The Sustained System Performance (SSP) is an aggregate, un-weighted measure of computational capability relevant to achievable scientific work. It is used as a way of measuring, reporting, and projecting the performance of a given system using a set of benchmark programs that represent a workload. Mathematically, it is expressed as the geometric mean of the processing rates of the benchmark programs multiplied by N, the number of nodes in the system. The processing rates, expressed here in units of TFlops per seecond, are calculated using a floating-point operation count predetermined on a reference system by NERSC. Thus, the inputs required for calculating the SSP consist of the times to execute the benchmark programs, the number of nodes on which they were executed, and the total size of the system for which the SSP is to be computed.
More detailed information on the SSP and its use in workload characterization related to previous NERSC acquisitions is also available.
The SSP calculation for the Trinity / NERSC-8 benchmark suite on the NERSC CRAY XE6 "Hopper" system appears below. A spreadsheet carrying out this calculation will be available for download and will be included in the RFP materials. In this spreadsheet and in the table below, items in green are supplied by ACES / NERSC and are not to be changed. Items in pink are to be supplied by the entity running the codes and items in blue are the calculated values. The problem sizes are the "large" cases and the run conditions are MPI only.
|HOPPER CRAY XE6||System Size (Nodes)||6384||Results|
|Nodes Used in Running Benchmark||Reference TFLOP Count |
(Measured by NERSC; do not change)
|Time (in seconds)|
(Measured benchmark wall-clock time)
|Rate (TF/s per Node)|
|SSP (in TFLOPS/s):||58.7|