Site Announcements

 GPU Technology Conference

_______________________________________________________________________________________________

Computational Finance

 Welcome to the Computational Finance community.

 This community covers all aspects of computational finance so I welcome contributions in areas such as option pricing using finite difference and Monte Carlo methods (which will also include random number generation as a sub-topic), as well as other areas such as portfolio optimisation and algorithmic trading.

Mike Giles My own research is primarily in Monte Carlo methods, but I have an extensive background in finite difference and finite volume methods in CFD (computational fluid dynamics). I am working with NAG to develop GPU implementations of random number generators and other numerical routines (see  www.nag.co.uk/numeric/GPUs/ ) and I have also created CUDA examples of both Monte Carlo and finite difference methods (see people.maths.ox.ac.uk/~gilesm/hpc/ ). 

I hope this site will stimulate a good discussion between academics and those working in industry, on ways of improving the exploitation of GPUs for high throughput computing, and at the same time trying to simplify the programming effort required. 

Mike Giles, University of Oxford.

Featured Stories and Papers

Computational finance in academia and industry


In this page I would like to gather together links to activities in computational finance in academia and industry.  If you have suggestions of new items to add, or if you find any of the existing links have moved or no longer exist, please let me know (mike.giles@maths.ox.ac.uk)

Academics:

 Software vendors:

 Random number generation:

 Industry use:

 Other sources of information:


Read More

Get CUDA Certified


NVIDIA has launched its first CUDA Certification program.

Be one of the first Certified CUDA Programmers - find out the full details at www.nvidia.com/certification

This exam tests candidates CUDA C programming and optimization skills. This 3 hour test can be taken at over 6500 test centers in over 165 countries.

Discounts are available for companies planning to certify 6 engineers or more. General questions or applications for bulk discounts can be addressed to certification@nvidia.com


Read More

Latest Code Snippets and Repositories

Featured Events

CUDA course at Oxford, July 26-30


This is a 5-day hands-on course for students, postdocs, academics and others who want to learn how to develop applications to run on NVIDIA GPUs using the CUDA programming environment.
Read More