Investment banks like calculations that require powerful computational resources. In many cases Monte-Carlo simulations are run on huge GRID systems that cost a lot.
Such systems are usually home grown and really look expensive to replicate elsewhere.
Few monthes ago I read an article in RISK magazine that outlined the same problem and as an option a chipper and more flexible approach was mentioned that is based on multi-core CPU and GPU.
http://www.nvidia.co.uk/content/EMEAI/PDF/risk-magazine-tesla-april2013.pdf
GPU programming probably is not too complex although it definitely requires some background desk devs or quants might not have. A company Xcelerit http://www.xcelerit.com/ made an attempt to ease the parallel programming. They provide SDK that allows quants develop and execute their C++ programs on a high-performance environment.
Furthermore they have a library that comes with base statistics functions, market data adapters and a number of interfaces for commonly used software packages, e.g. MATLAB, Excel.
http://www.xcelerit.com/xcelerit-forges-new-tools-for-quantitative-finance/
They also outlined some case studies of inefficiencies of sequential program execution on a GRID compared to multi-core CPU architectures.
http://blog.xcelerit.com/efficiently-using-computing-grids-in-the-financial-industry/
Examples of SDK usage
http://blog.xcelerit.com/xcelerit-sdk-user-experience/
HSBC usage
http://blog.xcelerit.com/hsbc-run-risk-in-real-time-with-xcelerit-and-gpus/
Let's see whether this attempt of Xcelerit will have a successful continuation.
Such systems are usually home grown and really look expensive to replicate elsewhere.
Few monthes ago I read an article in RISK magazine that outlined the same problem and as an option a chipper and more flexible approach was mentioned that is based on multi-core CPU and GPU.
http://www.nvidia.co.uk/content/EMEAI/PDF/risk-magazine-tesla-april2013.pdf
GPU programming probably is not too complex although it definitely requires some background desk devs or quants might not have. A company Xcelerit http://www.xcelerit.com/ made an attempt to ease the parallel programming. They provide SDK that allows quants develop and execute their C++ programs on a high-performance environment.
Furthermore they have a library that comes with base statistics functions, market data adapters and a number of interfaces for commonly used software packages, e.g. MATLAB, Excel.
http://www.xcelerit.com/xcelerit-forges-new-tools-for-quantitative-finance/
They also outlined some case studies of inefficiencies of sequential program execution on a GRID compared to multi-core CPU architectures.
http://blog.xcelerit.com/efficiently-using-computing-grids-in-the-financial-industry/
Examples of SDK usage
http://blog.xcelerit.com/xcelerit-sdk-user-experience/
HSBC usage
http://blog.xcelerit.com/hsbc-run-risk-in-real-time-with-xcelerit-and-gpus/
Let's see whether this attempt of Xcelerit will have a successful continuation.
No comments:
Post a Comment