Re: Linux/IA-64 byte order
Richard Gooch (rgooch@atnf.csiro.au)
Tue, 9 Mar 1999 19:56:08 +1100
Oren Laadan writes:
> Hi,
>
> > > Make an empty map for little-endian direct access and make a backing
> > > map with theactual file. Then install a signal handler to catch
> > > reads in the empty map, copy a page (or more) with byteswapping, and
> > > you're done. "Loading" is still extremely fast.
> >
> > Yes, "loading" a subsection of the data is still (fairly) fast. But
> > that doesn't solve the other problem: huge swap space consumption when
> > you want to access the entire dataset. It's often the case that you
> > have much more data disc than you have swap disc.
>
> How about this simple solution - write/use a utility which converts
> the data file from BE to LE (once for every file) ? (of course, you
> would need to know the exact structure of the binary data in the
> file for that).
You're talking about doubling the disc storage requirements. The
software which wrote the data is also going to be used to do some
analysis, so the user needs to keep that version around.
> This worked for me when I needed to compile and execute applications
> that used to run on Sparc, and required the original binary data
> files :-)
Experience has showed that users don't like these extra steps. It has
to be transparent. And transparently writing out a byte swapped copy
of the data is not going to be received well, either.
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/