STAC Report: STAC-A2 on NVIDIA & IBM iDataPlex

Over 9x the average speed of a system with the same class of CPUs but no GPUs in the end-to-end Greeks benchmark.

4 December 2013 - London

STAC recently tested NVIDIA GPUs against STAC-A2, the user-developed benchmark standard based on financial market risk analysis. The results are now available at www.STACresearch.com/NVIDIA. This is the first time that GPUs have been subjected to the rigorous STAC-A2 Benchmark standards, which were developed by quants and technologists from some of the world's largest banks.

The stack under test (SUT) consisted of benchmark-implementation code written by Nvidia using CUDA 5.5, running on an IBM System X iDataPlex dx360 M4 Server with two NVIDIA K20Xm co-processors and two 8-core Intel Xeon E5-2660 @ 2.20GHz (SandyBridge) processors.

In the mean end-to-end Greeks benchmark (STAC-A2.beta2.GREEKS.TIME), this system was over 9x the average speed of a system with the same class of CPUs but no GPUs and over 6x the average speed of the fastest publicly benchmarked system without GPUs. This system was also the first to handle the baseline problem size in "real time" (less than one second).

Qualified members of the STAC Benchmark Council can access the report here.

Additionally, the STAC-A2 Pack for CUDA 5.5 (NVIDIA's benchmark implementation) is also available to premium members.

 

About STAC News

Read the latest about research, events, and other important news from STAC.

Subscribe to notifications of research, events, and more.

(If you're a human, don't change the following field)
Your first name.
(If you're a human, don't change the following field)
Your first name.

Enter your email above, then click "Sign Up" to join the STAC mail list and (optionally) register to access materials on the site. Click for terms.