parallel programming open-MP
Locked
parallel programming open-MP
 
|
Hi,
I am new to quantLib and would like to start working on adding an Open- MP version of matrix operations to this opensource project. thoughts? Thanks ------------------------------------------------------------------------------ Come build with us! The BlackBerry® Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9-12, 2009. Register now! http://p.sf.net/sfu/devconf _______________________________________________ QuantLib-dev mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-dev |
Re: parallel programming open-MP
|
|
Welcome,
as an application, I'd rather suggest to add an Open-MP version of random number generation for Monte Carlo. Matrix operations are in my opinion not the application be parallelized in the first step as they are usually not the key bottleneck in quant finance applications. Thoughts? 2009/9/29 <[hidden email]> Hi, ------------------------------------------------------------------------------ Come build with us! The BlackBerry® Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9-12, 2009. Register now! http://p.sf.net/sfu/devconf _______________________________________________ QuantLib-dev mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-dev |
Re: parallel programming open-MP
|
|
Hi Dima,
Thanks for the reply. Maybe both :) can you point me to the random number generation in the source tree please. On 29 Sep 2009, at 08:19, Dima wrote: Welcome, ------------------------------------------------------------------------------ Come build with us! The BlackBerry® Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9-12, 2009. Register now! http://p.sf.net/sfu/devconf _______________________________________________ QuantLib-dev mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-dev |
Re: parallel programming open-MP
|
|
I'd look in the methods/montecarlo folder and see what you can potentially
parallelize in the path generating process. Would be interesting to see 2009/9/29 shoja <[hidden email]>
------------------------------------------------------------------------------ Come build with us! The BlackBerry® Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9-12, 2009. Register now! http://p.sf.net/sfu/devconf _______________________________________________ QuantLib-dev mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-dev |
Re: parallel programming open-MP
|
|
On Wed, 2009-09-30 at 16:43 +0200, Dima wrote:
> I'd look in the methods/montecarlo folder and see what you can > potentially parallelize in the path generating process. Last time I profiled it, the most time-expensive operation was converting uniform variates into Gaussian variates. Luigi -- Hofstadter's Law: It always takes longer than you expect, even when you take Hofstadter's Law into account. ------------------------------------------------------------------------------ Come build with us! The BlackBerry® Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9-12, 2009. Register now! http://p.sf.net/sfu/devconf _______________________________________________ QuantLib-dev mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-dev |
Re: parallel programming open-MP
|
|
So, this could be parallelized, no? I mean not the conversion. But since they are
indendent we could generate say 1000 variables in a parallel framework 2009/9/30 Luigi Ballabio <[hidden email]>
------------------------------------------------------------------------------ Come build with us! The BlackBerry® Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9-12, 2009. Register now! http://p.sf.net/sfu/devconf _______________________________________________ QuantLib-dev mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-dev |
Re: parallel programming open-MP
|
|
On Thu, 2009-10-01 at 08:42 +0200, Dima wrote:
> So, this could be parallelized, no? Yes. > I mean not the conversion. Not the internals of the conversion, you mean? > But since they are > indendent we could generate say 1000 variables in a parallel framework You mean "generate" as in "from scratch" (generate the uniform and transform) or as in "given N uniforms, transform them to normal in parallel"? The first might be harder to do across the different kinds of generator (pseudo-random, Sobol etc.) Luigi -- Within C++, there is a much smaller and cleaner language struggling to get out. -- Bjarne Stroustrup ------------------------------------------------------------------------------ Come build with us! The BlackBerry® Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9-12, 2009. Register now! http://p.sf.net/sfu/devconf _______________________________________________ QuantLib-dev mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-dev |
Re: parallel programming open-MP
|
|
In reply to this post by Mohammad shojatalab
On Tue, 2009-09-29 at 12:02 +0100, shoja wrote:
> Maybe both :) can you point me to the random number generation in the > source tree please. There's a number of pieces in <ql/math/randomnumbers>. Luigi -- Hanlon's Razor: Never attribute to malice that which is adequately explained by stupidity. ------------------------------------------------------------------------------ Come build with us! The BlackBerry® Developer Conference in SF, CA is the only developer event you need to attend this year. Jumpstart your developing skills, take BlackBerry mobile applications to market and stay ahead of the curve. Join us from November 9-12, 2009. Register now! http://p.sf.net/sfu/devconf _______________________________________________ QuantLib-dev mailing list [hidden email] https://lists.sourceforge.net/lists/listinfo/quantlib-dev |
«
Return to quantlib-dev
|
1 view|%1 views
| Free forum by Nabble | Edit this page |