Does the integration of Intel® Parallel Studio XE 2013 for Linux* and R lead to significant performance improvements? -


i running resource intensive computations in r. use for-loops, bootstrap simulations , on. have integrated intel® math kernel library linux* r , seems has lead significant improvement in computation times. thinking integrating intel® parallel studio xe 2013 linux* , r. means passing different compilers ship r:

(1) integration of intel® parallel studio xe 2013 linux* , r lead significant performance improvements?

(2) give examples in situations have benefit?

thank you!

very rough order of magnitude:

  • parallel / multi-core blas such mkl scale sublinearly in number of cores but parts of operations blas calls ie not basic "for-loops, bootstrap simulation , on"

  • byte-compiling r code may give factor of two, maybe three

  • after may need heavier weapons such example rcpp can give 50, 70, 90-fold speedups on code involving "for-loops, bootstrap simulation , on" why eg popular mcmc crowd

  • similarly, intel tbb , other parallel tricks require rewrites of code.

there no free lunch.


Comments

Popular posts from this blog

c++ - How to add Crypto++ library to Qt project -

jQuery Mobile app not scrolling in Firefox -

How to use vim as editor in Matlab GUI -