98bab638fb
* ggml : add ggml_scale_bias * ggml_vec_mad1_f32 * add more simd * add CUDA * sycl * vulkan * cann (placeholder) * opencl * will this fix cpu? * fix cuda * suggestions from coderabbit * fix cann compile error * vDSP_vsmsa * rm __ARM_FEATURE_SVE * use memcpy for op params * make code looks more consistent * use scalar for __ARM_FEATURE_SVE * add x param to ggml_vec_mad1_f32
25 lines
625 B
Plaintext
25 lines
625 B
Plaintext
#version 450
|
|
|
|
#include "types.comp"
|
|
#include "generic_unary_head.comp"
|
|
|
|
const uint num_threads = 128;
|
|
|
|
layout(local_size_x = num_threads, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
void main() {
|
|
uint idx = get_idx();
|
|
|
|
// num_threads * num_iter must equal 512, to match the wg_denoms and get_idx calculation
|
|
const uint num_iter = 4;
|
|
|
|
[[unroll]] for (uint i = 0; i < num_iter; ++i) {
|
|
if (idx >= p.ne) {
|
|
continue;
|
|
}
|
|
|
|
data_d[get_doffset() + idx] = D_TYPE(FLOAT_TYPE(data_a[get_aoffset() + idx]) * FLOAT_TYPE(p.param1) + FLOAT_TYPE(p.param2));
|
|
idx += num_threads;
|
|
}
|
|
}
|