Re: Linux/IA-64 byte order

From: Donald H. Gudehus (gpage11_at_comcast.net)
Date: 01/31/04

  • Next message: Jamie Lokier: "Re: [RFC][PATCH] linux-2.6.2-rc2_vsyscall-gtod_B1.patch" 
    Date:	Fri, 30 Jan 2004 18:35:15 -0800
To: linux-kernel@vger.kernel.org

    >I write visualisation software for astronomy. This software is used
    >all over the world, and often has to deal with very large
    >datasets. It's not uncommon to "load" a dataset (a cube) but only view
    >a small portion of it (a single plane (channel) of the cube). On
    >big-endian machines I can avoid loading data and instead use memory
    >mapping, because all the portable binary data formats are big-endian
    >(FITS, Miriad and my own).

    The SAD (Standard Astronomical Data) format is little-endian and was, in
    fact, developed in your home country at Mt. Stromlo and Sliding Springs
    Observatory.

    >In the astronomy community, big-endian machines dominate (despite the
    >growth of Linux/x86), and will always be favoured because the most
    >important data format (FITS) is big-endian. When we tender for a new
    >supercomputer, it is a requirement that it be big-endian.
    >BTW: FITS has become a NIST standard and is widely used outside the
    >astronomy community.

    Here in the US, FITS can be big-endian or little-endian depending on
    whether the keyword BYTEORDR equals BIG_ENDIAN or LITTLE_ENDIAN.
    Unfortunately this keyword is not always used because the byte order was
    never specified in the original FITS description. This naturally has
    led to some confusion, with some facilities adopting big endian, some
    adopting little endian, and some simply using the native format of the
    machine.

    Conceptually, it is more natural to have bits and bytes increase in
    significance as system memory location (word address) increases. This
    is of course completely independent of graphical representations where
    bit significance increases to the left, byte significance to the left or
    right, and word significance to the left or right (four possible cases).

    Donald Gudehus
    -
    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to majordomo@vger.kernel.org
    More majordomo info at http://vger.kernel.org/majordomo-info.html
    Please read the FAQ at http://www.tux.org/lkml/

  • Next message: Jamie Lokier: "Re: [RFC][PATCH] linux-2.6.2-rc2_vsyscall-gtod_B1.patch"