SpyderByte.com ;Technical Portals 
 News & Information Related to Linux High Performance Computing, Linux Clustering and Cloud Computing
Home About News Archives Contribute News, Articles, Press Releases Mobile Edition Contact Advertising/Sponsorship Search Privacy
HPC Vendors
Cluster Quoter (HPC Cluster RFQ)
Hardware Vendors
Software Vendors
HPC Consultants
Training Vendors
HPC Resources
Featured Articles
Cluster Builder
User Groups & Organizations
HP Server Diagrams
HPC News
Latest News
News Archives
Search Archives
HPC Links

HPC Tech Forum (was BW-BUG)
The Aggregate
Cluster Computing Info Centre
Coyote Gultch
Dr. Robert Brown's Beowulf Page
FreshMeat.net: HPC Software
HPC User Forum
HPC Newsletters
Stay current on Linux HPC news, events and information.
LinuxHPC.org Newsletter

Other Mailing Lists:
Linux High Availability
Beowulf Mailing List
Gelato.org (Linux Itanium)

Mobile Edition

Latest News

SciComp Accelerates Market Leading Derivative Pricing Software with NVIDIA CUDA
Posted by Julie Morgan, Tuesday September 16 2008 @ 11:47AM EDT

Trading in over-the-counter financial derivatives is a high-risk, high-pressure venture. SciComp, an Austin, Texas-based company, has a high-tech derivatives software solution to shorten the development time and accelerate the performance of Monte Carlo pricing models. The company 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. More significantly, this speed up can be achieved without any 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 key to this speedup is reliance on the graphics processing unit (GPU) for the calculations. A GPU is a many-core (up to 240 cores in the latest models) parallel processor that can run parallel applications many times faster than a computer's CPU. This massive parallel computational power is unlocked by NVIDIA CUDA architecture, a programming environment based on the industry-standard C language that enables developers to write software to solve complex computational problems in a fraction of the time.

"The old aphorism 'time is money' has never been more true than in the pressurized world of OTC derivatives trading, where the constant flow of new contracts demands the ability to produce complex mathematical pricing models rapidly," said Curt Randall, executive vice president of SciComp. "This process used to take days if not weeks of error prone hand coding, but with SciFinance, model developers make a few changes to a model specification of a half page or less and then generate accurate C or C++ source code pricing models in minutes."

"SciFinance's new ability to generate GPU-enabled code without additional programming is game-changing technology for our customers," added Randall. "The code takes full advantage of the GPU's parallel architecture, delivering an immediate 20-100X execution speed increase. Pricing models that used to run in minutes now complete in seconds, allowing financial institutions to test alternatives models, increase scenario analysis, and better understand their potential risk exposure. And best of all, they need not become experts in parallel coding concepts. SciFinance takes care of that."

To take advantage of CUDA architecture, a bank's in-house development team need simply use SciFinance's high-level financial and mathematical language for describing the derivatives model. Adding the keyword "CUDA" to a model specification outputs CUDA-enabled source code which can run on any standard PC with a CUDA-enabled GPU.

Financial institutions such as banks and hedge funds engage in derivative transactions to help manage financial exposure and risks. Derivative contracts are financial instruments whose value is based upon fluctuations in an underlying variable (e.g., the value of a stock option depends on the volatility of the underlying stock). Pricing derivatives requires complex mathematical models, often requiring the running of millions of scenarios. Therefore, fast and accurate calculations are at a premium.

"SciComp is one of the first companies to fully embrace the potential that GPUs have in the field of computational finance," said Andy Keane, general manager of the GPU Computing business at NVIDIA. "The ability to not just deliver small and incremental increases in performance, but instead to deliver 100X and reduce weeks of hand coding to immediate, real-time results is incredibly powerful. We look forward to working closely with SciComp going forward to bring more defining improvements to the SciFinance generated pricing models and in turn their customers' businesses."

More information on SciComp and SciFinance can be found at http://www.scicomp.com and for additional information on CUDA architecture, visit http://www.nvidia.com/cuda


NVIDIA (Nasdaq: NVDA) is the world leader in visual computing technologies and the inventor of the GPU, a high-performance processor which generates breathtaking, interactive graphics on workstations, personal computers, game consoles, and mobile devices. NVIDIA serves the entertainment and consumer market with its GeForce graphics products, the professional design and visualization market with its Quadro® graphics products, and the high-performance computing market with its Tesla computing solutions products. NVIDIA is headquartered in Santa Clara, Calif. and has offices throughout Asia, Europe, and the Americas. For more information, visit http://www.nvidia.com

About SciComp Inc.

A recognized leader in derivatives pricing software, SciComp provides a financial compiler for generating C or C++ pricing source code from concise, high-level model specifications. SciComp's global customer base includes investment banks, money center banks, asset managers, insurance companies, hedge funds and service providers. Derivative instruments supported include equity derivatives, convertible bonds, cross currency/interest rate derivatives, energy derivatives, FX products, credit derivatives and cross asset structures. Visit http://www.scicomp.com or call 512-451-1050 for more information.

< Fixstars Provides GigaAccel 180 with Yellow Dog | Clustercorp Integrates TotalView into Rocks+ >



Cluster Monkey

HPC Community

Supercomputing 2010

- Supercomputing 2010 website...

- 2010 Beowulf Bash

- SC10 hits YouTube!

- Louisiana Governor Jindal Proclaims the week of November 14th "Supercomputing Week" in honor of SC10!

Appro: High Performance Computing Resources
IDC: Appro Xtreme-X Supercomputer Blade Solution
Analysis of the Xtreme-X architecture and management system while assessing challenges and opportunities in the technical computing market for blade servers.

Video - The Road to PetaFlop Computing
Explore the Scalable Unit concept where multiple clusters of various sizes can be rapidly built and deployed into production. This new architectural approach yields many subtle benefits to dramatically lower total cost of ownership.
White Paper - Optimized HPC Performance
Multi-core processors provide a unique set of challenges and opportunities for the HPC market. Discover MPI strategies for the Next-Generation Quad-Core Processors.

Appro and the Three National Laboratories
[Appro delivers a new breed of highly scalable, dynamic, reliable and effective Linux clusters to create the next generation of supercomputers for the National Laboratories.

AMD Opteron-based products | Intel Xeon-based products

Home About News Archives Contribute News, Articles, Press Releases Mobile Edition Contact Advertising/Sponsorship Search Privacy
     Copyright © 2001-2011 LinuxHPC.org
Linux is a trademark of Linus Torvalds
All other trademarks are those of their owners.
  SpyderByte.com ;Technical Portals