We currently have a high-performance scientific application written in C++ that makes use of Intel Math Kernel Library. We are considering writing a benchmark application written in Java and...

I want to start to write applications(C++) that will utilize the additional cores to execute portions of the code that have a need to perform lots of calculations and whose computations are indepen...

Edit: The code here still has some bugs in it, and it could do better in the performance department, but instead of trying to fix this, for the record I took the problem over to the Intel discuss...