80f19b4186
* opencl: refactor - split the kernel files --------- Co-authored-by: Shangqing Gu <quic_shawngu@quicinc.com> * opencl: split more kernels into separate files * opencl: specify subgroup size instead of querying it * opencl: refine Adreno cl compiler version parsing * opencl: skip some kernels not used by Adreno on old compilers * opencl: refine logic for selecting Adreno kernels * opencl: refine Adreno cl compiler version * opencl: cleanup preprocessor for kernels * opencl: consider Adreno CL compiler on Windows * opencl: add final newline for `mul_mv_f16_f16.cl` --------- Co-authored-by: Shangqing Gu <quic_shawngu@quicinc.com>
17 lines
529 B
Common Lisp
17 lines
529 B
Common Lisp
#pragma OPENCL EXTENSION cl_khr_fp16 : enable
|
|
|
|
//------------------------------------------------------------------------------
|
|
// relu
|
|
//------------------------------------------------------------------------------
|
|
kernel void kernel_relu(
|
|
global float * src0,
|
|
ulong offset0,
|
|
global float * dst,
|
|
ulong offsetd
|
|
) {
|
|
src0 = (global float*)((global char*)src0 + offset0);
|
|
dst = (global float*)((global char*)dst + offsetd);
|
|
|
|
dst[get_global_id(0)] = fmax(0.0f, src0[get_global_id(0)]);
|
|
}
|