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>
42 lines
1.5 KiB
Plaintext
42 lines
1.5 KiB
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.z * 262144 + gl_GlobalInvocationID.y * 512 + gl_GlobalInvocationID.x;
|
|
const int dim = p.param3;
|
|
|
|
if (idx >= p.ne) {
|
|
return;
|
|
}
|
|
|
|
const uint i3 = idx / (p.ne22*p.ne21*p.ne20);
|
|
const uint i3_offset = i3 * p.ne22*p.ne21*p.ne20;
|
|
const uint i2 = (idx - i3_offset) / (p.ne21*p.ne20);
|
|
const uint i2_offset = i2*p.ne21*p.ne20;
|
|
const uint i1 = (idx - i3_offset - i2_offset) / p.ne20;
|
|
const uint i0 = idx - i3_offset - i2_offset - i1*p.ne20;
|
|
|
|
uint o[4] = {0, 0, 0, 0};
|
|
o[dim] = dim == 0 ? p.ne00 : (dim == 1 ? p.ne01 : (dim == 2 ? p.ne02 : p.ne03));
|
|
|
|
const uint src0_idx = i3*p.nb03 + i2*p.nb02 + i1*p.nb01 + i0*p.nb00;
|
|
const uint src1_idx = (i3 - o[3])*p.nb13 + (i2 - o[2])*p.nb12 + (i1 - o[1])*p.nb11 + (i0 - o[0])*p.nb10;
|
|
const uint dst_idx = i3*p.nb23 + i2*p.nb22 + i1*p.nb21 + i0*p.nb20;
|
|
|
|
const bool is_src0 = i0 < p.ne00 && i1 < p.ne01 && i2 < p.ne02 && i3 < p.ne03;
|
|
|
|
#ifndef OPTIMIZATION_ERROR_WORKAROUND
|
|
data_d[get_doffset() + dst_idx] = D_TYPE(is_src0 ? data_a[get_aoffset() + src0_idx] : data_b[get_boffset() + src1_idx]);
|
|
#else
|
|
if (is_src0) {
|
|
data_d[get_doffset() + dst_idx] = data_a[get_aoffset() + src0_idx];
|
|
} else {
|
|
data_d[get_doffset() + dst_idx] = data_b[get_boffset() + src1_idx];
|
|
}
|
|
#endif
|
|
}
|