mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-17 20:31:47 +02:00
AclyandJeff Bolz
e29acf74fe
* vulkan (DRAFT): split shader generation by GLSL source file, to improve incremental build times * support dep-files so shaders are recompiled if their included files change * rename shader files which are used as "headers" to use .glsl extension * move glslc extension detection shaders to separate folders * the above is to prevent them from getting glob'd with the actual compute shaders that need to be compiled * vulkan : only write embedded shader .hpp/.cpp when they change * avoid recompiling ggml-vulkan.cpp when editing shaders * pass single --source argument instead of --input-dir & --filter to shader gen * check for source file match earlier * fix hang in vulkan-shaders-gen when there are compilation errors * early out did not decrement compile_count * clean up * fix glslc integer dot product test * unconditionally write the embedded shader cpp output * replace output filepath in generated dep-files to match output in CMakeLists --------- Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
30 lines
946 B
Plaintext
30 lines
946 B
Plaintext
#version 450
|
|
|
|
#include "types.glsl"
|
|
#include "generic_binary_head.glsl"
|
|
|
|
layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
void main() {
|
|
const uint idx = gl_GlobalInvocationID.x;
|
|
if (idx >= p.ne) {
|
|
return;
|
|
}
|
|
|
|
const uint offset = p.param3;
|
|
const uint src1_i = idx - offset;
|
|
const uint oz = src1_i / p.nb02;
|
|
const uint oy = (src1_i - (oz * p.nb02)) / p.nb01;
|
|
const uint ox = src1_i % p.nb01;
|
|
|
|
uint i00, i01, i02, i03;
|
|
get_indices(idx, i00, i01, i02, i03);
|
|
|
|
if (ox < p.ne10 && oy < p.ne11 && oz < p.ne12) {
|
|
data_d[get_doffset() + dst_idx(i00, i01, i02, i03)] = D_TYPE(FLOAT_TYPE(data_a[get_aoffset() + src0_idx(i00, i01, i02, i03)]) + FLOAT_TYPE(data_b[get_boffset() + ox + oy * p.ne10 + oz * p.ne10 * p.ne11]));
|
|
} else {
|
|
data_d[get_doffset() + dst_idx(i00, i01, i02, i03)] = D_TYPE(FLOAT_TYPE(data_a[get_aoffset() + src0_idx(i00, i01, i02, i03)]));
|
|
}
|
|
}
|
|
|