[R-SIG-Mac]timing R and R and R and R

[Jan de Leeuw]

ATLAS is a portable fast BLAS (basic linear algebra subroutines),
which itself is a library of elementary linear algebra routines.
LAPACK consists of more elaborate linear algebra routines
build on top of the BLAS. It is possible to optimize the BLAS
for the system that it will be running on at compile time. I dont
know the details, but ATLAS does an enormous number of compile
time checks and optimizations, which can result in a major
speed increase in linear algebra computations.

The answer to the second question is probably "no".

On Thursday, November 15, 2001, at 12:34 , David J. Braden wrote:

> Forgive me, please, for my ignorance, but what is ATLAS?
>
> Also, is there a repository for solid empirics on how our various 
> systems
> fare with R?
>
> TIA, big time.
> Dave Braden
>
>> It may also be ATLAS that causes some of the 40% speed increase.
>>
>> On Tuesday, November 13, 2001, at 11:34 AM, Thomas Lumley wrote:
>>
>>> On Tue, 13 Nov 2001, David A Richmond wrote:
>>>
>>>> I am moving away from os9 and doing as much as I possibly can in
>>>> osX. I am going to abandon 9 completely as soon as it is feasible for
>>>> me
>>>> to do everything I need to do in X. What I would like to see most 
>>>> is a
>>>> Cocoa version of R. It is my understanding that Carbon is nice for
>>>> cross-OS compatibility, but ultimately Cocoa is the API of choice.
>>>> Would I
>>>> be correct in assuming that performance differences Jan found would
>>>> also
>>>> be seen between a Carbon app and a Cocoa app?
>>>
>>> I don't think we know. It's a reasonable guess, but there could be 
>>> user
>>> interface overhead.
>>>
>>> The difference is suprisingly large given that (IIRC) R runs with 
>>> almost
>>> the same speed under Windows and Linux on the same hardware.
>>>
>>>
>>> -thomas
>>>
>>> _______________________________________________
>>> R-SIG-Mac mailing list
>>> R-SIG-Mac@stat.math.ethz.ch
>>> http://www.stat.math.ethz.ch/mailman/listinfo/r-sig-mac
>>>
>>>
>> ===
>> Jan de Leeuw; Professor and Chair, UCLA Department of Statistics
>> US mail: 8142 Math Sciences Bldg, Box 951554, Los Angeles, CA 
>> 90095-1554
>> phone (310)-825-9550;  fax (310)-206-5658;  email: 
>> deleeuw@stat.ucla.edu
>>                 www: http://www.stat.ucla.edu/~deleeuw
>> ========================================================================
>> ==
>> ==
>>         Remember, wherever you go, there you are. --- Buckaroo Banzai
>> ========================================================================
>> ==
>> ==
>>
>> _______________________________________________
>> R-SIG-Mac mailing list
>> R-SIG-Mac@stat.math.ethz.ch
>> http://www.stat.math.ethz.ch/mailman/listinfo/r-sig-mac
>
> --
>
>
> _______________________________________________
> R-SIG-Mac mailing list
> R-SIG-Mac@stat.math.ethz.ch
> http://www.stat.math.ethz.ch/mailman/listinfo/r-sig-mac
>
>
===
Jan de Leeuw; Professor and Chair, UCLA Department of Statistics;
US mail: 9432 Boelter Hall, Box 951554, Los Angeles, CA 90095-1554
phone (310)-825-9550;  fax (310)-206-5658;  email: deleeuw@stat.ucla.edu
homepage: http://www.stat.ucla.edu/~deleeuw
========================================================
           No matter where you go, there you are. --- Buckaroo Banzai
                    http://www.stat.ucla.edu/~deleeuw/sounds/nomatter.au
========================================================