<t>After some direction from the Wilmott forums, we have parallelized the discrete hedging example in QuantLib, and got pretty good speed-up: almost 14X on a 16-core system.Here's the write-up: Multicore-enabling Discrete Hedging in QuantLibIt feels like Cilk++ lends itself well to taking a large li...

<t>After some direction from the Wilmott forums, we have parallelized the discrete hedging example in QuantLib, and got pretty good speed-up: almost 14X on a 16-core system.Here's the write-up: Multicore-enabling Discrete Hedging in QuantLibIt feels like Cilk++ lends itself well to taking a large li...

Thanks guys for the dialogue.Regarding Quantlib - is there a particular function and input data set that would be interesting?I ask because we're algorithms and parallel computing guys, but are novices with respect to what hard-core quants care about.thanks!ilya

<t>My sense is that in mainstream multicore programming for C/C++, it's currently a 4-horse race: Intel's TBB, OpenMP, Cilk++, and - soon - Microsoft's Concurrency Runtime platform.Each has pros and cons. For example, a library approach such as TBB works best for applications that have relatively di...

Some algorithms are in fact inherently serial, but others (for example, many Monte Carlo simulations) yield nicely to multithreading with Cilk++. We're looking for more good test cases, so we're interested in knowing which problems you consider both important and computationally expensive.

<t>I am looking for a compute-intensive C/C++ algorithm to multithread using the recently released Cilk++ programming platform (targeted at multicore programming, in particular bringing serial algorithms into the multicore realm).Any advice, or interest in playing around with the download?thanks in ...

<t>I am looking for a compute-intensive C/C++ algorithm to multithread using the recently released Cilk++ programming platform (targeted at multicore programming, in particular bringing serial algorithms into the multicore realm).Any advice, or interest in playing around with the (free) download?tha...

<r>Hi Daniel,We have a bunch of complete examples here: <URL url="http://www.cilk.com/resources-for-multicoders/for-developers-only/Cilk"><LINK_TEXT text="http://www.cilk.com/resources-for-multi ... -only/Cilk">http://www.cilk.com/resources-for-multicoders/for-developers-only/Cilk</LINK_TEXT></URL>+...

<t>QuoteOriginally posted by: CuchulainnIlya,Here is a 101 program in OpenMP to do some vector manipulation. How does the corresponding code look like in your product?test This snippet works but not in the expected way #pragma omp parallel for for(int j=0; j < (int)vec.size(); ++j) { cout << "vec[" ...

thanks Daniel - we'll take a look and report back.

<r>QuoteOriginally posted by: crosshatchI would start with some simple barebone examples:- The obvious is a Monte-Carlo example: Price a (path dependent) option by breaking the paths up using a "cilk_for". - Price an american option using (recursive) binomial trees using "cilk_spawn" and "cilk_sync"...

<r>Daniel - I should have also mentioned this page - we've made the alpha documentation and examples public: <URL url="http://www.cilk.com/resources-for-multicoders/for-developers-only/"><LINK_TEXT text="http://www.cilk.com/resources-for-multi ... pers-only/">http://www.cilk.com/resources-for-multic...

<r>Hi Daniel,Relative to OpenMP:1. Cilk++ has nested parallelism that works and provides guaranteed speed-up. OpenMP has nested parallelism, but it is a memory hog and not reliable.2. Cilk++ guarantees space bounds. On P processors, Cilk++ uses no more than P times the space of a serial execution. I...

<t>I am looking to multicore-enable a couple C++ algorithms with our tool (Cilk++).Is there a pointer to an algorithm or two (and if possible data set) that might be an interesting application to speed up using multicore processors?Would the QuantLib library be a good place to start?thanks in advanc...