[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Mac feff faster with IBM xlf compiler

To: "FEFF Users" <feffusers@u.washington.edu>
Subject: Mac feff faster with IBM xlf compiler
From: Paul Fons <paul-fons@aist.go.jp>
Date: Sun, 11 Jan 2004 13:56:46 +0900
List-help: <http://www.washington.edu/computing/listproc/>
List-owner: <mailto:feffusers-request@u.washington.edu> (Human contact for the list)
List-post: <mailto:feffusers@u.washington.edu>
List-subscribe: <mailto:listproc@u.washington.edu?body=subscribe%20feffusers%20YourName>
List-unsubscribe: <mailto:listproc@u.washington.edu?body=unsubscribe%20feffusers>
Reply-to: feffusers@u.washington.edu
Sender: FEFFUSERS-owner@u.washington.edu

I have compiled feff8.2 using ibm's new (now in beta) fortran compiler xlf under os 10.3. I have included threading and optimization for the g4 (it has optimization for the g5 as well, but sadly I don't have a g5 yet!). I was wondering if I could forward this to the feff site for other users to try out. I have only subjectively noticed a speedup and have not carefully benchmarked the difference, but I am sure it is faster for my runs. Would there be any interest in offering this from the feff distribution site? If so who would I forward a copy to?

Dr. Paul Fons
Senior Researcher
National Institute for Advanced Industrial Science & Technology
METI
Optoelectronics Division
Umezono 1-1-4
Tsukuba, Ibaraki JAPAN 305-8568

tel. +81-298-61-5636
fax. +81-298-61-5615

email: paul-fons@aist.go.jp

The lines below are in a Japanese font

〒３０５−８５６８
茨城県つくば市梅園１−１−４
光技術部
ポール・フォンス主任研究官

Prev by Date: Follow up Experimental Broadening question
Next by Date: this list is suffering...
Previous by thread: Follow up Experimental Broadening question
Next by thread: this list is suffering...
Index(es):
- Date
- Thread