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

Unidata Support: 960725: Cray Optimization, T90 status

This archive contains answers to questions sent to Unidata support through mid-2025. Note that the archive is no longer being updated. We provide the archive for reference; many of the answers presented here remain technically correct, even if somewhat outdated. For the most up-to-date information on the use of NSF Unidata software and data services, please consult the Software Documentation first.

  • Subject: Unidata Support: 960725: Cray Optimization, T90 status
  • Date: Mon, 29 Jul 1996 15:55:36 -0600
I'm forwarding this to support-netcdf just to get it indexed for
searching ...

------- Forwarded Message

Date:    Thu, 25 Jul 1996 09:05:43 -0600
From:    Unidata Support <address@hidden>
To:      address@hidden
Subject: 960725: Cray Optimization, T90 status

>To: address@hidden,
>To: address@hidden
>cc: address@hidden (Ramesh Rao),
>cc: address@hidden (Koushik Ghosh)
>From: address@hidden (John Sheldon)
>Subject: Cray Optimization, T90 status
>Organization: .
>Keywords: 199607251449.AA27504

Hi all-

Just thought I'd let you know that Cray is still working on their XDR
and "m4" problems on the IEEE T90, but I've been told to expect things
to be ironed out within about 10 days.

Also, based on some additional user experiences here running netCDF
on our C90, I've updated our "README" document for optimizing netCDF
performance on Crays using FFIO.  See

   http://www.gfdl.gov/~jps/txt/README.IO_Optimization.txt

Part of the updates concern the use of a two-layer cache employing an
SDS layer, which has been fixed in the latest Cray libraries. If you
get a chance, take a look at it and let me know if you think I've
overlooked something.  Thanks!

Cheers-
John

------- End of Forwarded Message