There's a sort.h library you should be able to include that will have quick sort + many others, and will allow the compiler to properly inline functions. https://github.com/swenson/sort (disclaimer: I wrote it). I get about a 10x speed improvement over qsort just for the ability to inline functions.
I've never used it with Cython, but I don't believe there should be any problems doing so. On Nov 23, 2014 10:11 AM, "Francesco Biscani" <bluesca...@gmail.com> wrote: > On 23 November 2014 at 19:05, Thierry Dumont <tdum...@math.univ-lyon1.fr> > wrote: >> >> Is gprof enough powerful with modern architectures on such programs? from >> my point of view, no. >> There are non free, commercial, tools like vtune which can do fantastic >> measurement job. Vtune shows, for example, that a call to std::copy is not >> as fast as a for loop, which is turned by the compiler in a memcopy >> (probably std::copy is not!). I do not think we can see this with gprof. >> But ok, you are not supposed to buy vtune... >> > > I would be surprised if any modern c++ library implementation does not > have specialisations of std::copy for POD types that use memcpy() or some > other trick. > > >> What about likwid https://code.google.com/p/likwid ? It is free. Did >> somebody used it to measure cython code performances? >> >> Likwid (and Vtune) have in common to use performance counters on Intel >> and AMD processors (not sure for AMD with Vtune...). >> >> What is the size of what you are sorting ? If it is small enough to fit >> in the caches, and better in the L1 cache, you can possibly improve >> something with your modification, but otherwise it is certainly memory >> bounded and you cannot do much... >> You have to measure the bandwidth of your program. Vtune does this, >> possibly likwid too. >> > > I used callgrind() in the past with some success... I would like to try > the google cpu profiler to see how it fares, but I haven't had the chance > yet. > > -- > You received this message because you are subscribed to the Google Groups > "sage-devel" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to sage-devel+unsubscr...@googlegroups.com. > To post to this group, send email to sage-devel@googlegroups.com. > Visit this group at http://groups.google.com/group/sage-devel. > For more options, visit https://groups.google.com/d/optout. > -- You received this message because you are subscribed to the Google Groups "sage-devel" group. To unsubscribe from this group and stop receiving emails from it, send an email to sage-devel+unsubscr...@googlegroups.com. To post to this group, send email to sage-devel@googlegroups.com. Visit this group at http://groups.google.com/group/sage-devel. For more options, visit https://groups.google.com/d/optout.
