Re: [Boost-users] R: R: [multi-array] Performance? Difference from GIL or uBLAS?

From: Mike Marchywka (marchywka_at_[hidden])
Date: 2008-08-09 15:54:49

>> All the GIL examples I saw use iterators and what I liked is that
>> complicated image calculations can be stacked. If I have to flip the an
>> image and convert it to B/W then traditionally I would do that in two steps,
>> with Gil you do that in one step only, with nearly double performance.
>>

I was going to reply earlier but since you touched on the issues I wanted
to mention, let me just suggest that cache awareness be considered
as a null inner loops has no obvious performance relationship to something that
just writes a constant into incrementing addresses. Any iterator that preserves
locality and anything that reduces the number of "passes" can easily pay for some overhead,
especially of order zero ( some setup calculations that determine things
like block sizes etc but don't get repeated during iteration).

I don't have links handy but I think that FFTW has a lot of related literature
on performanc issues and, again, Intel has a lot of good optimization references
on their site for their processors.

> Are there performance measurements for GIL?
>
> GIL uses Locators, which I love. GIL seems to be stuck on arrays that
> are an 'image' of 'pixels', which is not always the case for me.
> Ideally I would be able to construct an array of any type.
>
> I was looking into multi_array hoping there would be some analogy to GIL
> / Locators, but multi_array seems to be mimicking aspects of the syntax
> used in Fortran, Matlab, or Python. That's great from a high level
> point of view, but I am a bit afraid because I don't understand the
> performance implications.
>
> I think that in the spirit of 'zero overhead', there should be some
> boost requirement that certain libraries include performance
> measurements / graphs as part of their docs or build process. For
> things like multi_array or uBLAS or GIL, I think efficiency is
> important (not just asymptotic).
>
> For example, I would feel more comfortable if I could see something
> like: http://www.oonumerics.org/blitz/benchmarks/
>
> (The only reason I don't wanna use BLITZ is that the last release was 2005)
>
> --John
>
> _______________________________________________
> Boost-users mailing list
> Boost-users_at_[hidden]
> http://lists.boost.org/mailman/listinfo.cgi/boost-users

_________________________________________________________________
Get more from your digital life.  Find out how.
http://www.windowslive.com/default.html?ocid=TXT_TAGLM_WL_Home2_082008