[concurrency-interest] help show speed-up on a trivial but manual array-map operation?

Dan Grossman djg at cs.washington.edu
Fri Mar 30 01:41:20 EDT 2012


Thanks, Stefan.  This is good advice and when I first wrote the page I
thought I would discuss issues like this, but I ended up not getting
into anything related to how to do the timing.  I'll keep it in mind
if I get questions about how to do timing.

--Dan

On Mon, Mar 26, 2012 at 6:58 AM, Stefan Marr
<concurrency-interest at stefan-marr.de> wrote:
> Hi Dan:
>
> On 25 Mar 2012, at 22:48, Dan Grossman wrote:
>
>> Just to close the loop on this thread, today I edited
>>
>> http://www.cs.washington.edu/homes/djg/teachingMaterials/spac/grossmanSPAC_forkJoinFramework.html
>>
>> which is part of the materials at
>>
>> http://www.cs.washington.edu/homes/djg/teachingMaterials/spac/
>>
>> I added a new section "timing issues" that lists various reasons why
>> you might see a /simple/ fork-join computation run slower than a
>> corresponding sequential implementation.  This distills the
>> suggestions on this thread and other well-known ideas.  Additional
>> suggestions and clarifications are welcome.
>
> An additional suggestion might be to use some 'established' benchmarking framework like http://code.google.com/p/caliper/
> They also list common pitfalls for benchmarking on the JVMs.
>
> Best regards
> Stefan
>
>
> --
> Stefan Marr
> Software Languages Lab
> Vrije Universiteit Brussel
> Pleinlaan 2 / B-1050 Brussels / Belgium
> http://soft.vub.ac.be/~smarr
> Phone: +32 2 629 2974
> Fax:   +32 2 629 3525
>



More information about the Concurrency-interest mailing list