Performance and Benchmarking
Leveraging GPUs for performance improvement is one of the key values available from the Jacket platform. Performance will vary from application to application, but AccelerEyes has compiled a few performance benchmark examples to give our customers a sense of what is possible. These examples are part of every Jacket installation, located in the <jacket_root>/examples directory.
A set of benchmarks, which test a large number of Jacket/MATLAB functions for vector/matrix and for single/double precision are presented on the Jacket Wiki and Torben's Corner:- Jacket Benchmark Tables
- Jacket Floating Point Performance (GFlops)
- Influence of The Performance Setting Of The CPU
- GPU Memory Transfer
- Save/Load Disk Data
Additionally, GBENCH is available as a free GPU benchmarking utility to measure performance between different GPUs or versus CPU based systems.
Finally, AccelerEyes and our customers have jointly developed success stories to provide both a sense of what applications are possible with Jacket as well as performance information to illustrate the potential impact.
Performance Examples:The following charts illustrate performance characteristics of Jacket and NVIDIA's Tesla C1060 on a couple of applications. These illustrations demonstrate not only the relative performance versus CPUs running the same application but also demonstrate that larger datasets can potentially increase the performance gap.
 |
 |
The following performance chart is courtesy of Raphael Attie of the Max Planck Institute for Solar System Research. Jacket and Jacket HPC were used on a GPU cluster to perform important research work for the institute.
Benchmarking:
AccelerEyes has released a valuable and free GPU utility to assist the community in benchmarking the relative performance of applications and algorithms on different GPUs or CPU system configurations. Download GBENCH and give it a whirl!