Visible to Intel only — GUID: GUID-9AFCFC54-5C22-4C44-BCE9-79BAFE4852F3
Visible to Intel only — GUID: GUID-9AFCFC54-5C22-4C44-BCE9-79BAFE4852F3
Uniband
The Uniband benchmark measures the cumulative bandwidth and message rate values. To achieve this, the first half of ranks communicates with the second half using MPI_Isend/MPI_Recv/MPI_Wait calls. In case of the odd number of processes, one of them does not participate in the message exchange. The bunch of MPI_Isend calls are issued by each rank in the first half of ranks to its counterpart from the second half of ranks. The number of messages issued at each iteration step is defined with the MAX_WIN_SIZE constant. The same buffer is used for every send event in the iteration.
Uniband Definition
Property |
Description |
---|---|
Measured pattern |
(MAX_WIN_SIZE \*MPI_Isend)/(MAX_WIN_SIZE \*MPI_Irecv)/Waitall |
MPI data type |
MPI_BYTE (origin and target) |
Reported messagerate |
MAX_WIN_SIZE*N/MAX(process_timings), where N is the number of communicating pairs |
Reportedthroughput |
MBps (msg_rate *size_in_bytes/ 1000000.0) |