sample_0_benchmark_VkFFT_single case #209
root132322
started this conversation in
General
Replies: 1 comment
-
The results I ran are to be compared with those produced by NVCC. Should I use relative error for comparison since the output numbers are extremely large? If relative error is used, within what range is the precision considered acceptable? Please give me some advice. Thank you. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi, I have a question: After running the sample_0_benchmark_VkFFT_single case from the src/VkFFT/benchmark_scripts/vkFFT_scripts directory with our own compiler, I added printf at the end of each kernel to print the value of outputs[inoutID]. How should I compare the final results, and what accuracy threshold is considered acceptable?
Beta Was this translation helpful? Give feedback.
All reactions