Category: Question (Page 2 of 24)

CUDA Programming

write a CUDA program to perform a convolution.
We will first write a specialized convolution kernel to perform the convolution. Then we will use the kernel to compute a weighted running average.
The Convolution
In the textbook, we assume that the convolution mask is symmetric – that is, there are an odd number of elements in the mask and the center of the mask is align to the element we want to compute the convolution.
Continue reading
« Older posts Newer posts »

© 2021 AskTester

Theme by Anders NorenUp ↑