Acly
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>
27 lines
809 B
Plaintext
27 lines
809 B
Plaintext
#version 450
|
|
|
|
#include "types.glsl"
|
|
#include "generic_unary_head.glsl"
|
|
|
|
layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
uint src0_idx_mod(uint idx) {
|
|
const uint i13 = idx / (p.ne12*p.ne11*p.ne10);
|
|
const uint i13_offset = i13 * p.ne12*p.ne11*p.ne10;
|
|
const uint i12 = (idx - i13_offset) / (p.ne11*p.ne10);
|
|
const uint i12_offset = i12*p.ne11*p.ne10;
|
|
const uint i11 = (idx - i13_offset - i12_offset) / p.ne10;
|
|
const uint i10 = idx - i13_offset - i12_offset - i11*p.ne10;
|
|
return (i13 % p.ne03)*p.nb03 + (i12 % p.ne02)*p.nb02 + (i11 % p.ne01)*p.nb01 + (i10 % p.ne00)*p.nb00;
|
|
}
|
|
|
|
void main() {
|
|
const uint idx = get_idx();
|
|
|
|
if (idx >= p.ne) {
|
|
return;
|
|
}
|
|
|
|
data_d[get_doffset() + dst_idx(idx)] = D_TYPE(data_a[get_aoffset() + src0_idx_mod(idx)]);
|
|
}
|