[Haskell-cafe] Re: Haskell performance in heavy numerical
Donald Bruce Stewart
dons at cse.unsw.edu.au
Mon Jul 10 07:23:30 EDT 2006
> Hello Simon,
> Monday, July 10, 2006, 1:12:13 PM, you wrote:
> >> numerical speed is poor in ghc 6.4, according to my tests. it's 10-20
> >> times worse than of gcc. afair, the mandelbrot benchmark of Great
> >> Language Shootout proves this - despite all optimization attempts,
> >> GHC entry is still 5-10 times slower than gcc/ocaml/clean ones
> > We average 1.3x slower than C in the shootout. Thanks to Don Stewart for
> > the following stats...
> as i once wrote, most of shootout benchmarks depends on the libs. for
> example, multi-threading benchmark is much faster on GHC than on GCC
> because former has user-level threads support pre-included and for
> later the external libs should be used (testing policy prohibits using
> of additional libs)
> > The numerical floating-point-intensive benchmarks:
> > mandelbrot 2.7x C (Clean 1.7x, OCaml 2.4x, C++ 2.6x)
> > n-body 2.1x C (Clean 0.9x, OCaml 1.3x, C++ 1.4x)
> that is the benchmarks that i had in mind
> > http://shootout.alioth.debian.org/gp4/benchmark.php?test=mandelbrot&lang=all
> the same benchmark with N=600 and Sempron processor:
> here GHC is 10x slower than GCC and more than 5 times compared to
> Clean and Ocaml. i think that this is the real computing speed
> difference while with N=2000 C/Ocaml/Clean programs was really limited
> by memory speed.
Ah! In this case, on the debian, the benchmark has been compiled
_without_ -fexcess-precision, that's what's causing the big slow down.
We had to turn it on, on the gp4, but it seems the flag wasn't
propagated to the debian/sempron builds for some reason.
Looks like the ghc/mandelbrot benchmarks just needs to be rerun with
-fexcess-precision in this case.
More information about the Haskell-Cafe