[mvapich-discuss] Overlap of communication and computation on the GPU
Yussuf Ali
yussuf.ali at jaea.go.jp
Thu May 16 04:13:16 EDT 2019
Dear MVAPICH developers and users,
I have a question regarding communication and computation overlap with
MVAPICH2-GDR.
If we write the following code in our program:
MPI_Irecv(cuBufferA.......);
MPI_Isend(cuBufferB.......)
my_kernel<<<...>>>(cuBufferC,cuBufferD);
All buffers are device buffers and my_kernel can be calculated
independently of cuBufferA and cuBufferB.
Will the GPU automatically overlap Irecv/Isend with the my_kernel
execution?
Or will my_kernel be executed after Irecv/Isend are finished?
Thank you for your help,
Yussuf Ali
More information about the mvapich-discuss
mailing list