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>
43 lines
1.0 KiB
Plaintext
43 lines
1.0 KiB
Plaintext
#version 450
|
|
|
|
#extension GL_EXT_shader_16bit_storage : require
|
|
|
|
layout (push_constant) uniform parameter
|
|
{
|
|
uint nb1;
|
|
uint dim;
|
|
uint max_period;
|
|
} p;
|
|
|
|
#include "types.glsl"
|
|
|
|
#extension GL_EXT_control_flow_attributes : enable
|
|
#define BLOCK_SIZE 256
|
|
|
|
layout(local_size_x = BLOCK_SIZE, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
layout (binding = 0) readonly buffer X {A_TYPE data_a[];};
|
|
layout (binding = 1) writeonly buffer D {D_TYPE data_d[];};
|
|
|
|
void main() {
|
|
const uint i = gl_WorkGroupID.y;
|
|
const uint j = gl_GlobalInvocationID.x;
|
|
const uint d_offset = i * p.nb1;
|
|
|
|
const uint half_dim = p.dim / 2;
|
|
|
|
if (p.dim % 2 != 0 && j == half_dim) {
|
|
data_d[d_offset + 2 * half_dim] = 0.f;
|
|
}
|
|
|
|
if (j >= half_dim) {
|
|
return;
|
|
}
|
|
|
|
const float timestep = float(data_a[i]);
|
|
const float freq = float(exp(-log(p.max_period) * j / half_dim));
|
|
const float arg = timestep * freq;
|
|
data_d[d_offset + j] = D_TYPE(cos(arg));
|
|
data_d[d_offset + j + half_dim] = D_TYPE(sin(arg));
|
|
}
|