Benchmarking & Workload Characterization
NERSC assess available HPC system solutions using a combination of application benchmarks and microbenchmarks. By understanding the requirements of the NERSC workload we drive changes in computing architecture that will result in better HPC system architectures for scientific computing in future generation machines.
2018 Workload Analysis
As part of the NERSC-10 procurement, NERSC conducted a workload analysis (v1.0) on the Edison and Cori systems analyzing algorithmic diversity, GPU readiness, memory utilization, and I/O and storage patterns.
2014 Workload Analysis
As part of the NERSC-9 procurement, NERSC conducted a workload analysis (v1.1) on the Hopper and Edison systems analyzing algorithmic diversity, MPI and OpenMP concurrency, memory utilization, and I/O and storage needs.
2013 Workload Analysis
As part of the NERSC-8 procurement, NERSC conducted a workload analysis on the Hopper system analyzing application and algorithm breakdown, library usage, job size, as well as memory and threading usage.
Scalable System Improvement (SSI): An Application Performance Benchmarking Metric for HPC Scalable System Improvement (SSI) provides a means to measure relative application performance between two high-performance computing (HPC) platforms. In defining SSI, it was desired to have a single metric to measure performance improvement for a wide variety of application and platform characteristics, for example capability, throughput, strong scaling, weak scaling, system size, etc. It is also… Read More »