[Beowulf] gpgpu

Mikhail Kuzminsky kus at free.net
Wed Aug 27 09:39:37 PDT 2008

In message from "Li, Bo" <libo at buaa.edu.cn> (Wed, 27 Aug 2008 08:50:11 
>IMHO, it is better to call the BLAS or similiar libarary rather than 
>programing you own functions.

Eh, I would be happy to use GPGPUs only via math libraries - it's 
equal for me to "black box" as Vincent said. But this libraries are 
too restricted for our purposes.

> And CUDA treats the GPU as a cluster, 
>so .CU is not working as our normal codes. If you have got to many 
>matrix or vector computation, it is better to use Brook+/CAL, which 
>can show great power of AMD gpu.

There is 2 possible interpretations of your word "better".

1) Brook+/CAL gives more high performance or price/performance etc
than Nvidia (hard+software)


2) It's simpler to program using Brook+/CAL.

What is the right interpretation ? BTW, is in necessary to use Brook+ 
w/CAL - or I may write the program using Brook+ WITHOUT using (and 
detailed knowledge) of CAL ?

I.e. I want to write the "subroutine" on brcc, compile and then link 
w/fortran program using some gcc function as a "wrapper" (for 
organizing of interface to fortran).


>Li, Bo
>----- Original Message ----- 
>From: "Mikhail Kuzminsky" <kus at free.net>
>To: "Vincent Diepeveen" <diep at xs4all.nl>
>Cc: "Beowulf" <beowulf at beowulf.org>
>Sent: Wednesday, August 27, 2008 2:35 AM
>Subject: Re: [Beowulf] gpgpu
>> In message from Vincent Diepeveen <diep at xs4all.nl> (Tue, 26 Aug 2008 
>> 00:30:30 +0200):
>>>Hi Mikhail,
>>>I'd say they're ok for black box 32 bits calculations that can do 
>>>a GB or 2 RAM,
>>>other than that they're just luxurious electric heating.
>> I also want to have simple blackbox, but 64-bit (Tesla C1060 or 
>> Firestream 9170 or 9250). Unfortunately the life isn't restricted to 
>> So I'll need to program something other. People say that the best 
>> choice is CUDA for Nvidia. When I look to sgemm source, it has about 
>> thousand (or higher) strings in *.cu files. Thereofore I think that 
>> bit more difficult alghorithm  as some special matrix 
>> will require a lot of programming work :-(.
>> It's interesting, that when I read Firestream Brook+ "kernel 
>> source example - for addition of 2 vectors ("Building a High Level 
>> Language Compiler For GPGPU",
>> Bixia Zheng (bixia.zheng at amd.com)
>> Derek Gladding (dereked.gladding at amd.com)
>> Micah Villmow (micah.villmow at amd.com)
>> June 8th, 2008)
>> - it looks SIMPLE. May be there are a lot of details/source lines 
>> which were omitted from this example ?
>>>p.s. if you ask me, honestely, 250 watt or so for latest gpu is 
>>>too much.
>> 250 W is TDP, the average value declared is about 160 W. I don't 
>> remember, which GPU - from AMD or Nvidia - has a lot of special 
>> functional units for sin/cos/exp/etc. If they are not used, may be 
>> power will a bit more lower.
>> What is about Firestream 9250, AMD says about 150 W (although I'm 
>> absolutely sure that it's TDP) - it's as for some 
>> Intel Xeon quad-cores chips w/names beginning from X.
>> Mikhail
>>>On Aug 23, 2008, at 10:31 PM, Mikhail Kuzminsky wrote:
>>>> BTW, why GPGPUs are considered as vector systems ?
>>>> Taking into account that GPGPUs contain many (equal) execution 
>>>> I think it might be not SIMD, but SPMD model. Or it depends from  
>>>> the software tools used (CUDA etc) ?
>>>> Mikhail Kuzminsky
>>>> Computer Assistance to Chemical Research Center
>>>> Zelinsky Institute of Organic Chemistry
>>>> Moscow
>>>> _______________________________________________
>>>> Beowulf mailing list, Beowulf at beowulf.org
>>>> To change your subscription (digest mode or unsubscribe) visit  
>>>> http://www.beowulf.org/mailman/listinfo/beowulf
>> _______________________________________________
>> Beowulf mailing list, Beowulf at beowulf.org
>> To change your subscription (digest mode or unsubscribe) visit 

More information about the Beowulf mailing list