One known overhead in numba-cuda is kernel launch. We should profile it carefully and come up with a comprehensive improvement plan, but one obvious source of latency is preparing the kernel args, which is currently done using ctypes. We should switch to use cuda.core.launch().
|
def launch(self, args, griddim, blockdim, stream=0, sharedmem=0): |
|
# Prepare kernel |
|
cufunc = self._codelibrary.get_cufunc() |
|
|
|
if self.debug: |
|
excname = cufunc.name + "__errcode__" |
|
excmem, excsz = cufunc.module.get_global_symbol(excname) |
|
assert excsz == ctypes.sizeof(ctypes.c_int) |
|
excval = ctypes.c_int() |
|
excmem.memset(0, stream=stream) |
|
|
|
# Prepare arguments |
|
retr = [] # hold functors for writeback |
|
|
|
kernelargs = [] |
|
for t, v in zip(self.argument_types, args): |
|
self._prepare_args(t, v, stream, retr, kernelargs) |
|
|
|
if driver.USE_NV_BINDING: |
|
stream_handle = stream and stream.handle.value or 0 |
|
else: |
|
zero_stream = None |
|
stream_handle = stream and stream.handle or zero_stream |
|
|
|
# Invoke kernel |
|
driver.launch_kernel( |
|
cufunc.handle, |
|
*griddim, |
|
*blockdim, |
|
sharedmem, |
|
stream_handle, |
|
kernelargs, |
|
cooperative=self.cooperative, |
|
) |
