64ae065511
* double the number of rows per workgroup * Update ggml-vulkan.cpp * Vulkan: Add VK_EXT_subgroup_size_control support to ensure full subgroups for coopmats * only increase the number of rows for amd and subgroup size 64 * fix missing NUM_ROWS for mul_mat_vec_iq4_nl_f16_f32, untested * use subgroup min and max to check for gcn (requires https://github.com/ggerganov/llama.cpp/pull/10721) * manual merge ggml-vulkan.cpp * set min and max subgroup size in any case * Also double the number of rows for Intel GPUs
39 lines
1.1 KiB
Text
39 lines
1.1 KiB
Text
#version 450
|
|
|
|
#include "types.comp"
|
|
#include "generic_binary_head.comp"
|
|
#include "dequant_funcs.comp"
|
|
|
|
layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
void main() {
|
|
const uint i00 = (gl_GlobalInvocationID.x)*2;
|
|
const uint i10 = gl_GlobalInvocationID.y;
|
|
const uint i11 = (gl_GlobalInvocationID.z)/p.ne12;
|
|
const uint i12 = (gl_GlobalInvocationID.z)%p.ne12;
|
|
|
|
#if defined(DATA_A_IQ4_NL)
|
|
init_iq4nl_shmem();
|
|
#endif
|
|
|
|
if (i00 >= p.ne00) {
|
|
return;
|
|
}
|
|
|
|
const uint i01 = data_b[i10*p.nb10 + i11*p.nb11 + i12*p.nb12];
|
|
|
|
const uint a_offset = i01*p.nb01 + i11*p.nb02 + i12*p.nb03;
|
|
const uint d_offset = i10*p.nb21 + i11*p.nb22 + i12*p.nb23;
|
|
|
|
const uint ib = a_offset + i00/QUANT_K; // block index
|
|
const uint iqs = (i00%QUANT_K)/QUANT_R; // quant index
|
|
const uint iybs = i00 - i00%QUANT_K; // dst block start index
|
|
const uint y_offset = QUANT_R == 1 ? 1 : QUANT_K/2;
|
|
|
|
vec2 v = dequantize(ib, iqs, 0);
|
|
const vec2 dm = get_dm(ib, 0);
|
|
v = v * dm.x + dm.y;
|
|
|
|
data_d[d_offset + iybs + iqs ] = D_TYPE(v.x);
|
|
data_d[d_offset + iybs + iqs + y_offset] = D_TYPE(v.y);
|
|
}
|