Yes, and for alphas I malloc() and read() with byte swapping. It's not
that I can't support LE machines (I develop under Linux/x86, after
all), it's just that performance on LE machines is much lower than BE
machines where I can safely mmap(). Also, the LE machines require swap
space at least equal to the dataset size. When we're talking about
datasets in the gigabytes, this becomes a problem (especially if
multiple users want to view the same dataset).
> And as for
> > In the astronomy community, big-endian machines dominate
> Armagh observatory hasn't got a single Big endian machine - 40 Linux
> PC's and about 15 Alphas (abotu 10 running linux). Actually I
> lie... I have a sparc 2 at home, and there's an IPC I've hooked up
> to some old disks to serve some disks...
I've worked at or visited ATNF, AAO, SydUni, UNSW, MSSSO, NRAO, UMN,
NCSA(Illinois), UCalgary, DRAO, Uni Durham, NFRA, RUG and Uni Bonn and
with the exception of Uni Bonn, they're all dominated by BE machines.
Regards,
Richard....
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/