Subject: Re: [ublas] Status of development /Benchmarks
From: Riccardo Rossi (rrossi_at_[hidden])
Date: 2013-12-09 11:26:07
just a brief comment again on OpenMP:
openmp IS compatible with c++, and a clang version exists already, although
it is not merged to the repository
On Mon, Dec 9, 2013 at 4:14 PM, Nasos Iliopoulos <nasos_i_at_[hidden]>wrote:
> I am not so sure the requirements for smal /large containers are so
> diverse. After all you can have compile-time dispatching for small (static)
> or large (dynamic) containers if you want to use different algorithms for
> each or for mixed cases. Can you please elaborate if I am not getting it
> On 12/09/2013 09:49 AM, Karl Rupp wrote:
>> Hi guys,
>> > the whole problem of most numerical packages, IMHO, is that everything
>>> is tied together. I would encourage a very loosely coupled system. I.e.,
>>> a system that maybe even would be able to switch storage layout,
>>> algorithms, etc., at run-time, maybe following some simple numerical
>>> tests. Of course, only if this would be enabled at compile-time.
>> From my experience with rebuilding the uBLAS interface within ViennaCL I
>> fully support this suggestion.
>> * the storage of data. This is about memory-efficiency, and hence, speed
>>> of computation. Storage engines might be linear, sparse, etc..
>>> * functional shape of the data. Dense, triangular, etc.
>>> * numerical properties of the data. Positive definite, etc.
>>> * loading and saving the data. Why not support a whole bunch of
>>> * unified matrix/vector view on the data
>>> * procedural manipulation of the data, shallow views on the data, views
>>> on views, etc.
>> One important question should be answered upfront: Should ublas focus on
>> linear algebra for 'small' vectors/matrices, or 'big' vectors/matrices? I
>> don't consider 'both' a legitimate answer here, because the two extremes
>> have highly diverse requirements:
>> - For 'small' data (say, 10x10) one goes with expression templates, just
>> because any additional runtime overhead is not acceptable.
>> - For 'large' data one can do a lot of tricks with respect to avoiding
>> memory transfers with some delayed execution techniques. Also, this is the
>> regime where one can slowly start to think about threads, accelerators,
>> etc. Most machine-specific metrics then become only available at runtime,
>> so one needs some runtime logic in addition to expression templates anyway.
>> One may even get rid of expression templates here and instead enjoy faster
>> compilation times and increased flexibility at runtime.
>> Just my 2 cents of course... :-)
>> Best regards,
>> ublas mailing list
>> Sent to: athanasios.iliopoulos.ctr.gr_at_[hidden]
> ublas mailing list
> Sent to: rrossi_at_[hidden]
-- Dr. Riccardo Rossi, Civil Engineer Member of Kratos Team International Center for Numerical Methods in Engineering - CIMNE Campus Norte, Edificio C1 c/ Gran CapitÃ¡n s/n 08034 Barcelona, EspaÃ±a Tel: (+34) 93 401 56 96 Fax: (+34) 93.401.6517 web: www.cimne.com