Open tkphd opened 6 years ago
Inner loops on CUDA convolution code should run faster using a #pragma unroll statement.
#pragma unroll
#pragma unroll N
-Munroll
Inner loops on CUDA convolution code should run faster using a
#pragma unrollstatement.#pragma unroll Nin CUDA#pragma unroll Nin OpenCL-Munrollflag with pgcc#pragma unroll Nfor icc]()