PaddlePaddle/Anakin

Does it have the multi-thread test ?

Rpersie opened this issue · 1 comments

In my task, I need not only do network computations on gpu but also do complex post processing on cpu.
So I need to create multithreads on cpu and push the data to gpu individually by every thread. But I have counter a big problem. This architecture can not support many threads on cpu. For example, the machine can run 56 threads on cpu . But the cpu-gpu mix architecture can only run 8 threads . Does this project
have some multithread examples ? Or some advices about how to use it in multithread . Thank you !

Anakin has updated the multi-thread test in docs/Manual/Anakin_helper_ch.md, and will push to GitHub very soon.