[Beowulf] Athlon64 / Opteron test
Many of your questions may have already been answered in earlier discussions or in the FAQ. The search results page will indicate current discussions as well as past list serves, articles, and papers.
Robert G. Brown rgb at phy.duke.eduFri May 14 21:16:50 PDT 2004
- Previous message: [Beowulf] Athlon64 / Opteron test
- Next message: [Beowulf] Re: Athlon64 / Opteron test
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
On Fri, 14 May 2004, Donald Becker wrote: > > [[ The mailing list should now be back up and running for all > subscribers. I'll write up the long story of the Beowulf Mailing List > problems over the weekend, assuming that everything continues running. > - DJB]] > > On Fri, 14 May 2004, Greg Lindahl wrote: > > > On Fri, May 14, 2004 at 11:49:34AM -0400, Robert G. Brown wrote: > > > > > rgb at s02|B:1003>./Ospin > > > -bash: ./Ospin: /lib/ld-linux.so.2: bad ELF interpreter: No such file or directory > > > rgb at s02|B:1004> > > > > Pilot error. You have to install a couple of additional rpms to run > > 32-bit stuff on an Opteron. The annoying thing about it is that they > > have the same names as x86_64 packages, grrrr. In this case you need > > glibc-*.i686.rpm. > > That makes it sound easier than it really is... > > We distribute 32 bit library RPMs with the Scyld Beowulf for AMD64 > distribution. But those libraries are not just a simple duplication of > the x86 32 bit RPMs. > > The 32 bit library RPMs must contain only the libraries, not other > configuration and documentation files. The libraries must placed > in the proper directories or otherwise made to have non-conflicting > names. Some libraries that exist only as 32 bit versions must be placed > in the LSB-standard location. And all of this get extra complicated > with 3rd party compilers. > > We started out with an ad hoc approach, using the 32 bit RPMs, but > quickly decided that it had too many exceptions to support for end users. We just haven't messed with trying to (build and/or) install the compatibility libraries on our Opterons (yet). It's not that big a deal to do a recompile or rebuild to 64 bit code (for cleanly written applications), and we're currently using all our Opterons as relatively thin compute nodes so it is typically only one or two strictly numerical applications that need the recompile. If/when they start showing up on the desktop, perhaps this will change. I haven't looked at the latest version of the fedora64 core to see if somebody has built and contributed the libraries in a way that will kickstart/yum (sheer laziness on my part, let's see: rgb at s02|B:1001>yum list glibc\* Gathering header information file(s) from server(s) Server: Fedora Core 1 - x86_64 - base Server: Physics RHL Server: Fedora Core 1 - x86_64 - updates Finding updated packages Downloading needed headers Looking in Available Packages: Name Arch Version Repo -------------------------------------------------------------------------------- glibc i686 2.3.2-101.4 base glibc-debug x86_64 2.3.2-101.4 base glibc-devel i386 2.3.2-101.4 base glibc-profile x86_64 2.3.2-101.4 base glibc-utils x86_64 2.3.2-101.4 base Looking in Installed Packages: Name Arch Version Repo -------------------------------------------------------------------------------- glibc x86_64 2.3.2-101.4 db glibc-common x86_64 2.3.2-101.4 db glibc-devel x86_64 2.3.2-101.4 db glibc-headers x86_64 2.3.2-101.4 db glibc-kernheaders x86_64 2.4-8.36 db Hmmm, looks like there is a glibc i686. I'm home, and not eager to try a secondary glibc install from here because messing with glibc on a running system HAS been known to crash systems;-) but perhaps next week I'll experiment with this some If this fedora rpm just "works", it should be fairly simple to get it to install in kickstart (if necessary in the %post), but I'm not sure how to get it to install in yum. I'll ask Seth about it -- if this is a compatibility library rpm, it should probably have a name like glibc_i686 or glibc_32 to make it easier to install and update. rgb -- Robert G. Brown http://www.phy.duke.edu/~rgb/ Duke University Dept. of Physics, Box 90305 Durham, N.C. 27708-0305 Phone: 1-919-660-2567 Fax: 919-660-2525 email:rgb at phy.duke.edu
- Previous message: [Beowulf] Athlon64 / Opteron test
- Next message: [Beowulf] Re: Athlon64 / Opteron test
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
