Sign Up to our social questions and Answers Engine to ask questions, answer people’s questions, and connect with other people.
Login to our social questions & Answers Engine to ask questions answer people’s questions & connect with other people.
Lost your password? Please enter your email address. You will receive a link and will create a new password via email.
Please briefly explain why you feel this question should be reported.
Please briefly explain why you feel this answer should be reported.
Please briefly explain why you feel this user should be reported.
I have a simple kernel without using multiple events, and i want to create a CPU version of it which i’ve done and measure the difference between them. I don’t know if events are strictly created for CUDA, but i guess my example is simple enough and does not contain anything to be ok to do that. Opinions?
If you are measuring time on the CPU, nothing is better than High performance counters E.g for java, you can measure time in the nano second range. Events are generally used for the GPU as the start and stop event are added to the GPU queue, not the CPU one.