mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-11 10:36:54 +00:00
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>
26 lines
752 B
GLSL
26 lines
752 B
GLSL
#ifndef UTILS_COMP
|
|
#define UTILS_COMP
|
|
|
|
// mod and div are expensive and coordinates/dimensions are often power of 2 or equal to 1
|
|
uint fastmod(uint a, uint b) {
|
|
if ((b & (b-1)) == 0) {
|
|
return a & (b-1);
|
|
}
|
|
return a % b;
|
|
}
|
|
|
|
uint fastdiv(uint a, uint b) {
|
|
return (a < b) ? 0 : (a / b);
|
|
}
|
|
|
|
void get_indices(uint idx, out uint i00, out uint i01, out uint i02, out uint i03, uint ne00, uint ne01, uint ne02, uint ne03) {
|
|
i03 = fastdiv(idx, (ne02*ne01*ne00));
|
|
const uint i03_offset = i03 * ne02*ne01*ne00;
|
|
i02 = fastdiv((idx - i03_offset), (ne01*ne00));
|
|
const uint i02_offset = i02*ne01*ne00;
|
|
i01 = (idx - i03_offset - i02_offset) / ne00;
|
|
i00 = idx - i03_offset - i02_offset - i01*ne00;
|
|
}
|
|
|
|
#endif // UTILS_COMP
|