From owner-chemistry@ccl.net Tue Apr 24 20:47:00 2012 From: "Joe Leonard jleonard42\a/gmail.com" To: CCL Subject: CCL: Effect of using SSD for scratch Message-Id: <-46781-120424194206-13877-9r1Y+vL3PgZ/UEXvHUivEw.@.server.ccl.net> X-Original-From: Joe Leonard Content-Type: multipart/alternative; boundary="Apple-Mail=_3D5E0A01-143B-457C-A7C9-F1E29D8286D9" Date: Tue, 24 Apr 2012 19:41:41 -0400 Mime-Version: 1.0 (Apple Message framework v1257) Sent to CCL by: Joe Leonard [jleonard42+*+gmail.com] --Apple-Mail=_3D5E0A01-143B-457C-A7C9-F1E29D8286D9 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=iso-8859-1 John, it's anecdotal, but my wife's Macbook Air boots far faster than a = similarly configured Macbook Pro - the difference is the 4200 rpm laptop = disk in the latter vs. the SSD in the former. We also have a PC at work = with a small/expensive SSD that is noticeably faster with Powerpoint = presentations. This said, I would think that a careful review of read/write/reread = speeds (and seek times) would demonstrate that SSD should outperform = "normal PC/laptop disks". The question is the vendor and cost for such = an SSD... I also wonder whether direct methods would outperform any = external-storage-based method given the staggering speed difference = between chip/cache and I/O pipeline. I would think this especially = important for GPU based codes? But then, I've been wrong before :-). Joe On Apr 24, 2012, at 5:42 PM, John McKelvey jmmckel[]gmail.com wrote: >=20 > Sent to CCL by: John McKelvey [jmmckel#gmail.com] > CCLers >=20 > I am looking to buy a machine sort of specific for running > Hartree-Fock and DFT codes. There is always the issue of cpu speed, > but for large systems disk-io can be a significant issue, even for the > usual scratch file. Has anyone done any direct or reasonable indirect > evaluations around this issue? >=20 > Many thanks, >=20 > John >=20 >=20 >=20 > --=20 > John McKelvey > 10819 Middleford Pl > Ft Wayne, IN 46818 > 260-489-2160 > jmmckel^^^gmail.com >=20 >=20 >=20 > -=3D This is automatically added to each message by the mailing script = =3D- > To recover the email address of the author of the message, please = change>=20>=20>=20 > Subscribe/Unsubscribe:=20>=20>=20 > Job: http://www.ccl.net/jobs=20 > Conferences: = http://server.ccl.net/chemistry/announcements/conferences/ >=20>=20>=20>=20 >=20 -- Apple had just one customer. He passed away last year. --Apple-Mail=_3D5E0A01-143B-457C-A7C9-F1E29D8286D9 Content-Transfer-Encoding: quoted-printable Content-Type: text/html; charset=iso-8859-1 John, = it's anecdotal, but my wife's Macbook Air boots far faster than a = similarly configured Macbook Pro - the difference is the 4200 rpm laptop = disk in the latter vs. the SSD in the former.  We also have a PC at = work with a small/expensive SSD that is noticeably faster with = Powerpoint presentations.

This said, I would think = that a careful review of read/write/reread speeds (and seek times) would = demonstrate that SSD should outperform "normal PC/laptop disks". =  The question is the vendor and cost for such an SSD...  I = also wonder whether direct methods would outperform any = external-storage-based method given the staggering speed difference = between chip/cache and I/O pipeline.  I would think this especially = important for GPU based codes?

But then, I've = been wrong before :-).

Joe
On Apr = 24, 2012, at 5:42 PM, John McKelvey jmmckel[]gmail.com wrote:


Sent to CCL by: John McKelvey = [jmmckel#gmail.com]
CCLers

I am looking to buy a machine sort = of specific for running
Hartree-Fock and DFT codes.  There is = always the issue of cpu speed,
but for large systems disk-io can be a = significant issue, even for the
usual scratch file.  Has anyone = done any direct or reasonable indirect
evaluations around this = issue?

Many thanks,

John



--
John = McKelvey
10819 Middleford Pl
Ft Wayne, IN = 46818
260-489-2160
jmmckel^^^gmail.com



-=3D This is = automatically added to each message by the mailing script =3D-
To = recover the email address of the author of the message, please = change
the strange characters on the top line to the -$- sign. You can = also
look up the X-Original-From: line in the mail = header.

E-mail to subscribers: CHEMISTRY-$-ccl.net or use:
=      http://www.ccl.ne= t/cgi-bin/ccl/send_ccl_message

E-mail to administrators: CHEMISTRY-REQUEST-$-ccl.net = or use
     http://www.ccl.ne= t/cgi-bin/ccl/send_ccl_message
=      http://www.ccl.net/c= hemistry/sub_unsub.shtml

Before posting, check wait time at: = http://www.ccl.net

Job: http://www.ccl.net/jobs =
Conferences: http:/= /server.ccl.net/chemistry/announcements/conferences/

Search = Messages: http://www.ccl= .net/chemistry/searchccl/index.shtml

If your mail bounces = > from CCL with 5.7.1 error, check:
     http://www.ccl.net/spammers.txt

RTFI: http://www.cc= l.net/chemistry/aboutccl/instructions/


<= /div>
--
Apple had just one customer. He = passed away last = year.

<= /span>

= --Apple-Mail=_3D5E0A01-143B-457C-A7C9-F1E29D8286D9--