Tom Groenfeldt, Forbes, The Risk Management Race Goes To Nvidia GPUs, here. Perhaps, A Risk Management Race Goes To Nvidia GPUs?
The Securities Technology Analysis Center (STAC), presented the results recently at a conference in London to showcase its latest benchmark, STAC-A2, the first benchmark to compare the performance of traditional IntelINTC -0.61% CPUs with NVIDIANVDA +1.49%’s K20X GPU accelerators – ultra-high performance processors that dramatically accelerate the processing of massive and complex datasets. GPUs, (Graphics Processing Unit(s) are a key component in video gaming. They are extremely fast but can often be very difficult to program. Details of the benchmark and the test are on the STAC Web site.
We should go check the details at the STAC Web site, right?
Securities Technology Analysis Center, STAC Report: STAC-A2 on NVIDIA & IBM iDataPlex, here. Looks like Eigen 3 running on Sandy Bridge cores, no AVX2 here. That’s unusual, right? Testing Sandy Bridge and no AVX2 to determine what is the fastest machine in a Risk Management race in 2014, is that really a thing? Isn’t it a little like deciding the best chess player on earth, while Carlsen, Anand, Gelfand, Kramnik, and Nakamura are flying over the Atlantic and implicitly arguing, well they weren’t “on earth” when we ran the benchmark, and publishing the results.
Specs: STAC-A2 Benchmarks
Stack under test:
– NVIDIA CUDA 5.5
– NVIDIA cuRand and cuBLAS
– CUB library
– Eigen 3 library
– GNU OpenMP (libgomp)
– 2 x NVIDIA K20X @ 2600MHz, 784MHz (with ECC enabled)
– IBM System X iDataPlex dx360 M4 Server
– 2 x Intel Xeon E5-2660 @ 2.20GHz (SandyBridge)
– CentOS Linux 6.4
– 96GB DDR3 RAM