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_control_flow_attributes : require
|
|
|
|
#include "types.glsl"
|
|
|
|
layout (push_constant) uniform parameter
|
|
{
|
|
uint ne0;
|
|
uint ne1;
|
|
uint s01;
|
|
uint s02;
|
|
uint s11;
|
|
uint s21;
|
|
} p;
|
|
|
|
#define BLOCK_SIZE 512
|
|
|
|
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) readonly buffer Y {B_TYPE data_b[];};
|
|
layout (binding = 2) readonly buffer Z {int32_t data_c[];};
|
|
layout (binding = 3) writeonly buffer D {D_TYPE data_d[];};
|
|
|
|
void main() {
|
|
const uint i1 = gl_WorkGroupID.x;
|
|
const uint i2 = gl_WorkGroupID.y;
|
|
|
|
const uint i11 = data_c[i1 + i2 * p.s21];
|
|
|
|
const uint s1 = p.ne0;
|
|
const uint s2 = p.ne0 * p.ne1;
|
|
|
|
const uint d0 = i1 * s1 + i2 * s2;
|
|
const uint a0 = i1 * p.s01 + i2 * p.s02;
|
|
const uint b0 = i11 * p.s11;
|
|
|
|
for (uint i0 = gl_LocalInvocationID.x; i0 < p.ne0; i0 += BLOCK_SIZE) {
|
|
data_d[d0 + i0] = data_a[a0 + i0] + data_b[b0 + i0];
|
|
}
|
|
}
|