[Beowulf] re: Quick question... on Fortran
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.
Bill Broadley bill at cse.ucdavis.eduThu May 10 13:48:59 PDT 2007
- Previous message: [Beowulf] re: Quick question... on Fortran
- Next message: [Beowulf] Quick question... on Fortran
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
> The limit is 2GB for Intel ia-32 compilers, fortran or not. You may > need to compile -static to get it. Since this is half the 4GB limit of > a 32 bit system (maybe the last bit is lost because of signed > arithmetic?), I'm guessing the ia-64 compilers can have much larger > arrays. For g77 with a 32 bit binary I think you are right: bigmem.f:119: error: size of variable 'a' is too large pathf90 producing a 32 bit binary: ### Assertion failure at line 726 of ../../be/cg/x8664/exp_loadstore.cxx: ### Compiler Error in file bigmem.f during Code_Expansion phase: ### NYI: 64-bit offset under -m32 Gcc and a 32 bit binary seems fine with 3GB: # file ./a.out ./a.out: ELF 32-bit LSB executable, Intel 80386, version 1 (SYSV), for GNU/Linux 2.2.5, dynamically linked (uses shared libs), not stripped Verified with top: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 16246 root 25 0 3073m 3.0g 288 R 100 76.7 0:07.09 a.out with x86-64 binaries I've tried 6GB arrays, and could try 12 GB if there is interest.
- Previous message: [Beowulf] re: Quick question... on Fortran
- Next message: [Beowulf] Quick question... on Fortran
- Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]
More information about the Beowulf mailing list
