mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-08 11:46:53 +01:00
f3f65429c4
* scripts : update sync [no ci] * files : relocate [no ci] * ci : disable kompute build [no ci] * cmake : fixes [no ci] * server : fix mingw build ggml-ci * cmake : minor [no ci] * cmake : link math library [no ci] * cmake : build normal ggml library (not object library) [no ci] * cmake : fix kompute build ggml-ci * make,cmake : fix LLAMA_CUDA + replace GGML_CDEF_PRIVATE ggml-ci * move public backend headers to the public include directory (#8122) * move public backend headers to the public include directory * nix test * spm : fix metal header --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * scripts : fix sync paths [no ci] * scripts : sync ggml-blas.h [no ci] --------- Co-authored-by: slaren <slarengh@gmail.com>
38 lines
887 B
Plaintext
38 lines
887 B
Plaintext
#version 450
|
|
|
|
#include "generic_head.comp"
|
|
#include "types.comp"
|
|
|
|
#extension GL_EXT_control_flow_attributes : enable
|
|
layout(local_size_x_id = 0, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
layout (binding = 0) readonly buffer A {A_TYPE data_a[];};
|
|
layout (binding = 1) writeonly buffer D {D_TYPE data_d[];};
|
|
|
|
layout (constant_id = 0) const uint BLOCK_SIZE = 32;
|
|
|
|
shared FLOAT_TYPE tmp[BLOCK_SIZE];
|
|
|
|
void main() {
|
|
const uint row = gl_WorkGroupID.x;
|
|
const uint col = gl_LocalInvocationID.x;
|
|
|
|
tmp[col] = FLOAT_TYPE(0.0f);
|
|
|
|
for (uint i = col; i < p.KX; i += BLOCK_SIZE) {
|
|
tmp[col] += FLOAT_TYPE(data_a[row*p.KX + i]);
|
|
}
|
|
|
|
barrier();
|
|
[[unroll]] for (int s = int(BLOCK_SIZE) / 2; s > 0; s >>= 1) {
|
|
if (col < s) {
|
|
tmp[col] += tmp[col + s];
|
|
}
|
|
barrier();
|
|
}
|
|
|
|
if (col == 0) {
|
|
data_d[row] = D_TYPE(tmp[0]);
|
|
}
|
|
}
|