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
Post a Comment