Execution mode question: asynchronous or synchronous

Accelerated Computing CUDA CUDA Programming and Performance
1

  1. Most lectures say: cudaMemcpy() is synchronous. This is what I understand.

  2. But when I read “CUDA C Programming Guide Version 3.2”, got really confused by $3.2.7.1:

Asynchronous Concurrent Execution:
“Host <-> device memory copies of a memory block of 64 KB or less”.

Do these two conflict? Thanks.

2
  1. is an exception to 1). It has only recently been documented by Nvidia, so most lectures predate this.

Actually I think only host->device copies of 64kB or less are asynchronous, as asynchronous device->host copy would violate the API and make a lot of programs fail that would need extra synchronization.

3

I was worried about cudaMemcpy. I use a lot, if it’s not synchronous (device to host), my program will crash :-)

Thanks.

4

To ease your worries, have a look at this thread.

5

Thank you so much, tera :-)