs_u32_6[l+2] - hmk_3[l+2], sum))))))));
sum = fma(FLOAT_TYPE( b0[l]) * sccache[csel][ix][v_im][0], qs_u32_0[l ] - hmk_0[l ],
fma(FLOAT_TYPE( b16[l]) * sccache[csel][ix][v_im][1], qs_u32_0[l+2] - hmk_0[l+2],
fma(FLOAT_TYPE( b32[l]) * sccache[csel][ix][v_im][2], qs_u32_2[l ] - hmk_1[l ],
fma(FLOAT_TYPE( b48[l]) * sccache[csel][ix][v_im][3], qs_u32_2[l+2] - hmk_1[l+2],
fma(FLOAT_TYPE( b64[l]) * sccache[csel][ix][v_im][4], qs_u32_4[l ] - hmk_2[l ],
fma(FLOAT_TYPE( b80[l]) * sccache[csel][ix][v_im][5], qs_u32_4[l+2] - hmk_2[l+2],
fma(FLOAT_TYPE( b96[l]) * sccache[csel][ix][v_im][6], qs_u32_6[l ] - hmk_3[l ],
fma(FLOAT_TYPE(b112[l]) * sccache[csel][ix][v_im][7], qs_u32_6[l+2] - hmk_3[l+2], sum))))))));
}
temp[j][n] = fma(d, sum, temp[j][n]);
}