mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-11-11 14:22:09 +01:00
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
859 B
GLSL
30 lines
859 B
GLSL
void main() {
|
|
const uint i = gl_GlobalInvocationID.z * 262144 + gl_GlobalInvocationID.y * 512 + gl_GlobalInvocationID.x;
|
|
|
|
if (i >= p.N) {
|
|
return;
|
|
}
|
|
|
|
const uint row = i / p.ne20;
|
|
const uint col = i - row * p.ne20;
|
|
|
|
if (p.mode == 0) {
|
|
// Default
|
|
const uint offset = p.ne00 / 2;
|
|
const uint idx = row * p.ne00 + col;
|
|
|
|
data_d[row * offset + col] = D_TYPE(op(float(data_a[idx]), float(data_a[idx + offset])));
|
|
} else if (p.mode == 1) {
|
|
// Swapped
|
|
const uint offset = p.ne00 / 2;
|
|
const uint idx = row * p.ne00 + col;
|
|
|
|
data_d[row * offset + col] = D_TYPE(op(float(data_a[idx + offset]), float(data_a[idx])));
|
|
} else {
|
|
// Split
|
|
const uint idx = row * p.ne00 + col;
|
|
|
|
data_d[idx] = D_TYPE(op(float(data_a[idx]), float(data_b[idx])));
|
|
}
|
|
}
|