mirror of
https://github.com/tinygrad/tinygrad.git
synced 2026-01-10 07:28:15 -05:00
bbeba8ec85
* device default * Device.DEFAULT * half max for cuda * CUDA_INCLUDE_PATH * closer to working * cuda fixups * Update ops_cuda.py
14 lines
370 B
Python
14 lines
370 B
Python
from tinygrad.runtime.ops_gpu import CLDevice, CLProgram, compile_cl
|
|
|
|
if __name__ == "__main__":
|
|
dev = CLDevice()
|
|
lib = compile_cl("""
|
|
#pragma OPENCL EXTENSION cl_khr_fp16 : enable
|
|
__kernel void test(__global half *out, __global half *a, __global half *b) {
|
|
int gid = get_global_id(0);
|
|
out[gid] = max(a[gid], b[gid]);
|
|
}
|
|
""")
|
|
prg = CLProgram(dev, "test", lib)
|
|
|