I've used TBB to the some extent (but not on a quant project). Don't know about "Task Parallel Lib", so I cannot compare here. Basically, TBB is OK for expressing task-level parallelism in situations when one want/has to go with C++; however, most people in HPC community are sticking with C or Fortran for their work, so pthreads or OpenMP are much more used. On the other side, TBB is mostly thin wrapper around native threading libraries, so performance-wise is on the similar level as these libraries.
Btw, if you get into TBB, then you may also get interested in Array Building Blocks, which is C++ library by Intel (arisen from their failed Larrabee project, and then also from the acquisition of Rapidmind guys) for expressing data-level parallelism, and is intended to challenge GPGPU approach. Lots of parallel development tools fighting for its market segment, it's going to be interesting to see which ones are going to prevail in coming years...
This site uses cookies to help personalise content, tailor your experience and to keep you logged in if you register.
By continuing to use this site, you are consenting to our use of cookies.