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>
32 lines
796 B
Plaintext
32 lines
796 B
Plaintext
#version 450
|
|
|
|
#extension GL_EXT_control_flow_attributes : enable
|
|
|
|
#include "types.glsl"
|
|
#include "generic_head.glsl"
|
|
|
|
layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
layout (binding = 0) readonly buffer X {A_TYPE data_a[];};
|
|
layout (binding = 1) readonly buffer Y {B_TYPE data_b[];};
|
|
layout (binding = 2) buffer D {D_TYPE data_d[];};
|
|
|
|
const uint CHUNK_SIZE = 512;
|
|
|
|
void main() {
|
|
const uint base = gl_WorkGroupID.x * CHUNK_SIZE;
|
|
const uint col = gl_LocalInvocationID.x;
|
|
|
|
uint count = 0;
|
|
[[unroll]]
|
|
for (uint i = 0; i < CHUNK_SIZE; i += gl_WorkGroupSize.x) {
|
|
const uint idx = base + i + col;
|
|
if (idx >= p.KX) {
|
|
break;
|
|
}
|
|
count += uint(data_a[idx] == data_b[idx]);
|
|
}
|
|
|
|
atomicAdd(data_d[0], D_TYPE(count));
|
|
}
|