Xuan-Son Nguyen
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
18 lines
578 B
Common Lisp
18 lines
578 B
Common Lisp
#pragma OPENCL EXTENSION cl_khr_fp16 : enable
|
|
|
|
//------------------------------------------------------------------------------
|
|
// scale
|
|
//------------------------------------------------------------------------------
|
|
kernel void kernel_scale(
|
|
global float4 * src0,
|
|
ulong offset0,
|
|
global float4 * dst,
|
|
ulong offsetd,
|
|
float scale,
|
|
float bias
|
|
) {
|
|
src0 = (global float4*)((global char*)src0 + offset0);
|
|
dst = (global float4*)((global char*)dst + offsetd);
|
|
dst[get_global_id(0)] = src0[get_global_id(0)] * scale + bias;
|
|
}
|