I use nvcc to compile the CUDA kernel. Unfortunately, nvcc does not seem to support uint8_t, although it does support int8_t(!). I would also not use it unsigned char, for the convenience of portability, readability and sanity. Is there another good alternative?
To prevent any possible misunderstanding, here are some details.
$ nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2010 NVIDIA Corporation
Built on Mon_Jun__7_18:56:31_PDT_2010
Cuda compilation tools, release 3.1, V0.2.1221
Code containing
int8_t test = 0;
excellent, but the code containing
uint8_t test = 0;
gives an error message, for example
test.cu(8): error: identifier "uint8_t" is undefined
source
share