[BiO BB] Time execute blast and Memory

Mike Marchywka marchywka at hotmail.com
Fri Mar 23 18:15:35 EDT 2007


I'm not sure specifically what you want to know or what you already know but
to give you some ideas of what is fast/slow on Intel, take a look at some of 
these:

http://www.google.com/search?hl=en&q=ia32+optimization+memory+cache+site%3Aintel.com

Not all memory is the same and constant cache misses can slow things down a 
lot.
You could be amazed how important locality is to performance.



>From: Daniel Xavier de Sousa <danielucg at yahoo.com.br>
>Reply-To: "General Forum at Bioinformatics.Org" 
><bio_bulletin_board at bioinformatics.org>
>To: bio_bulletin_board at bioinformatics.org
>Subject: [BiO BB] Time execute blast and Memory
>Date: Fri, 23 Mar 2007 12:07:08 -0700 (PDT)
>
>Hi for all,
>
>
>
>
>
>I’m executing the BLAST  program and have knew stranger (I guess) time
>of execute with differences RAM memory.  Same with less memory, the 
>difference of total
>time between X memory and X/2 memory is little.
>
>
>
>Look:
>
>
>
>
>
>PROGRAM NCBI BLAST == DATABASE NR (1.8 GB)
>
>
>
>
>
>Memory                    *TIME          * I/O               *SWAP
>
>
>1 GB RAM              *0:03:01         *2610920        *9456
>
>
>512 MB RAM         *0:03:10         *2670376        *18128
>
>
>256 MB RAM         *0:03:35         *2713160        *21856
>
>
>128 MB RAM         *0:04:22         *2751120         *30640
>
>
>64 MB RAM           *0:05:30         *3050656         *64168
>
>
>
>
>
>PROGRAM WUBLAST1.4 == DATABASE NR (1.8 GB)
>
>
>Memory                     *TIME            *I/O                  *SWAP
>
>
>1 GB RAM              *0:12:14         *2496144              *0
>
>
>512 MB RAM         *0:13:37         *2500216              *0
>
>
>256 MB RAM         *0:13:29         *2502376              *1720
>
>
>128 MB RAM         *0:13:35         *2513432              *1760
>
>
>64 MB RAM           *0:13:57         *2546192              *51048
>
>
>
>
>
>The difference using more memory, must be better. For
>exempla, there is little difference using 1 GB and 512 MB for a database of
>1.8GB (NR). The little difference is more accentuated to WUblast 1.4 than 
>NCIBI
>BLAST.
>
>
>
>
>
>So, I want help to two things:
>
>
>1 – It results is normal, to WUBlast1.4 and NCBIBlast?
>
>
>2 – What can I do to get more difference when I change my
>RAM memory?
>
>
>
>
>
>
>
>
>Thank very much,
>
>
>Daniel
>
>*****************************************************************
>*        Daniel Xavier de Sousa                    *
>*        Mestrando em Informática - PUC-Rio        *
>*        E-MAIL : dsousaARROBAinf.puc-rio.br       *
>*        Fone   : +55 21 35271500 - 4543           *
>****************************************************************
>
>
>
>__________________________________________________
>Fale com seus amigos  de graça com o novo Yahoo! Messenger
>http://br.messenger.yahoo.com/
>_______________________________________________
>General Forum at Bioinformatics.Org - BiO_Bulletin_Board at bioinformatics.org
>https://bioinformatics.org/mailman/listinfo/bio_bulletin_board

_________________________________________________________________
Mortgage refinance is hot 1) Rates near 30-yr lows 2) Good credit get 
intro-rate 4.625%* 
https://www2.nextag.com/goto.jsp?product=100000035&url=%2fst.jsp&tm=y&search=mortgage_text_links_88_h2a5f&s=4056&p=5117&disc=y&vers=743




More information about the BBB mailing list