Was this with tossing the partial sums code into the optimised bangs program? Weird. I wonder if profiling will help explain why? In any case, If nobody comes up with any other tweaks, I'll probably submit the optimised bangs version to the shootout this weekend.

--S

On Nov 30, 2007 1:30 PM, Richard Kelsall <r.kelsall@millstream.com> wrote:
Sterling Clover wrote:
> I'm still curious if the pre-calculation of partial sums that I did
> works well across processors, as I don't see why it shouldn't. My
> less-strictified version of Don's code is attached, and below are the
> functions you'll need to insert/replace to make the partial-sums
> optimization work.

Hello Sterling, I've timed your new Fasta with optimised bangs - it's
the fastest so far. But the pre-calculated partial-sums version seems
to go a bit slower for some unknown reason.

                          Seconds
Optimised bangs program    11.20    compiled ghc --make
Optimised bangs program    10.73    compiled with -O -fglasgow-exts
                                       -optc-mfpmath=sse -optc-msse2
                                       -optc-march=pentium4
Partial-sums program       11.97    compiled ghc --make
Partial-sums program       11.14    compiled with -O -fglasgow-exts
                                       -optc-mfpmath=sse -optc-msse2
                                       -optc-march=pentium4

This is on my GHC 6.6.1, W2K, Intel Core 2 Duo 2.33GHz machine - same
as for the previous timings I gave in this thread.


Richard.