[Bioclusters] RE: Bioclusters digest, Vol 1 #225 - 12 msgs
Bourgeois, Andre
bioclusters@bioinformatics.org
Thu, 6 Mar 2003 11:59:11 -0500
This message is in MIME format. Since your mail reader does not understand
this format, some or all of this message may not be legible.
------_=_NextPart_001_01C2E401.B5CB3950
Content-Type: text/plain
Please unsubscribe me andre.bourgeois@veridian.com
Thanks you,
Andre
-----Original Message-----
From: bioclusters-request@bioinformatics.org
[mailto:bioclusters-request@bioinformatics.org]
Sent: Thursday, March 06, 2003 11:49 AM
To: bioclusters@bioinformatics.org
Subject: Bioclusters digest, Vol 1 #225 - 12 msgs
Send Bioclusters mailing list submissions to
bioclusters@bioinformatics.org
To subscribe or unsubscribe via the World Wide Web, visit
https://bioinformatics.org/mailman/listinfo/bioclusters
or, via email, send a message with subject or body 'help' to
bioclusters-request@bioinformatics.org
You can reach the person managing the list at
bioclusters-admin@bioinformatics.org
When replying, please edit your Subject line so it is more specific
than "Re: Contents of Bioclusters digest..."
Today's Topics:
1. Re: mpiBLAST compile error (Jones George)
2. Re: mpiBLAST compile error (Pamela Culpepper)
3. Re: mpiBLAST compile error (Joe Landman)
4. Re: mpiBLAST compile error (Steve Pittard)
5. what motherboards are people using for dual Athlon boxes? (Chris
Dagdigian)
6. Re: what motherboards are people using for dual
Athlon boxes? (Joseph Landman)
7. Re: what motherboards are people using for dual Athlon boxes? (Borries
Demeler)
8. RE: what motherboards are people using for dual Athlon boxes? (Steve
Gaudet)
9. Re: what motherboards are people using for dual Athlon boxes? (William
Park)
10. RE: what motherboards are people using for dual
Athlon boxes? (Joseph Landman)
--__--__--
Message: 1
Date: Wed, 05 Mar 2003 14:08:30 -0500
From: "Jones George" <JBGeorge@wyeth.com>
To: <bioclusters@bioinformatics.org>
Subject: Re: [Bioclusters] mpiBLAST compile error
Reply-To: bioclusters@bioinformatics.org
Hello,
Does anyone know where I can get the complete NCBI ToolKit=20
that contains these header files:
xmlblast.h, mblast.h, objblst3.h, netblap3.h
Thanks,
Jones
>>> JBGeorge@wyeth.com 03/03/03 01:43PM >>>
Joe,
I found the RPM at:
http://rpmfind.net/linux/RPM/contrib/libc6/i386/ncbi-6.0-1.i386.html=20
I will try installing the direct toolkit.. will update on how it goes..
-Jones
>>> landman@scalableinformatics.com 02/28/03 05:22PM >>>
Hi Jones:
Either from the direct toolkit, or I can craft a source RPM to go =
with=20
my binary RPMs (http://scalableinformatics.com/downloads/). Where did=20
you get the blast RPM BTW?
Joe
Jones George wrote:
> Joe,
> Thanks for the clarification.
>=20
> I do not have this file on the system.. anywhere...
>=20
> i do not have: xmlblast.h, mblast.h, objblst3.h, netblap3.h
>=20
> I am trying to understand why they are not part of:
>=20
> ncbi-6.0-1 RPM...
>=20
> Maybe I need to reinstall install the toolkit from some other source..
>=20
> any recommendations?
>=20
> Thanks,
> jones
>=20
>=20
>=20
>=20
>>>>landman@scalableinformatics.com 02/28/03 04:56PM >>>
>=20
> Jones:
>=20
> These are not libraries, but C header files. On your system, try
>=20
> locate xmlblast.h
>=20
> and see if you see it anywhere. If so, add a pointer to this file in=20
> your Makefile.
>=20
> -I/path/to/include/files
>=20
> along with the other paths that they have there for include directories.
>=20
> Joe
>=20
> --
> Joseph Landman, Ph.D
> Scalable Informatics LLC,
> email: landman@scalableinformatics.com=20
> web : http://scalableinformatics.com=20
> phone: +1 734 612 4615
>=20
> Jones George wrote:
>=20
>>I understand.. but I installed the RPM
>>and these 4 libs were not installed.
>>I cannot find them anywhere in the system.
>>
>>
>>
>>>>>landman@scalableinformatics.com 02/28/03 04:30PM >>>
>>
>>These files are located in ncbi/include/ from the toolkit source.
>>
>>
>>
>>_______________________________________________
>>Bioclusters maillist - Bioclusters@bioinformatics.org=20
>>https://bioinformatics.org/mailman/listinfo/bioclusters=20
>>
>>_______________________________________________
>>Bioclusters maillist - Bioclusters@bioinformatics.org=20
>>https://bioinformatics.org/mailman/listinfo/bioclusters=20
>=20
>=20
>=20
> _______________________________________________
> Bioclusters maillist - Bioclusters@bioinformatics.org=20
> https://bioinformatics.org/mailman/listinfo/bioclusters=20
>=20
> _______________________________________________
> Bioclusters maillist - Bioclusters@bioinformatics.org=20
> https://bioinformatics.org/mailman/listinfo/bioclusters=20
--=20
Joseph Landman, Ph.D
Scalable Informatics LLC,
email: landman@scalableinformatics.com=20
web : http://scalableinformatics.com=20
phone: +1 734 612 4615
_______________________________________________
Bioclusters maillist - Bioclusters@bioinformatics.org=20
https://bioinformatics.org/mailman/listinfo/bioclusters=20
_______________________________________________
Bioclusters maillist - Bioclusters@bioinformatics.org=20
https://bioinformatics.org/mailman/listinfo/bioclusters
--__--__--
Message: 2
Date: Wed, 05 Mar 2003 15:43:47 -0600
From: Pamela Culpepper <pac@bcm.tmc.edu>
Organization: Baylor College of Medicine
To: bioclusters@bioinformatics.org
Subject: Re: [Bioclusters] mpiBLAST compile error
Reply-To: bioclusters@bioinformatics.org
Get the NCBI C language toolbox from the NCBI ftp site.
They are in the include directory.
If you need help compiling, I am very familiar with the insanities of
this approach.
Pam Culpepper
Sr. Systems Programmer
Biomedical Computing Facility
Baylor College of Medicine
Jones George wrote:
>Hello,
>
>Does anyone know where I can get the complete NCBI ToolKit
>that contains these header files:
>
>xmlblast.h, mblast.h, objblst3.h, netblap3.h
>
>
>Thanks,
>Jones
>
>
>
>
>>>>JBGeorge@wyeth.com 03/03/03 01:43PM >>>
>>>>
>>>>
>Joe,
>
>I found the RPM at:
>
>http://rpmfind.net/linux/RPM/contrib/libc6/i386/ncbi-6.0-1.i386.html
>
>I will try installing the direct toolkit.. will update on how it goes..
>
>-Jones
>
>
>
>>>>landman@scalableinformatics.com 02/28/03 05:22PM >>>
>>>>
>>>>
>Hi Jones:
>
> Either from the direct toolkit, or I can craft a source RPM to go with
>my binary RPMs (http://scalableinformatics.com/downloads/). Where did
>you get the blast RPM BTW?
>
>Joe
>
>Jones George wrote:
>
>
>>Joe,
>>Thanks for the clarification.
>>
>>I do not have this file on the system.. anywhere...
>>
>>i do not have: xmlblast.h, mblast.h, objblst3.h, netblap3.h
>>
>>I am trying to understand why they are not part of:
>>
>>ncbi-6.0-1 RPM...
>>
>>Maybe I need to reinstall install the toolkit from some other source..
>>
>>any recommendations?
>>
>>Thanks,
>>jones
>>
>>
>>
>>
>>
>>
>>>>>landman@scalableinformatics.com 02/28/03 04:56PM >>>
>>>>>
>>>>>
>>Jones:
>>
>> These are not libraries, but C header files. On your system, try
>>
>> locate xmlblast.h
>>
>>and see if you see it anywhere. If so, add a pointer to this file in
>>your Makefile.
>>
>> -I/path/to/include/files
>>
>>along with the other paths that they have there for include directories.
>>
>>Joe
>>
>>--
>>Joseph Landman, Ph.D
>>Scalable Informatics LLC,
>>email: landman@scalableinformatics.com
>>web : http://scalableinformatics.com
>>phone: +1 734 612 4615
>>
>>Jones George wrote:
>>
>>
>>
>>>I understand.. but I installed the RPM
>>>and these 4 libs were not installed.
>>>I cannot find them anywhere in the system.
>>>
>>>
>>>
>>>
>>>
>>>>>>landman@scalableinformatics.com 02/28/03 04:30PM >>>
>>>>>>
>>>>>>
>>>These files are located in ncbi/include/ from the toolkit source.
>>>
>>>
>>>
>>>_______________________________________________
>>>Bioclusters maillist - Bioclusters@bioinformatics.org
>>>https://bioinformatics.org/mailman/listinfo/bioclusters
>>>
>>>_______________________________________________
>>>Bioclusters maillist - Bioclusters@bioinformatics.org
>>>https://bioinformatics.org/mailman/listinfo/bioclusters
>>>
>>>
>>
>>_______________________________________________
>>Bioclusters maillist - Bioclusters@bioinformatics.org
>>https://bioinformatics.org/mailman/listinfo/bioclusters
>>
>>_______________________________________________
>>Bioclusters maillist - Bioclusters@bioinformatics.org
>>https://bioinformatics.org/mailman/listinfo/bioclusters
>>
>>
>
>
>
--__--__--
Message: 3
Subject: Re: [Bioclusters] mpiBLAST compile error
From: Joe Landman <landman@scalableinformatics.com>
To: bioclusters@bioinformatics.org
Organization:
Date: 05 Mar 2003 16:49:24 -0500
Reply-To: bioclusters@bioinformatics.org
ftp://ftp.ncbi.nlm.nih.gov/toolbox/ncbi_tools/ncbi.tar.Z
On Wed, 2003-03-05 at 14:08, Jones George wrote:
> Hello,
>
> Does anyone know where I can get the complete NCBI ToolKit
> that contains these header files:
>
> xmlblast.h, mblast.h, objblst3.h, netblap3.h
>
>
> Thanks,
> Jones
>
>
> >>> JBGeorge@wyeth.com 03/03/03 01:43PM >>>
> Joe,
>
> I found the RPM at:
>
> http://rpmfind.net/linux/RPM/contrib/libc6/i386/ncbi-6.0-1.i386.html
>
> I will try installing the direct toolkit.. will update on how it goes..
>
> -Jones
>
> >>> landman@scalableinformatics.com 02/28/03 05:22PM >>>
> Hi Jones:
>
> Either from the direct toolkit, or I can craft a source RPM to go with
> my binary RPMs (http://scalableinformatics.com/downloads/). Where did
> you get the blast RPM BTW?
>
> Joe
>
> Jones George wrote:
> > Joe,
> > Thanks for the clarification.
> >
> > I do not have this file on the system.. anywhere...
> >
> > i do not have: xmlblast.h, mblast.h, objblst3.h, netblap3.h
> >
> > I am trying to understand why they are not part of:
> >
> > ncbi-6.0-1 RPM...
> >
> > Maybe I need to reinstall install the toolkit from some other source..
> >
> > any recommendations?
> >
> > Thanks,
> > jones
> >
> >
> >
> >
> >>>>landman@scalableinformatics.com 02/28/03 04:56PM >>>
> >
> > Jones:
> >
> > These are not libraries, but C header files. On your system, try
> >
> > locate xmlblast.h
> >
> > and see if you see it anywhere. If so, add a pointer to this file in
> > your Makefile.
> >
> > -I/path/to/include/files
> >
> > along with the other paths that they have there for include directories.
> >
> > Joe
> >
> > --
> > Joseph Landman, Ph.D
> > Scalable Informatics LLC,
> > email: landman@scalableinformatics.com
> > web : http://scalableinformatics.com
> > phone: +1 734 612 4615
> >
> > Jones George wrote:
> >
> >>I understand.. but I installed the RPM
> >>and these 4 libs were not installed.
> >>I cannot find them anywhere in the system.
> >>
> >>
> >>
> >>>>>landman@scalableinformatics.com 02/28/03 04:30PM >>>
> >>
> >>These files are located in ncbi/include/ from the toolkit source.
> >>
> >>
> >>
> >>_______________________________________________
> >>Bioclusters maillist - Bioclusters@bioinformatics.org
> >>https://bioinformatics.org/mailman/listinfo/bioclusters
> >>
> >>_______________________________________________
> >>Bioclusters maillist - Bioclusters@bioinformatics.org
> >>https://bioinformatics.org/mailman/listinfo/bioclusters
> >
> >
> >
> > _______________________________________________
> > Bioclusters maillist - Bioclusters@bioinformatics.org
> > https://bioinformatics.org/mailman/listinfo/bioclusters
> >
> > _______________________________________________
> > Bioclusters maillist - Bioclusters@bioinformatics.org
> > https://bioinformatics.org/mailman/listinfo/bioclusters
--
Joseph Landman, Ph.D
Scalable Informatics LLC,
email: landman@scalableinformatics.com
web : http://scalableinformatics.com
phone: +1 734 612 4615
--__--__--
Message: 4
Date: Wed, 5 Mar 2003 17:13:07 -0500 (EST)
From: Steve Pittard <wsp@emory.edu>
To: bioclusters@bioinformatics.org
Subject: Re: [Bioclusters] mpiBLAST compile error
Reply-To: bioclusters@bioinformatics.org
so, get the NCBI toolkit and unpack it in , for example,
/var/tmp. I have /var/tmp/ncbi. I put mpiBLAST
in /opt/mpiBLAST and from that dir I do
$ ./configure --with-ncbi=/var/tmp/ncbi --prefix=/usr/local/mpiblast
This should build the config with a knowledge of the location
of the NCBI files.
$ make
$ make -n install (to see what it will do without actually doing it)
$ make install
Steve Pittard | http://catalina.bimcore.emory.edu (HOME PAGE)
Emory University | wsp@emory.edu, wsp@bimcore.emory.edu (INTERNET)
BIMCORE Support | 404 727 0038
--__--__--
Message: 5
Date: Wed, 05 Mar 2003 17:54:19 -0500
From: Chris Dagdigian <dag@sonsorol.org>
To: bioclusters@bioinformatics.org
Subject: [Bioclusters] what motherboards are people using for dual Athlon
boxes?
Reply-To: bioclusters@bioinformatics.org
Hi folks,
Anyone using anything other than Tyan mainboards for dual-AMD cluster
systems? Anyone with happy/unhappy motherboard related issues with
AMD-based systems?
I've got a client who is looking at a bunch of vendor proposals for
2.8ghz dual-Xeon cluster systems and several for dual Athlon MP2600+
systems. One vendor is even quoting MP2800+ cpus which do not seem to be
officially released yet in volume from AMD. heh.
Personally I've never had problems with Tyan but the customer has had
Tyan-related mainboard issues in the past and in general seems to feel a
slight sense of unease in that 100% of the Athlon-based proposals so far
are using Tyan boards. They are wondering if there are any serious
non-Tyan mainboards available that are suitable for dual-AMD use in a
technical computing environment. I'm guessing choice is pretty limited.
What are people here using? Any recommendations? Are the current
generation dual-AMD server boards from Tyan giving anyone problems?
Booards that I've seen in some the proposals:
Compute nodes: (Tyan S2722) & (Tyan S2466N-4M)
Head nodes : (Tyan S2469) & (Tyan S2466N-4M)
Regards,
Chris
--
Chris Dagdigian, <dag@sonsorol.org>
BioTeam Inc. - Independent Bio-IT & Informatics consulting
Office: 617-666-6454, Mobile: 617-877-5498, Fax: 425-699-0193
PGP KeyID: 83D4310E Yahoo IM: craffi Web: http://bioteam.net
--__--__--
Message: 6
Subject: Re: [Bioclusters] what motherboards are people using for dual
Athlon boxes?
From: Joseph Landman <landman@scalableinformatics.com>
To: biocluster <bioclusters@bioinformatics.org>
Organization:
Date: 05 Mar 2003 18:53:47 -0500
Reply-To: bioclusters@bioinformatics.org
There are several, though they lack some of the Tyan "features"
http://networking.gigabyte.com.tw/Products/Products_ServerBoard_Spec.asp?Pro
ductID=83
http://www.iwillusa.com/products/ProductDetail.asp?vID=19
http://www.msicomputer.com/product/detail_spec/product_detail.asp?model=K7D_
Master_L
The gigabyte looks good. I am building a test unit with it.
BTW: on a single CPU machine, the Asus nForce2 gives a nice dual
channel to ram. Without working at it, streams is reporting in the mid
1.1GB/s for triad. BLAST is latency bound, but having lots of memory
bandwidth is great for the chemistry codes. The MPX760 based chipsets
have hit 600-700 MB/s. The KT266a have hit about 800-900 MB/s.
Not exactly a server MB, but interesting in its own right.
On Wed, 2003-03-05 at 17:54, Chris Dagdigian wrote:
> Hi folks,
>
> Anyone using anything other than Tyan mainboards for dual-AMD cluster
> systems? Anyone with happy/unhappy motherboard related issues with
> AMD-based systems?
>
> I've got a client who is looking at a bunch of vendor proposals for
> 2.8ghz dual-Xeon cluster systems and several for dual Athlon MP2600+
> systems. One vendor is even quoting MP2800+ cpus which do not seem to be
> officially released yet in volume from AMD. heh.
>
> Personally I've never had problems with Tyan but the customer has had
> Tyan-related mainboard issues in the past and in general seems to feel a
> slight sense of unease in that 100% of the Athlon-based proposals so far
> are using Tyan boards. They are wondering if there are any serious
> non-Tyan mainboards available that are suitable for dual-AMD use in a
> technical computing environment. I'm guessing choice is pretty limited.
>
> What are people here using? Any recommendations? Are the current
> generation dual-AMD server boards from Tyan giving anyone problems?
>
> Booards that I've seen in some the proposals:
>
> Compute nodes: (Tyan S2722) & (Tyan S2466N-4M)
> Head nodes : (Tyan S2469) & (Tyan S2466N-4M)
>
>
> Regards,
> Chris
--
Joseph Landman <landman@scalableinformatics.com>
--__--__--
Message: 7
From: Borries Demeler <demeler@bioc09.v19.uthscsa.edu>
Subject: Re: [Bioclusters] what motherboards are people using for dual
Athlon boxes?
To: bioclusters@bioinformatics.org
Date: Wed, 5 Mar 2003 18:21:10 -0600 (CST)
Reply-To: bioclusters@bioinformatics.org
We have bought three Tyan MB's for testing about a year ago and
had lots of stability problems with them until bios upgrades
fixed most of the problems. Never had a single problem with
the Asus boards, and we have since built 2 clusters using the
Asus boards, and are very happy with both performance and stability.
They also don't seem to be too picky about the memory, we've
been able to run the cheap generic stuff in one of them we use for
video processing.
Maybe it's just having been lucky, but I would recommend going
with the Asus.
-Borries
>
>
> Hi folks,
>
> Anyone using anything other than Tyan mainboards for dual-AMD cluster
> systems? Anyone with happy/unhappy motherboard related issues with
> AMD-based systems?
>
> I've got a client who is looking at a bunch of vendor proposals for
> 2.8ghz dual-Xeon cluster systems and several for dual Athlon MP2600+
> systems. One vendor is even quoting MP2800+ cpus which do not seem to be
> officially released yet in volume from AMD. heh.
>
> Personally I've never had problems with Tyan but the customer has had
> Tyan-related mainboard issues in the past and in general seems to feel a
> slight sense of unease in that 100% of the Athlon-based proposals so far
> are using Tyan boards. They are wondering if there are any serious
> non-Tyan mainboards available that are suitable for dual-AMD use in a
> technical computing environment. I'm guessing choice is pretty limited.
>
> What are people here using? Any recommendations? Are the current
> generation dual-AMD server boards from Tyan giving anyone problems?
>
> Booards that I've seen in some the proposals:
>
> Compute nodes: (Tyan S2722) & (Tyan S2466N-4M)
> Head nodes : (Tyan S2469) & (Tyan S2466N-4M)
>
>
> Regards,
> Chris
>
>
> --
> Chris Dagdigian, <dag@sonsorol.org>
> BioTeam Inc. - Independent Bio-IT & Informatics consulting
> Office: 617-666-6454, Mobile: 617-877-5498, Fax: 425-699-0193
> PGP KeyID: 83D4310E Yahoo IM: craffi Web: http://bioteam.net
>
> _______________________________________________
> Bioclusters maillist - Bioclusters@bioinformatics.org
> https://bioinformatics.org/mailman/listinfo/bioclusters
>
--__--__--
Message: 8
From: "Steve Gaudet" <sgaudet@wildopensource.com>
To: <bioclusters@bioinformatics.org>, <dag@sonsorol.org>
Subject: RE: [Bioclusters] what motherboards are people using for dual
Athlon boxes?
Date: Thu, 6 Mar 2003 09:28:33 -0500
Reply-To: bioclusters@bioinformatics.org
Hello Chris,
> Anyone using anything other than Tyan mainboards for dual-AMD cluster
> systems? Anyone with happy/unhappy motherboard related issues with
> AMD-based systems?
>
> I've got a client who is looking at a bunch of vendor proposals for
> 2.8ghz dual-Xeon cluster systems and several for dual Athlon MP2600+
> systems. One vendor is even quoting MP2800+ cpus which do not
> seem to be officially released yet in volume from AMD. heh.
>
> Personally I've never had problems with Tyan but the customer has had
> Tyan-related mainboard issues in the past and in general
> seems to feel a slight sense of unease in that 100% of the Athlon-based
> proposals so far are using Tyan boards. They are wondering if there are
any serious
> non-Tyan mainboards available that are suitable for dual-AMD use in a
> technical computing environment. I'm guessing choice is pretty limited.
>
> What are people here using? Any recommendations? Are the current
> generation dual-AMD server boards from Tyan giving anyone problems?
>
> Booards that I've seen in some the proposals:
>
> Compute nodes: (Tyan S2722) & (Tyan S2466N-4M)
> Head nodes : (Tyan S2469) & (Tyan S2466N-4M)
Having sold both Intel and AMD in the past and now vendor neutral I'll tell
you what I've seen. Tyan (my feelings here) has anyways been too fast to
release a product and wait for "customers/end users" build then an error
report. Then and only then do they make changes. This was seen on their
first release of the dual Thunder K7. Today, I hear from customers now that
are using them, and they are upset with very slow turn around time on
repairs.
Two alternatives are ASUS and Gigabyte, both have had good reviews from end
users.
Another choice would be Intel based, either true Intel with the new 7501
chipset or Supermicro. Intel offers a 3 year warranty on their motherbds.
Supermicro one year. What I like about Supermicro is they test the heck out
of everything, and "its solid". Moreover, Intel will tell you off the
record that Supermicro is their biggest competitor. Reason, good quality,
very aggressive pricing, and they build a complete solution. Meaning, CASE,
POWER SUPPLY, and MOTHERBD...that's tested!
Other consideration for Intel is Hyperthreading, and the new 7501 chipset
will deliver at least 80% from the second cpu...depending on your code.
Some people won't consider Intel because they don't want to rework their
code. Understandable, however, those that do see the benefits of the new
Xeon over Athlon. Some of our customers have seen close to 90% unitization
from the second cpu with the 7501 chipset when their code is performance
tuned.
My .02.
Cheers,
Stephen Gaudet
Wild Open Source
Bedford, NH 03110
pH:603-488-1599
cell:603-498-1600
http://www.wildopensource.com
--__--__--
Message: 9
Date: Thu, 6 Mar 2003 11:43:31 -0500
From: William Park <opengeometry@yahoo.ca>
To: bioclusters@bioinformatics.org
Subject: Re: [Bioclusters] what motherboards are people using for dual
Athlon boxes?
Reply-To: bioclusters@bioinformatics.org
On Wed, Mar 05, 2003 at 05:54:19PM -0500, Chris Dagdigian wrote:
>
> Hi folks,
>
> Anyone using anything other than Tyan mainboards for dual-AMD cluster
> systems? Anyone with happy/unhappy motherboard related issues with
> AMD-based systems?
>
> I've got a client who is looking at a bunch of vendor proposals for
> 2.8ghz dual-Xeon cluster systems and several for dual Athlon MP2600+
> systems. One vendor is even quoting MP2800+ cpus which do not seem to be
> officially released yet in volume from AMD. heh.
If that's the specs they want from contractors, then you have no choice.
Tyan for dual-AMD, and Tyan/Supermicro/Intel for dual-Xeon. But, if you
have speaking relationship with the client, perhaps you can convince
them that single-CPU is better route to go, ie. more motherboard choice,
faster cpu, faster development, no memory/cache contention, etc.
--
William Park, Open Geometry Consulting, <opengeometry@yahoo.ca>
Linux solution for data management and processing.
--__--__--
Message: 10
Subject: RE: [Bioclusters] what motherboards are people using for dual
Athlon boxes?
From: Joseph Landman <landman@scalableinformatics.com>
To: biocluster <bioclusters@bioinformatics.org>
Organization:
Date: 06 Mar 2003 11:51:36 -0500
Reply-To: bioclusters@bioinformatics.org
On Thu, 2003-03-06 at 09:28, Steve Gaudet wrote:
> Other consideration for Intel is Hyperthreading, and the new 7501 chipset
> will deliver at least 80% from the second cpu...depending on your code.
Various testing on the OpenMosix list (and several other places)
contradicts this on "real" codes. The best I have heard out of a real
code is about 30%, and the nominal is closer to -5 to -10%. This is the
case to the point that systems manufacturers are starting to ship HT
threading turned off in the bios.
> Some people won't consider Intel because they don't want to rework their
> code. Understandable, however, those that do see the benefits of the new
> Xeon over Athlon. Some of our customers have seen close to 90%
unitization
> from the second cpu with the 7501 chipset when their code is performance
> tuned.
Possibly on an SMP, and that would be nice to see on this platform.
Unlikely on HT. For BLAST however, the Athlon does nicely, and the -j 2
switch gives you 50-90% additional performance (search and algorithm
dependent) from what I have tried myself on non-pathological cases.
The nice aspect about the Athlon is that you get the performance without
reworking the code. Using the nForce2 MB I got a 30% boost in memory
bandwidth, which translated to something around 30% on some of the codes
I was working on. It was about a 10% better performer on BLAST than the
KT266a. I don't have easy access to a 3+ GHz P4, or a 2800+ AMD Athlon,
or an Opteron, so I cannot do a BLAST comparison at this time with the
really new stuff. The older P4's needed more than a 500+MHz clock speed
advantage to near the performance of the older Athlons. If I can get my
hands on some of the newer stuff, I will run some tests (blastx of a
large set of ests vs nr).
I think the HT support needs to mature for it to be of signficant value,
though as with everything, your mileage will vary. The PPC vector
support is interesting in how easy it is to integrate into existing
codes. I would like to see this with SSE2/MMX2 for x86 stuff.
--
Joseph Landman, Ph.D
Scalable Informatics LLC
email: landman@scalableinformatics.com
web: http://scalableinformatics.com
phone: +1 734 612 4615
--__--__--
_______________________________________________
Bioclusters maillist - Bioclusters@bioinformatics.org
https://bioinformatics.org/mailman/listinfo/bioclusters
End of Bioclusters Digest
------_=_NextPart_001_01C2E401.B5CB3950
Content-Type: text/html
Content-Transfer-Encoding: quoted-printable
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN">
<HTML>
<HEAD>
<META HTTP-EQUIV=3D"Content-Type" CONTENT=3D"text/html; =
charset=3Dus-ascii">
<META NAME=3D"Generator" CONTENT=3D"MS Exchange Server version =
5.5.2653.12">
<TITLE>RE: Bioclusters digest, Vol 1 #225 - 12 msgs</TITLE>
</HEAD>
<BODY>
<P><FONT SIZE=3D2>Please unsubscribe me =
andre.bourgeois@veridian.com</FONT>
</P>
<P><FONT SIZE=3D2>Thanks you,</FONT>
<BR><FONT SIZE=3D2>Andre</FONT>
</P>
<BR>
<P><FONT SIZE=3D2>-----Original Message-----</FONT>
<BR><FONT SIZE=3D2>From: bioclusters-request@bioinformatics.org [<A =
HREF=3D"mailto:bioclusters-request@bioinformatics.org">mailto:biocluster=
s-request@bioinformatics.org</A>] </FONT>
<BR><FONT SIZE=3D2>Sent: Thursday, March 06, 2003 11:49 AM</FONT>
<BR><FONT SIZE=3D2>To: bioclusters@bioinformatics.org</FONT>
<BR><FONT SIZE=3D2>Subject: Bioclusters digest, Vol 1 #225 - 12 =
msgs</FONT>
</P>
<P><FONT SIZE=3D2>Send Bioclusters mailing list submissions to</FONT>
<BR> <FONT =
SIZE=3D2>bioclusters@bioinformatics.org</FONT>
</P>
<P><FONT SIZE=3D2>To subscribe or unsubscribe via the World Wide Web, =
visit</FONT>
<BR> <FONT SIZE=3D2><A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s</A></FONT>
<BR><FONT SIZE=3D2>or, via email, send a message with subject or body =
'help' to</FONT>
<BR> <FONT =
SIZE=3D2>bioclusters-request@bioinformatics.org</FONT>
</P>
<P><FONT SIZE=3D2>You can reach the person managing the list at</FONT>
<BR> <FONT =
SIZE=3D2>bioclusters-admin@bioinformatics.org</FONT>
</P>
<P><FONT SIZE=3D2>When replying, please edit your Subject line so it is =
more specific</FONT>
<BR><FONT SIZE=3D2>than "Re: Contents of Bioclusters =
digest..."</FONT>
</P>
<BR>
<P><FONT SIZE=3D2>Today's Topics:</FONT>
</P>
<P><FONT SIZE=3D2> 1. Re: mpiBLAST compile error (Jones =
George)</FONT>
<BR><FONT SIZE=3D2> 2. Re: mpiBLAST compile error (Pamela =
Culpepper)</FONT>
<BR><FONT SIZE=3D2> 3. Re: mpiBLAST compile error (Joe =
Landman)</FONT>
<BR><FONT SIZE=3D2> 4. Re: mpiBLAST compile error (Steve =
Pittard)</FONT>
<BR><FONT SIZE=3D2> 5. what motherboards are people using =
for dual Athlon boxes? (Chris Dagdigian)</FONT>
<BR><FONT SIZE=3D2> 6. Re: what motherboards are people =
using for dual</FONT>
<BR><FONT SIZE=3D2> Athlon boxes? =
(Joseph Landman)</FONT>
<BR><FONT SIZE=3D2> 7. Re: what motherboards are people =
using for dual Athlon boxes? (Borries Demeler)</FONT>
<BR><FONT SIZE=3D2> 8. RE: what motherboards are people =
using for dual Athlon boxes? (Steve Gaudet)</FONT>
<BR><FONT SIZE=3D2> 9. Re: what motherboards are people =
using for dual Athlon boxes? (William Park)</FONT>
<BR><FONT SIZE=3D2> 10. RE: what motherboards are people using =
for dual</FONT>
<BR><FONT SIZE=3D2> Athlon boxes? =
(Joseph Landman)</FONT>
</P>
<P><FONT SIZE=3D2>--__--__--</FONT>
</P>
<P><FONT SIZE=3D2>Message: 1</FONT>
<BR><FONT SIZE=3D2>Date: Wed, 05 Mar 2003 14:08:30 -0500</FONT>
<BR><FONT SIZE=3D2>From: "Jones George" =
<JBGeorge@wyeth.com></FONT>
<BR><FONT SIZE=3D2>To: <bioclusters@bioinformatics.org></FONT>
<BR><FONT SIZE=3D2>Subject: Re: [Bioclusters] mpiBLAST compile =
error</FONT>
<BR><FONT SIZE=3D2>Reply-To: bioclusters@bioinformatics.org</FONT>
</P>
<P><FONT SIZE=3D2>Hello,</FONT>
</P>
<P><FONT SIZE=3D2>Does anyone know where I can get the complete NCBI =
ToolKit=3D20</FONT>
<BR><FONT SIZE=3D2>that contains these header files:</FONT>
</P>
<P><FONT SIZE=3D2>xmlblast.h, mblast.h, objblst3.h, netblap3.h</FONT>
</P>
<BR>
<P><FONT SIZE=3D2>Thanks,</FONT>
<BR><FONT SIZE=3D2>Jones</FONT>
</P>
<BR>
<P><FONT SIZE=3D2>>>> JBGeorge@wyeth.com 03/03/03 01:43PM =
>>></FONT>
<BR><FONT SIZE=3D2>Joe,</FONT>
</P>
<P><FONT SIZE=3D2>I found the RPM at:</FONT>
</P>
<P><FONT SIZE=3D2><A =
HREF=3D"http://rpmfind.net/linux/RPM/contrib/libc6/i386/ncbi-6.0-1.i386.=
html=3D20" =
TARGET=3D"_blank">http://rpmfind.net/linux/RPM/contrib/libc6/i386/ncbi-6=
.0-1.i386.html=3D20</A></FONT>
</P>
<P><FONT SIZE=3D2>I will try installing the direct toolkit.. will =
update on how it goes..</FONT>
</P>
<P><FONT SIZE=3D2>-Jones</FONT>
</P>
<P><FONT SIZE=3D2>>>> landman@scalableinformatics.com 02/28/03 =
05:22PM >>></FONT>
<BR><FONT SIZE=3D2>Hi Jones:</FONT>
</P>
<P><FONT SIZE=3D2> Either from the direct toolkit, or I can craft =
a source RPM to go =3D</FONT>
<BR><FONT SIZE=3D2>with=3D20</FONT>
<BR><FONT SIZE=3D2>my binary RPMs (<A =
HREF=3D"http://scalableinformatics.com/downloads/" =
TARGET=3D"_blank">http://scalableinformatics.com/downloads/</A>). =
Where did=3D20</FONT>
<BR><FONT SIZE=3D2>you get the blast RPM BTW?</FONT>
</P>
<P><FONT SIZE=3D2>Joe</FONT>
</P>
<P><FONT SIZE=3D2>Jones George wrote:</FONT>
<BR><FONT SIZE=3D2>> Joe,</FONT>
<BR><FONT SIZE=3D2>> Thanks for the clarification.</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> I do not have this file on the system.. =
anywhere...</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> i do not have: xmlblast.h, mblast.h, =
objblst3.h, netblap3.h</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> I am trying to understand why they are not part =
of:</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> ncbi-6.0-1 RPM...</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> Maybe I need to reinstall install the toolkit =
from some other source..</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> any recommendations?</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> Thanks,</FONT>
<BR><FONT SIZE=3D2>> jones</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>>>>>landman@scalableinformatics.com =
02/28/03 04:56PM >>></FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> Jones:</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> These are not libraries, but =
C header files. On your system, try</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> locate =
xmlblast.h</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> and see if you see it anywhere. If so, =
add a pointer to this file in=3D20</FONT>
<BR><FONT SIZE=3D2>> your Makefile.</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> =
-I/path/to/include/files</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> along with the other paths that they have there =
for include directories.</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> Joe</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> --</FONT>
<BR><FONT SIZE=3D2>> Joseph Landman, Ph.D</FONT>
<BR><FONT SIZE=3D2>> Scalable Informatics LLC,</FONT>
<BR><FONT SIZE=3D2>> email: =
landman@scalableinformatics.com=3D20</FONT>
<BR><FONT SIZE=3D2>> web : <A =
HREF=3D"http://scalableinformatics.com=3D20" =
TARGET=3D"_blank">http://scalableinformatics.com=3D20</A></FONT>
<BR><FONT SIZE=3D2>> phone: +1 734 612 4615</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> Jones George wrote:</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>>>I understand.. but I installed the =
RPM</FONT>
<BR><FONT SIZE=3D2>>>and these 4 libs were not installed.</FONT>
<BR><FONT SIZE=3D2>>>I cannot find them anywhere in the =
system.</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>>>>landman@scalableinformatics.com =
02/28/03 04:30PM >>></FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>These files are located in =
ncbi/include/ from the toolkit source.</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT =
SIZE=3D2>>>_______________________________________________</FONT>
<BR><FONT SIZE=3D2>>>Bioclusters maillist - =
Bioclusters@bioinformatics.org=3D20</FONT>
<BR><FONT SIZE=3D2>>><A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters=3D20" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s=3D20</A></FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT =
SIZE=3D2>>>_______________________________________________</FONT>
<BR><FONT SIZE=3D2>>>Bioclusters maillist - =
Bioclusters@bioinformatics.org=3D20</FONT>
<BR><FONT SIZE=3D2>>><A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters=3D20" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s=3D20</A></FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> =
_______________________________________________</FONT>
<BR><FONT SIZE=3D2>> Bioclusters maillist - =
Bioclusters@bioinformatics.org=3D20</FONT>
<BR><FONT SIZE=3D2>> <A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters=3D20" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s=3D20</A></FONT>
<BR><FONT SIZE=3D2>>=3D20</FONT>
<BR><FONT SIZE=3D2>> =
_______________________________________________</FONT>
<BR><FONT SIZE=3D2>> Bioclusters maillist - =
Bioclusters@bioinformatics.org=3D20</FONT>
<BR><FONT SIZE=3D2>> <A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters=3D20" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s=3D20</A></FONT>
</P>
<P><FONT SIZE=3D2>--=3D20</FONT>
<BR><FONT SIZE=3D2>Joseph Landman, Ph.D</FONT>
<BR><FONT SIZE=3D2>Scalable Informatics LLC,</FONT>
<BR><FONT SIZE=3D2>email: landman@scalableinformatics.com=3D20</FONT>
<BR><FONT SIZE=3D2>web : <A =
HREF=3D"http://scalableinformatics.com=3D20" =
TARGET=3D"_blank">http://scalableinformatics.com=3D20</A></FONT>
<BR><FONT SIZE=3D2>phone: +1 734 612 4615</FONT>
</P>
<BR>
<P><FONT =
SIZE=3D2>_______________________________________________</FONT>
<BR><FONT SIZE=3D2>Bioclusters maillist - =
Bioclusters@bioinformatics.org=3D20</FONT>
<BR><FONT SIZE=3D2><A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters=3D20" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s=3D20</A></FONT>
</P>
<P><FONT =
SIZE=3D2>_______________________________________________</FONT>
<BR><FONT SIZE=3D2>Bioclusters maillist - =
Bioclusters@bioinformatics.org=3D20</FONT>
<BR><FONT SIZE=3D2><A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s</A></FONT>
</P>
<BR>
<P><FONT SIZE=3D2>--__--__--</FONT>
</P>
<P><FONT SIZE=3D2>Message: 2</FONT>
<BR><FONT SIZE=3D2>Date: Wed, 05 Mar 2003 15:43:47 -0600</FONT>
<BR><FONT SIZE=3D2>From: Pamela Culpepper =
<pac@bcm.tmc.edu></FONT>
<BR><FONT SIZE=3D2>Organization: Baylor College of Medicine</FONT>
<BR><FONT SIZE=3D2>To: bioclusters@bioinformatics.org</FONT>
<BR><FONT SIZE=3D2>Subject: Re: [Bioclusters] mpiBLAST compile =
error</FONT>
<BR><FONT SIZE=3D2>Reply-To: bioclusters@bioinformatics.org</FONT>
</P>
<P><FONT SIZE=3D2>Get the NCBI C language toolbox from the NCBI ftp =
site. </FONT>
</P>
<P><FONT SIZE=3D2>They are in the include directory.</FONT>
</P>
<P><FONT SIZE=3D2>If you need help compiling, I am very familiar with =
the insanities of </FONT>
<BR><FONT SIZE=3D2>this approach.</FONT>
</P>
<P><FONT SIZE=3D2>Pam Culpepper</FONT>
<BR><FONT SIZE=3D2>Sr. Systems Programmer</FONT>
<BR><FONT SIZE=3D2>Biomedical Computing Facility</FONT>
<BR><FONT SIZE=3D2>Baylor College of Medicine</FONT>
</P>
<P><FONT SIZE=3D2>Jones George wrote:</FONT>
</P>
<P><FONT SIZE=3D2>>Hello,</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>>Does anyone know where I can get the complete =
NCBI ToolKit </FONT>
<BR><FONT SIZE=3D2>>that contains these header files:</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>>xmlblast.h, mblast.h, objblst3.h, =
netblap3.h</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>>Thanks,</FONT>
<BR><FONT SIZE=3D2>>Jones</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>>>>>JBGeorge@wyeth.com 03/03/03 01:43PM =
>>></FONT>
<BR><FONT =
SIZE=3D2>>>>> =
</FONT>
<BR><FONT SIZE=3D2>>>>></FONT>
<BR><FONT SIZE=3D2>>Joe,</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>>I found the RPM at:</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>><A =
HREF=3D"http://rpmfind.net/linux/RPM/contrib/libc6/i386/ncbi-6.0-1.i386.=
html" =
TARGET=3D"_blank">http://rpmfind.net/linux/RPM/contrib/libc6/i386/ncbi-6=
.0-1.i386.html</A> </FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>>I will try installing the direct toolkit.. will =
update on how it goes..</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>>-Jones</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>>>>>landman@scalableinformatics.com =
02/28/03 05:22PM >>></FONT>
<BR><FONT =
SIZE=3D2>>>>> =
</FONT>
<BR><FONT SIZE=3D2>>>>></FONT>
<BR><FONT SIZE=3D2>>Hi Jones:</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>> Either from the direct toolkit, or I can =
craft a source RPM to go with </FONT>
<BR><FONT SIZE=3D2>>my binary RPMs (<A =
HREF=3D"http://scalableinformatics.com/downloads/" =
TARGET=3D"_blank">http://scalableinformatics.com/downloads/</A>). =
Where did </FONT>
<BR><FONT SIZE=3D2>>you get the blast RPM BTW?</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>>Joe</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>>Jones George wrote:</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>>>Joe,</FONT>
<BR><FONT SIZE=3D2>>>Thanks for the clarification.</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>I do not have this file on the system.. =
anywhere...</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>i do not have: xmlblast.h, mblast.h, =
objblst3.h, netblap3.h</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>I am trying to understand why they are not =
part of:</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>ncbi-6.0-1 RPM...</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>Maybe I need to reinstall install the =
toolkit from some other source..</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>any recommendations?</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>Thanks,</FONT>
<BR><FONT SIZE=3D2>>>jones</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>> </FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>>>>landman@scalableinformatics.com =
02/28/03 04:56PM >>></FONT>
<BR><FONT =
SIZE=3D2>>>>>> &=
nbsp; </FONT>
<BR><FONT SIZE=3D2>>>>>></FONT>
<BR><FONT SIZE=3D2>>>Jones:</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>> These are not libraries, but C =
header files. On your system, try</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>> locate =
xmlblast.h</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>and see if you see it anywhere. If so, =
add a pointer to this file in </FONT>
<BR><FONT SIZE=3D2>>>your Makefile.</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>> =
-I/path/to/include/files</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>along with the other paths that they have =
there for include directories.</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>Joe</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>--</FONT>
<BR><FONT SIZE=3D2>>>Joseph Landman, Ph.D</FONT>
<BR><FONT SIZE=3D2>>>Scalable Informatics LLC,</FONT>
<BR><FONT SIZE=3D2>>>email: landman@scalableinformatics.com =
</FONT>
<BR><FONT SIZE=3D2>>>web : <A =
HREF=3D"http://scalableinformatics.com" =
TARGET=3D"_blank">http://scalableinformatics.com</A> </FONT>
<BR><FONT SIZE=3D2>>>phone: +1 734 612 4615</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>Jones George wrote:</FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>> </FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>>>>I understand.. but I installed the =
RPM</FONT>
<BR><FONT SIZE=3D2>>>>and these 4 libs were not =
installed.</FONT>
<BR><FONT SIZE=3D2>>>>I cannot find them anywhere in the =
system.</FONT>
<BR><FONT SIZE=3D2>>>></FONT>
<BR><FONT SIZE=3D2>>>></FONT>
<BR><FONT SIZE=3D2>>>></FONT>
<BR><FONT SIZE=3D2>>>> </FONT>
<BR><FONT SIZE=3D2>>>></FONT>
<BR><FONT =
SIZE=3D2>>>>>>>landman@scalableinformatics.com =
02/28/03 04:30PM >>></FONT>
<BR><FONT =
SIZE=3D2>>>>>>> &nb=
sp; </FONT>
<BR><FONT SIZE=3D2>>>>>>></FONT>
<BR><FONT SIZE=3D2>>>>These files are located in =
ncbi/include/ from the toolkit source.</FONT>
<BR><FONT SIZE=3D2>>>></FONT>
<BR><FONT SIZE=3D2>>>></FONT>
<BR><FONT SIZE=3D2>>>></FONT>
<BR><FONT =
SIZE=3D2>>>>_______________________________________________</FO=
NT>
<BR><FONT SIZE=3D2>>>>Bioclusters maillist - =
Bioclusters@bioinformatics.org </FONT>
<BR><FONT SIZE=3D2>>>><A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s</A> </FONT>
<BR><FONT SIZE=3D2>>>></FONT>
<BR><FONT =
SIZE=3D2>>>>_______________________________________________</FO=
NT>
<BR><FONT SIZE=3D2>>>>Bioclusters maillist - =
Bioclusters@bioinformatics.org </FONT>
<BR><FONT SIZE=3D2>>>><A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s</A> </FONT>
<BR><FONT SIZE=3D2>>>> </FONT>
<BR><FONT SIZE=3D2>>>></FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT =
SIZE=3D2>>>_______________________________________________</FONT>
<BR><FONT SIZE=3D2>>>Bioclusters maillist - =
Bioclusters@bioinformatics.org </FONT>
<BR><FONT SIZE=3D2>>><A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s</A> </FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT =
SIZE=3D2>>>_______________________________________________</FONT>
<BR><FONT SIZE=3D2>>>Bioclusters maillist - =
Bioclusters@bioinformatics.org </FONT>
<BR><FONT SIZE=3D2>>><A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s</A> </FONT>
<BR><FONT SIZE=3D2>>> </FONT>
<BR><FONT SIZE=3D2>>></FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>></FONT>
</P>
<BR>
<BR>
<P><FONT SIZE=3D2>--__--__--</FONT>
</P>
<P><FONT SIZE=3D2>Message: 3</FONT>
<BR><FONT SIZE=3D2>Subject: Re: [Bioclusters] mpiBLAST compile =
error</FONT>
<BR><FONT SIZE=3D2>From: Joe Landman =
<landman@scalableinformatics.com></FONT>
<BR><FONT SIZE=3D2>To: bioclusters@bioinformatics.org</FONT>
<BR><FONT SIZE=3D2>Organization: </FONT>
<BR><FONT SIZE=3D2>Date: 05 Mar 2003 16:49:24 -0500</FONT>
<BR><FONT SIZE=3D2>Reply-To: bioclusters@bioinformatics.org</FONT>
</P>
<P><FONT SIZE=3D2><A =
HREF=3D"ftp://ftp.ncbi.nlm.nih.gov/toolbox/ncbi_tools/ncbi.tar.Z" =
TARGET=3D"_blank">ftp://ftp.ncbi.nlm.nih.gov/toolbox/ncbi_tools/ncbi.tar=
.Z</A></FONT>
</P>
<P><FONT SIZE=3D2>On Wed, 2003-03-05 at 14:08, Jones George =
wrote:</FONT>
<BR><FONT SIZE=3D2>> Hello,</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Does anyone know where I can get the complete =
NCBI ToolKit </FONT>
<BR><FONT SIZE=3D2>> that contains these header files:</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> xmlblast.h, mblast.h, objblst3.h, =
netblap3.h</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Thanks,</FONT>
<BR><FONT SIZE=3D2>> Jones</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> >>> JBGeorge@wyeth.com 03/03/03 =
01:43PM >>></FONT>
<BR><FONT SIZE=3D2>> Joe,</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> I found the RPM at:</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> <A =
HREF=3D"http://rpmfind.net/linux/RPM/contrib/libc6/i386/ncbi-6.0-1.i386.=
html" =
TARGET=3D"_blank">http://rpmfind.net/linux/RPM/contrib/libc6/i386/ncbi-6=
.0-1.i386.html</A></FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> I will try installing the direct toolkit.. will =
update on how it goes..</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> -Jones</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> >>> landman@scalableinformatics.com =
02/28/03 05:22PM >>></FONT>
<BR><FONT SIZE=3D2>> Hi Jones:</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Either from the direct toolkit, or =
I can craft a source RPM to go with </FONT>
<BR><FONT SIZE=3D2>> my binary RPMs (<A =
HREF=3D"http://scalableinformatics.com/downloads/" =
TARGET=3D"_blank">http://scalableinformatics.com/downloads/</A>). =
Where did </FONT>
<BR><FONT SIZE=3D2>> you get the blast RPM BTW?</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Joe</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Jones George wrote:</FONT>
<BR><FONT SIZE=3D2>> > Joe,</FONT>
<BR><FONT SIZE=3D2>> > Thanks for the clarification.</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > I do not have this file on the system.. =
anywhere...</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > i do not have: xmlblast.h, mblast.h, =
objblst3.h, netblap3.h</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > I am trying to understand why they are not =
part of:</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > ncbi-6.0-1 RPM...</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > Maybe I need to reinstall install the =
toolkit from some other source..</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > any recommendations?</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > Thanks,</FONT>
<BR><FONT SIZE=3D2>> > jones</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> >>>>landman@scalableinformatics.com =
02/28/03 04:56PM >>></FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > Jones:</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > These are not libraries, =
but C header files. On your system, try</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > locate =
xmlblast.h</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > and see if you see it anywhere. If =
so, add a pointer to this file in </FONT>
<BR><FONT SIZE=3D2>> > your Makefile.</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > =
-I/path/to/include/files</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > along with the other paths that they have =
there for include directories.</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > Joe</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > --</FONT>
<BR><FONT SIZE=3D2>> > Joseph Landman, Ph.D</FONT>
<BR><FONT SIZE=3D2>> > Scalable Informatics LLC,</FONT>
<BR><FONT SIZE=3D2>> > email: landman@scalableinformatics.com =
</FONT>
<BR><FONT SIZE=3D2>> > web : <A =
HREF=3D"http://scalableinformatics.com" =
TARGET=3D"_blank">http://scalableinformatics.com</A></FONT>
<BR><FONT SIZE=3D2>> > phone: +1 734 612 4615</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > Jones George wrote:</FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> >>I understand.. but I installed =
the RPM</FONT>
<BR><FONT SIZE=3D2>> >>and these 4 libs were not =
installed.</FONT>
<BR><FONT SIZE=3D2>> >>I cannot find them anywhere in the =
system.</FONT>
<BR><FONT SIZE=3D2>> >></FONT>
<BR><FONT SIZE=3D2>> >></FONT>
<BR><FONT SIZE=3D2>> >></FONT>
<BR><FONT SIZE=3D2>> =
>>>>>landman@scalableinformatics.com 02/28/03 04:30PM =
>>></FONT>
<BR><FONT SIZE=3D2>> >></FONT>
<BR><FONT SIZE=3D2>> >>These files are located in =
ncbi/include/ from the toolkit source.</FONT>
<BR><FONT SIZE=3D2>> >></FONT>
<BR><FONT SIZE=3D2>> >></FONT>
<BR><FONT SIZE=3D2>> >></FONT>
<BR><FONT SIZE=3D2>> =
>>_______________________________________________</FONT>
<BR><FONT SIZE=3D2>> >>Bioclusters maillist - =
Bioclusters@bioinformatics.org </FONT>
<BR><FONT SIZE=3D2>> >><A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s</A></FONT>
<BR><FONT SIZE=3D2>> >></FONT>
<BR><FONT SIZE=3D2>> =
>>_______________________________________________</FONT>
<BR><FONT SIZE=3D2>> >>Bioclusters maillist - =
Bioclusters@bioinformatics.org </FONT>
<BR><FONT SIZE=3D2>> >><A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s</A></FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > =
_______________________________________________</FONT>
<BR><FONT SIZE=3D2>> > Bioclusters maillist - =
Bioclusters@bioinformatics.org </FONT>
<BR><FONT SIZE=3D2>> > <A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s</A></FONT>
<BR><FONT SIZE=3D2>> > </FONT>
<BR><FONT SIZE=3D2>> > =
_______________________________________________</FONT>
<BR><FONT SIZE=3D2>> > Bioclusters maillist - =
Bioclusters@bioinformatics.org </FONT>
<BR><FONT SIZE=3D2>> > <A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s</A></FONT>
<BR><FONT SIZE=3D2>-- </FONT>
<BR><FONT SIZE=3D2>Joseph Landman, Ph.D</FONT>
<BR><FONT SIZE=3D2>Scalable Informatics LLC,</FONT>
<BR><FONT SIZE=3D2>email: landman@scalableinformatics.com</FONT>
<BR><FONT SIZE=3D2>web : <A =
HREF=3D"http://scalableinformatics.com" =
TARGET=3D"_blank">http://scalableinformatics.com</A></FONT>
<BR><FONT SIZE=3D2>phone: +1 734 612 4615</FONT>
</P>
<BR>
<P><FONT SIZE=3D2>--__--__--</FONT>
</P>
<P><FONT SIZE=3D2>Message: 4</FONT>
<BR><FONT SIZE=3D2>Date: Wed, 5 Mar 2003 17:13:07 -0500 (EST)</FONT>
<BR><FONT SIZE=3D2>From: Steve Pittard <wsp@emory.edu></FONT>
<BR><FONT SIZE=3D2>To: bioclusters@bioinformatics.org</FONT>
<BR><FONT SIZE=3D2>Subject: Re: [Bioclusters] mpiBLAST compile =
error</FONT>
<BR><FONT SIZE=3D2>Reply-To: bioclusters@bioinformatics.org</FONT>
</P>
<BR>
<P><FONT SIZE=3D2>so, get the NCBI toolkit and unpack it in , for =
example,</FONT>
<BR><FONT SIZE=3D2>/var/tmp. I have /var/tmp/ncbi. I put =
mpiBLAST</FONT>
<BR><FONT SIZE=3D2>in /opt/mpiBLAST and from that dir I do</FONT>
</P>
<P><FONT SIZE=3D2>$ ./configure --with-ncbi=3D/var/tmp/ncbi =
--prefix=3D/usr/local/mpiblast</FONT>
</P>
<P><FONT SIZE=3D2>This should build the config with a knowledge of the =
location</FONT>
<BR><FONT SIZE=3D2>of the NCBI files. </FONT>
</P>
<P><FONT SIZE=3D2>$ make</FONT>
<BR><FONT SIZE=3D2>$ make -n install (to see what it will do without =
actually doing it)</FONT>
<BR><FONT SIZE=3D2>$ make install</FONT>
</P>
<BR>
<BR>
<P><FONT SIZE=3D2>Steve Pittard | <A =
HREF=3D"http://catalina.bimcore.emory.edu" =
TARGET=3D"_blank">http://catalina.bimcore.emory.edu</A> (HOME =
PAGE)</FONT>
<BR><FONT SIZE=3D2>Emory University | wsp@emory.edu, =
wsp@bimcore.emory.edu (INTERNET) </FONT>
<BR><FONT SIZE=3D2>BIMCORE Support | 404 727 0038 </FONT>
</P>
<BR>
<BR>
<P><FONT SIZE=3D2>--__--__--</FONT>
</P>
<P><FONT SIZE=3D2>Message: 5</FONT>
<BR><FONT SIZE=3D2>Date: Wed, 05 Mar 2003 17:54:19 -0500</FONT>
<BR><FONT SIZE=3D2>From: Chris Dagdigian =
<dag@sonsorol.org></FONT>
<BR><FONT SIZE=3D2>To: bioclusters@bioinformatics.org</FONT>
<BR><FONT SIZE=3D2>Subject: [Bioclusters] what motherboards are people =
using for dual Athlon boxes?</FONT>
<BR><FONT SIZE=3D2>Reply-To: bioclusters@bioinformatics.org</FONT>
</P>
<BR>
<P><FONT SIZE=3D2>Hi folks,</FONT>
</P>
<P><FONT SIZE=3D2>Anyone using anything other than Tyan mainboards for =
dual-AMD cluster </FONT>
<BR><FONT SIZE=3D2>systems? Anyone with happy/unhappy motherboard =
related issues with </FONT>
<BR><FONT SIZE=3D2>AMD-based systems?</FONT>
</P>
<P><FONT SIZE=3D2>I've got a client who is looking at a bunch of vendor =
proposals for </FONT>
<BR><FONT SIZE=3D2>2.8ghz dual-Xeon cluster systems and several for =
dual Athlon MP2600+ </FONT>
<BR><FONT SIZE=3D2>systems. One vendor is even quoting MP2800+ cpus =
which do not seem to be </FONT>
<BR><FONT SIZE=3D2>officially released yet in volume from AMD. =
heh.</FONT>
</P>
<P><FONT SIZE=3D2>Personally I've never had problems with Tyan but the =
customer has had </FONT>
<BR><FONT SIZE=3D2>Tyan-related mainboard issues in the past and in =
general seems to feel a </FONT>
<BR><FONT SIZE=3D2>slight sense of unease in that 100% of the =
Athlon-based proposals so far </FONT>
<BR><FONT SIZE=3D2>are using Tyan boards. They are wondering if there =
are any serious </FONT>
<BR><FONT SIZE=3D2>non-Tyan mainboards available that are suitable for =
dual-AMD use in a </FONT>
<BR><FONT SIZE=3D2>technical computing environment. I'm guessing choice =
is pretty limited.</FONT>
</P>
<P><FONT SIZE=3D2>What are people here using? Any recommendations? Are =
the current </FONT>
<BR><FONT SIZE=3D2>generation dual-AMD server boards from Tyan giving =
anyone problems?</FONT>
</P>
<P><FONT SIZE=3D2>Booards that I've seen in some the proposals:</FONT>
</P>
<P><FONT SIZE=3D2>Compute nodes: (Tyan S2722) & (Tyan =
S2466N-4M)</FONT>
<BR><FONT SIZE=3D2>Head nodes : (Tyan S2469) & (Tyan =
S2466N-4M)</FONT>
</P>
<BR>
<P><FONT SIZE=3D2>Regards,</FONT>
<BR><FONT SIZE=3D2>Chris</FONT>
</P>
<BR>
<P><FONT SIZE=3D2>-- </FONT>
<BR><FONT SIZE=3D2>Chris Dagdigian, <dag@sonsorol.org></FONT>
<BR><FONT SIZE=3D2>BioTeam Inc. - Independent Bio-IT & Informatics =
consulting</FONT>
<BR><FONT SIZE=3D2>Office: 617-666-6454, Mobile: 617-877-5498, Fax: =
425-699-0193</FONT>
<BR><FONT SIZE=3D2>PGP KeyID: 83D4310E Yahoo IM: craffi Web: <A =
HREF=3D"http://bioteam.net" =
TARGET=3D"_blank">http://bioteam.net</A></FONT>
</P>
<BR>
<P><FONT SIZE=3D2>--__--__--</FONT>
</P>
<P><FONT SIZE=3D2>Message: 6</FONT>
<BR><FONT SIZE=3D2>Subject: Re: [Bioclusters] what motherboards are =
people using for dual</FONT>
<BR> <FONT SIZE=3D2>Athlon =
boxes?</FONT>
<BR><FONT SIZE=3D2>From: Joseph Landman =
<landman@scalableinformatics.com></FONT>
<BR><FONT SIZE=3D2>To: biocluster =
<bioclusters@bioinformatics.org></FONT>
<BR><FONT SIZE=3D2>Organization: </FONT>
<BR><FONT SIZE=3D2>Date: 05 Mar 2003 18:53:47 -0500</FONT>
<BR><FONT SIZE=3D2>Reply-To: bioclusters@bioinformatics.org</FONT>
</P>
<P><FONT SIZE=3D2>There are several, though they lack some of the Tyan =
"features"</FONT>
</P>
<P><FONT SIZE=3D2><A =
HREF=3D"http://networking.gigabyte.com.tw/Products/Products_ServerBoard_=
Spec.asp?ProductID=3D83" =
TARGET=3D"_blank">http://networking.gigabyte.com.tw/Products/Products_Se=
rverBoard_Spec.asp?ProductID=3D83</A></FONT>
<BR><FONT SIZE=3D2><A =
HREF=3D"http://www.iwillusa.com/products/ProductDetail.asp?vID=3D19" =
TARGET=3D"_blank">http://www.iwillusa.com/products/ProductDetail.asp?vID=
=3D19</A></FONT>
<BR><FONT SIZE=3D2><A =
HREF=3D"http://www.msicomputer.com/product/detail_spec/product_detail.as=
p?model=3DK7D_Master_L" =
TARGET=3D"_blank">http://www.msicomputer.com/product/detail_spec/product=
_detail.asp?model=3DK7D_Master_L</A></FONT>
</P>
<P><FONT SIZE=3D2>The gigabyte looks good. I am building a test =
unit with it.</FONT>
</P>
<P><FONT SIZE=3D2>BTW: on a single CPU machine, the Asus nForce2 =
gives a nice dual</FONT>
<BR><FONT SIZE=3D2>channel to ram. Without working at it, streams =
is reporting in the mid</FONT>
<BR><FONT SIZE=3D2>1.1GB/s for triad. BLAST is latency bound, but =
having lots of memory</FONT>
<BR><FONT SIZE=3D2>bandwidth is great for the chemistry codes. =
The MPX760 based chipsets</FONT>
<BR><FONT SIZE=3D2>have hit 600-700 MB/s. The KT266a have hit =
about 800-900 MB/s. </FONT>
</P>
<P><FONT SIZE=3D2>Not exactly a server MB, but interesting in its own =
right.</FONT>
</P>
<P><FONT SIZE=3D2>On Wed, 2003-03-05 at 17:54, Chris Dagdigian =
wrote:</FONT>
<BR><FONT SIZE=3D2>> Hi folks,</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Anyone using anything other than Tyan =
mainboards for dual-AMD cluster </FONT>
<BR><FONT SIZE=3D2>> systems? Anyone with happy/unhappy motherboard =
related issues with </FONT>
<BR><FONT SIZE=3D2>> AMD-based systems?</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> I've got a client who is looking at a bunch of =
vendor proposals for </FONT>
<BR><FONT SIZE=3D2>> 2.8ghz dual-Xeon cluster systems and several =
for dual Athlon MP2600+ </FONT>
<BR><FONT SIZE=3D2>> systems. One vendor is even quoting MP2800+ =
cpus which do not seem to be </FONT>
<BR><FONT SIZE=3D2>> officially released yet in volume from AMD. =
heh.</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Personally I've never had problems with Tyan =
but the customer has had </FONT>
<BR><FONT SIZE=3D2>> Tyan-related mainboard issues in the past and =
in general seems to feel a </FONT>
<BR><FONT SIZE=3D2>> slight sense of unease in that 100% of the =
Athlon-based proposals so far </FONT>
<BR><FONT SIZE=3D2>> are using Tyan boards. They are wondering if =
there are any serious </FONT>
<BR><FONT SIZE=3D2>> non-Tyan mainboards available that are suitable =
for dual-AMD use in a </FONT>
<BR><FONT SIZE=3D2>> technical computing environment. I'm guessing =
choice is pretty limited.</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> What are people here using? Any =
recommendations? Are the current </FONT>
<BR><FONT SIZE=3D2>> generation dual-AMD server boards from Tyan =
giving anyone problems?</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Booards that I've seen in some the =
proposals:</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Compute nodes: (Tyan S2722) & (Tyan =
S2466N-4M)</FONT>
<BR><FONT SIZE=3D2>> Head nodes : (Tyan S2469) & =
(Tyan S2466N-4M)</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Regards,</FONT>
<BR><FONT SIZE=3D2>> Chris</FONT>
<BR><FONT SIZE=3D2>-- </FONT>
<BR><FONT SIZE=3D2>Joseph Landman =
<landman@scalableinformatics.com></FONT>
</P>
<BR>
<P><FONT SIZE=3D2>--__--__--</FONT>
</P>
<P><FONT SIZE=3D2>Message: 7</FONT>
<BR><FONT SIZE=3D2>From: Borries Demeler =
<demeler@bioc09.v19.uthscsa.edu></FONT>
<BR><FONT SIZE=3D2>Subject: Re: [Bioclusters] what motherboards are =
people using for dual Athlon boxes?</FONT>
<BR><FONT SIZE=3D2>To: bioclusters@bioinformatics.org</FONT>
<BR><FONT SIZE=3D2>Date: Wed, 5 Mar 2003 18:21:10 -0600 (CST)</FONT>
<BR><FONT SIZE=3D2>Reply-To: bioclusters@bioinformatics.org</FONT>
</P>
<P><FONT SIZE=3D2>We have bought three Tyan MB's for testing about a =
year ago and</FONT>
<BR><FONT SIZE=3D2>had lots of stability problems with them until bios =
upgrades</FONT>
<BR><FONT SIZE=3D2>fixed most of the problems. Never had a single =
problem with </FONT>
<BR><FONT SIZE=3D2>the Asus boards, and we have since built 2 clusters =
using the </FONT>
<BR><FONT SIZE=3D2>Asus boards, and are very happy with both =
performance and stability.</FONT>
<BR><FONT SIZE=3D2>They also don't seem to be too picky about the =
memory, we've</FONT>
<BR><FONT SIZE=3D2>been able to run the cheap generic stuff in one of =
them we use for </FONT>
<BR><FONT SIZE=3D2>video processing.</FONT>
</P>
<P><FONT SIZE=3D2>Maybe it's just having been lucky, but I would =
recommend going</FONT>
<BR><FONT SIZE=3D2>with the Asus.</FONT>
</P>
<P><FONT SIZE=3D2>-Borries</FONT>
</P>
<P><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Hi folks,</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Anyone using anything other than Tyan =
mainboards for dual-AMD cluster </FONT>
<BR><FONT SIZE=3D2>> systems? Anyone with happy/unhappy motherboard =
related issues with </FONT>
<BR><FONT SIZE=3D2>> AMD-based systems?</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> I've got a client who is looking at a bunch of =
vendor proposals for </FONT>
<BR><FONT SIZE=3D2>> 2.8ghz dual-Xeon cluster systems and several =
for dual Athlon MP2600+ </FONT>
<BR><FONT SIZE=3D2>> systems. One vendor is even quoting MP2800+ =
cpus which do not seem to be </FONT>
<BR><FONT SIZE=3D2>> officially released yet in volume from AMD. =
heh.</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Personally I've never had problems with Tyan =
but the customer has had </FONT>
<BR><FONT SIZE=3D2>> Tyan-related mainboard issues in the past and =
in general seems to feel a </FONT>
<BR><FONT SIZE=3D2>> slight sense of unease in that 100% of the =
Athlon-based proposals so far </FONT>
<BR><FONT SIZE=3D2>> are using Tyan boards. They are wondering if =
there are any serious </FONT>
<BR><FONT SIZE=3D2>> non-Tyan mainboards available that are suitable =
for dual-AMD use in a </FONT>
<BR><FONT SIZE=3D2>> technical computing environment. I'm guessing =
choice is pretty limited.</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> What are people here using? Any =
recommendations? Are the current </FONT>
<BR><FONT SIZE=3D2>> generation dual-AMD server boards from Tyan =
giving anyone problems?</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Booards that I've seen in some the =
proposals:</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Compute nodes: (Tyan S2722) & (Tyan =
S2466N-4M)</FONT>
<BR><FONT SIZE=3D2>> Head nodes : (Tyan S2469) & =
(Tyan S2466N-4M)</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Regards,</FONT>
<BR><FONT SIZE=3D2>> Chris</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> -- </FONT>
<BR><FONT SIZE=3D2>> Chris Dagdigian, =
<dag@sonsorol.org></FONT>
<BR><FONT SIZE=3D2>> BioTeam Inc. - Independent Bio-IT & =
Informatics consulting</FONT>
<BR><FONT SIZE=3D2>> Office: 617-666-6454, Mobile: 617-877-5498, =
Fax: 425-699-0193</FONT>
<BR><FONT SIZE=3D2>> PGP KeyID: 83D4310E Yahoo IM: craffi Web: <A =
HREF=3D"http://bioteam.net" =
TARGET=3D"_blank">http://bioteam.net</A></FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> =
_______________________________________________</FONT>
<BR><FONT SIZE=3D2>> Bioclusters maillist - =
Bioclusters@bioinformatics.org</FONT>
<BR><FONT SIZE=3D2>> <A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s</A></FONT>
<BR><FONT SIZE=3D2>> </FONT>
</P>
<BR>
<P><FONT SIZE=3D2>--__--__--</FONT>
</P>
<P><FONT SIZE=3D2>Message: 8</FONT>
<BR><FONT SIZE=3D2>From: "Steve Gaudet" =
<sgaudet@wildopensource.com></FONT>
<BR><FONT SIZE=3D2>To: <bioclusters@bioinformatics.org>, =
<dag@sonsorol.org></FONT>
<BR><FONT SIZE=3D2>Subject: RE: [Bioclusters] what motherboards are =
people using for dual Athlon boxes?</FONT>
<BR><FONT SIZE=3D2>Date: Thu, 6 Mar 2003 09:28:33 -0500</FONT>
<BR><FONT SIZE=3D2>Reply-To: bioclusters@bioinformatics.org</FONT>
</P>
<P><FONT SIZE=3D2>Hello Chris,</FONT>
</P>
<P><FONT SIZE=3D2>> Anyone using anything other than Tyan mainboards =
for dual-AMD cluster</FONT>
<BR><FONT SIZE=3D2>> systems? Anyone with happy/unhappy motherboard =
related issues with</FONT>
<BR><FONT SIZE=3D2>> AMD-based systems?</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>> I've got a client who is looking at a bunch of =
vendor proposals for</FONT>
<BR><FONT SIZE=3D2>> 2.8ghz dual-Xeon cluster systems and several =
for dual Athlon MP2600+</FONT>
<BR><FONT SIZE=3D2>> systems. One vendor is even quoting MP2800+ =
cpus which do not</FONT>
<BR><FONT SIZE=3D2>> seem to be officially released yet in volume =
from AMD. heh.</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>> Personally I've never had problems with Tyan =
but the customer has had</FONT>
<BR><FONT SIZE=3D2>> Tyan-related mainboard issues in the past and =
in general</FONT>
<BR><FONT SIZE=3D2>> seems to feel a slight sense of unease in that =
100% of the Athlon-based</FONT>
<BR><FONT SIZE=3D2>> proposals so far are using Tyan boards. They =
are wondering if there are</FONT>
<BR><FONT SIZE=3D2>any serious</FONT>
<BR><FONT SIZE=3D2>> non-Tyan mainboards available that are suitable =
for dual-AMD use in a</FONT>
<BR><FONT SIZE=3D2>> technical computing environment. I'm guessing =
choice is pretty limited.</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>> What are people here using? Any =
recommendations? Are the current</FONT>
<BR><FONT SIZE=3D2>> generation dual-AMD server boards from Tyan =
giving anyone problems?</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>> Booards that I've seen in some the =
proposals:</FONT>
<BR><FONT SIZE=3D2>></FONT>
<BR><FONT SIZE=3D2>> Compute nodes: (Tyan S2722) & (Tyan =
S2466N-4M)</FONT>
<BR><FONT SIZE=3D2>> Head nodes : (Tyan S2469) & =
(Tyan S2466N-4M)</FONT>
</P>
<P><FONT SIZE=3D2>Having sold both Intel and AMD in the past and now =
vendor neutral I'll tell</FONT>
<BR><FONT SIZE=3D2>you what I've seen. Tyan (my feelings here) =
has anyways been too fast to</FONT>
<BR><FONT SIZE=3D2>release a product and wait for "customers/end =
users" build then an error</FONT>
<BR><FONT SIZE=3D2>report. Then and only then do they make =
changes. This was seen on their</FONT>
<BR><FONT SIZE=3D2>first release of the dual Thunder K7. Today, I =
hear from customers now that</FONT>
<BR><FONT SIZE=3D2>are using them, and they are upset with very slow =
turn around time on</FONT>
<BR><FONT SIZE=3D2>repairs.</FONT>
</P>
<P><FONT SIZE=3D2>Two alternatives are ASUS and Gigabyte, both have had =
good reviews from end</FONT>
<BR><FONT SIZE=3D2>users.</FONT>
</P>
<P><FONT SIZE=3D2>Another choice would be Intel based, either true =
Intel with the new 7501</FONT>
<BR><FONT SIZE=3D2>chipset or Supermicro. Intel offers a 3 year =
warranty on their motherbds.</FONT>
<BR><FONT SIZE=3D2>Supermicro one year. What I like about =
Supermicro is they test the heck out</FONT>
<BR><FONT SIZE=3D2>of everything, and "its solid". =
Moreover, Intel will tell you off the</FONT>
<BR><FONT SIZE=3D2>record that Supermicro is their biggest =
competitor. Reason, good quality,</FONT>
<BR><FONT SIZE=3D2>very aggressive pricing, and they build a complete =
solution. Meaning, CASE,</FONT>
<BR><FONT SIZE=3D2>POWER SUPPLY, and MOTHERBD...that's tested!</FONT>
</P>
<P><FONT SIZE=3D2>Other consideration for Intel is Hyperthreading, and =
the new 7501 chipset</FONT>
<BR><FONT SIZE=3D2>will deliver at least 80% from the second =
cpu...depending on your code.</FONT>
<BR><FONT SIZE=3D2>Some people won't consider Intel because they don't =
want to rework their</FONT>
<BR><FONT SIZE=3D2>code. Understandable, however, those that do =
see the benefits of the new</FONT>
<BR><FONT SIZE=3D2>Xeon over Athlon. Some of our customers have =
seen close to 90% unitization</FONT>
<BR><FONT SIZE=3D2>from the second cpu with the 7501 chipset when their =
code is performance</FONT>
<BR><FONT SIZE=3D2>tuned.</FONT>
</P>
<P><FONT SIZE=3D2>My .02.</FONT>
</P>
<P><FONT SIZE=3D2>Cheers,</FONT>
</P>
<P><FONT SIZE=3D2>Stephen Gaudet</FONT>
</P>
<P><FONT SIZE=3D2>Wild Open Source</FONT>
<BR><FONT SIZE=3D2>Bedford, NH 03110</FONT>
<BR><FONT SIZE=3D2>pH:603-488-1599</FONT>
<BR><FONT SIZE=3D2>cell:603-498-1600</FONT>
<BR><FONT SIZE=3D2><A HREF=3D"http://www.wildopensource.com" =
TARGET=3D"_blank">http://www.wildopensource.com</A></FONT>
</P>
<BR>
<BR>
<P><FONT SIZE=3D2>--__--__--</FONT>
</P>
<P><FONT SIZE=3D2>Message: 9</FONT>
<BR><FONT SIZE=3D2>Date: Thu, 6 Mar 2003 11:43:31 -0500</FONT>
<BR><FONT SIZE=3D2>From: William Park =
<opengeometry@yahoo.ca></FONT>
<BR><FONT SIZE=3D2>To: bioclusters@bioinformatics.org</FONT>
<BR><FONT SIZE=3D2>Subject: Re: [Bioclusters] what motherboards are =
people using for dual Athlon boxes?</FONT>
<BR><FONT SIZE=3D2>Reply-To: bioclusters@bioinformatics.org</FONT>
</P>
<P><FONT SIZE=3D2>On Wed, Mar 05, 2003 at 05:54:19PM -0500, Chris =
Dagdigian wrote:</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Hi folks,</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> Anyone using anything other than Tyan =
mainboards for dual-AMD cluster </FONT>
<BR><FONT SIZE=3D2>> systems? Anyone with happy/unhappy motherboard =
related issues with </FONT>
<BR><FONT SIZE=3D2>> AMD-based systems?</FONT>
<BR><FONT SIZE=3D2>> </FONT>
<BR><FONT SIZE=3D2>> I've got a client who is looking at a bunch of =
vendor proposals for </FONT>
<BR><FONT SIZE=3D2>> 2.8ghz dual-Xeon cluster systems and several =
for dual Athlon MP2600+ </FONT>
<BR><FONT SIZE=3D2>> systems. One vendor is even quoting MP2800+ =
cpus which do not seem to be </FONT>
<BR><FONT SIZE=3D2>> officially released yet in volume from AMD. =
heh.</FONT>
</P>
<P><FONT SIZE=3D2>If that's the specs they want from contractors, then =
you have no choice.</FONT>
<BR><FONT SIZE=3D2>Tyan for dual-AMD, and Tyan/Supermicro/Intel for =
dual-Xeon. But, if you</FONT>
<BR><FONT SIZE=3D2>have speaking relationship with the client, perhaps =
you can convince</FONT>
<BR><FONT SIZE=3D2>them that single-CPU is better route to go, ie. more =
motherboard choice,</FONT>
<BR><FONT SIZE=3D2>faster cpu, faster development, no memory/cache =
contention, etc.</FONT>
</P>
<P><FONT SIZE=3D2>-- </FONT>
<BR><FONT SIZE=3D2>William Park, Open Geometry Consulting, =
<opengeometry@yahoo.ca></FONT>
<BR><FONT SIZE=3D2>Linux solution for data management and processing. =
</FONT>
</P>
<P><FONT SIZE=3D2>--__--__--</FONT>
</P>
<P><FONT SIZE=3D2>Message: 10</FONT>
<BR><FONT SIZE=3D2>Subject: RE: [Bioclusters] what motherboards are =
people using for dual</FONT>
<BR> <FONT SIZE=3D2>Athlon =
boxes?</FONT>
<BR><FONT SIZE=3D2>From: Joseph Landman =
<landman@scalableinformatics.com></FONT>
<BR><FONT SIZE=3D2>To: biocluster =
<bioclusters@bioinformatics.org></FONT>
<BR><FONT SIZE=3D2>Organization: </FONT>
<BR><FONT SIZE=3D2>Date: 06 Mar 2003 11:51:36 -0500</FONT>
<BR><FONT SIZE=3D2>Reply-To: bioclusters@bioinformatics.org</FONT>
</P>
<P><FONT SIZE=3D2>On Thu, 2003-03-06 at 09:28, Steve Gaudet =
wrote:</FONT>
</P>
<P><FONT SIZE=3D2>> Other consideration for Intel is Hyperthreading, =
and the new 7501 chipset</FONT>
<BR><FONT SIZE=3D2>> will deliver at least 80% from the second =
cpu...depending on your code.</FONT>
</P>
<P><FONT SIZE=3D2>Various testing on the OpenMosix list (and several =
other places)</FONT>
<BR><FONT SIZE=3D2>contradicts this on "real" codes. =
The best I have heard out of a real</FONT>
<BR><FONT SIZE=3D2>code is about 30%, and the nominal is closer to -5 =
to -10%. This is the</FONT>
<BR><FONT SIZE=3D2>case to the point that systems manufacturers are =
starting to ship HT</FONT>
<BR><FONT SIZE=3D2>threading turned off in the bios.</FONT>
</P>
<P><FONT SIZE=3D2>> Some people won't consider Intel because they =
don't want to rework their</FONT>
<BR><FONT SIZE=3D2>> code. Understandable, however, those that =
do see the benefits of the new</FONT>
<BR><FONT SIZE=3D2>> Xeon over Athlon. Some of our customers =
have seen close to 90% unitization</FONT>
<BR><FONT SIZE=3D2>> from the second cpu with the 7501 chipset when =
their code is performance</FONT>
<BR><FONT SIZE=3D2>> tuned.</FONT>
</P>
<P><FONT SIZE=3D2>Possibly on an SMP, and that would be nice to see on =
this platform. </FONT>
<BR><FONT SIZE=3D2>Unlikely on HT. For BLAST however, the Athlon =
does nicely, and the -j 2</FONT>
<BR><FONT SIZE=3D2>switch gives you 50-90% additional performance =
(search and algorithm</FONT>
<BR><FONT SIZE=3D2>dependent) from what I have tried myself on =
non-pathological cases.</FONT>
</P>
<P><FONT SIZE=3D2>The nice aspect about the Athlon is that you get the =
performance without</FONT>
<BR><FONT SIZE=3D2>reworking the code. Using the nForce2 MB I got =
a 30% boost in memory</FONT>
<BR><FONT SIZE=3D2>bandwidth, which translated to something around 30% =
on some of the codes</FONT>
<BR><FONT SIZE=3D2>I was working on. It was about a 10% better =
performer on BLAST than the</FONT>
<BR><FONT SIZE=3D2>KT266a. I don't have easy access to a 3+ GHz =
P4, or a 2800+ AMD Athlon,</FONT>
<BR><FONT SIZE=3D2>or an Opteron, so I cannot do a BLAST comparison at =
this time with the</FONT>
<BR><FONT SIZE=3D2>really new stuff. The older P4's needed more =
than a 500+MHz clock speed</FONT>
<BR><FONT SIZE=3D2>advantage to near the performance of the older =
Athlons. If I can get my</FONT>
<BR><FONT SIZE=3D2>hands on some of the newer stuff, I will run some =
tests (blastx of a</FONT>
<BR><FONT SIZE=3D2>large set of ests vs nr). </FONT>
</P>
<P><FONT SIZE=3D2>I think the HT support needs to mature for it to be =
of signficant value,</FONT>
<BR><FONT SIZE=3D2>though as with everything, your mileage will =
vary. The PPC vector</FONT>
<BR><FONT SIZE=3D2>support is interesting in how easy it is to =
integrate into existing</FONT>
<BR><FONT SIZE=3D2>codes. I would like to see this with SSE2/MMX2 =
for x86 stuff.</FONT>
</P>
<P><FONT SIZE=3D2>-- </FONT>
<BR><FONT SIZE=3D2>Joseph Landman, Ph.D</FONT>
<BR><FONT SIZE=3D2>Scalable Informatics LLC</FONT>
<BR><FONT SIZE=3D2>email: landman@scalableinformatics.com</FONT>
<BR><FONT SIZE=3D2> web: <A =
HREF=3D"http://scalableinformatics.com" =
TARGET=3D"_blank">http://scalableinformatics.com</A></FONT>
<BR><FONT SIZE=3D2>phone: +1 734 612 4615</FONT>
</P>
<BR>
<BR>
<P><FONT SIZE=3D2>--__--__--</FONT>
</P>
<P><FONT =
SIZE=3D2>_______________________________________________</FONT>
<BR><FONT SIZE=3D2>Bioclusters maillist - =
Bioclusters@bioinformatics.org</FONT>
<BR><FONT SIZE=3D2><A =
HREF=3D"https://bioinformatics.org/mailman/listinfo/bioclusters" =
TARGET=3D"_blank">https://bioinformatics.org/mailman/listinfo/biocluster=
s</A></FONT>
</P>
<BR>
<P><FONT SIZE=3D2>End of Bioclusters Digest</FONT>
</P>
</BODY>
</HTML>
------_=_NextPart_001_01C2E401.B5CB3950--