Visible to Intel only — GUID: GUID-8F0CD89F-02CA-45F7-8F6A-B206372D671E
Visible to Intel only — GUID: GUID-8F0CD89F-02CA-45F7-8F6A-B206372D671E
Sendrecv
The Sendrecv benchmark is based on MPI_Sendrecv. In this benchmark, the processes form a periodic communication chain. Each process sends a message to the right neighbor and receives a message from the left neighbor in the chain. The turnover count is two messages per sample (one in, one out) for each process.
In the case of two processes, Sendrecv is equivalent to the PingPing benchmark of IMB1.x. For two processes, it reports the bidirectional bandwidth of the system, as obtained by the optimized MPI_Sendrecv function.
Sendrecv Definition
Property |
Description |
---|---|
Measured pattern |
As symbolized between in the figure below. |
MPI routines |
MPI_Sendrecv |
MPI data type |
MPI_BYTE |
Reported timings |
time=Δt (in μsec) as indicated in the figure below. |
Reported throughput |
2X/time |