SciComp Accelerates Derivative Pricing Software with NVIDIA CUDA

By DE Editors

NVIDIA (Santa Clara, CA) announced that SciComp (Austin, TX) is using NVIDIA CUDA to accelerate the performance of Monte Carlo pricing models — running up to 100 times faster than serial code.

Trading in over-the-counter financial derivatives is a high-risk, high-pressure venture. SciComp, which has a high-tech derivatives software solution to shorten the development time and accelerate the performance of Monte Carlo pricing models, has enhanced SciFinance, its flagship product, to deliver accurate NVIDIA CUDA-enabled derivatives pricing models that run up to 100 times faster than serial code. This speedup for the calculations can be achieved without additional work or hand programming, which, in a market where a slight delay or inaccuracy can end up costing millions, is a critical advance.

The graphics processing unit (GPU) is the key to this speedup. This massive parallel computational power — made possible by the GPU’s up to 240 cores parallel processor that can run parallel applications many times faster than a computer's CPU — is unlocked by NVIDIA CUDA architecture. This programming environment is based on the industry-standard C language that enables developers to write software to solve complex computational problems in a fraction of the time.

More information on SciFinance can be found at SciComp; visit NVIDIA for more information on CUDA architecture.

Sources: Press materials received from the company and additional information gleaned from the company's website.