Wierd smart talkin'

Collapse
This topic is closed.
X
X
 
  • Time
  • Show
Clear All
new posts
  • Jeremy Cowles

    Wierd smart talkin'

    I am new to C++ (and have only a light understanding of ASM).
    I know this is a bit off topic, but I read this the other day and was
    wondering exactly what they mean:

    "The original Q2 has optimized x86 assembly rasterizers, these were one of
    the fastest of their time, and they played with cunning tricks such as
    explicitely paralellizing x86 and x87 instructions to achieve maximum speed
    (for example, the division for perspective correction for the next 8 pixel
    span was performed in parallel with the actual rendering of the current 8
    pixel span, ie, the perspective correction was almost 'free'). "

    What does that mean "explicitly paralellizing"?


    Thanks,
    Jeremy

  • Alf P. Steinbach

    #2
    Re: Wierd smart talkin'

    On Thu, 17 Jul 2003 13:11:51 GMT, "Jeremy Cowles" <jeremy.stop-spam-now.cowles@asif l.com> wrote:
    [color=blue]
    >I am new to C++ (and have only a light understanding of ASM).
    >I know this is a bit off topic, but I read this the other day and was
    >wondering exactly what they mean:
    >
    >"The original Q2 has optimized x86 assembly rasterizers, these were one of
    >the fastest of their time, and they played with cunning tricks such as
    >explicitely paralellizing x86 and x87 instructions to achieve maximum speed
    >(for example, the division for perspective correction for the next 8 pixel
    >span was performed in parallel with the actual rendering of the current 8
    >pixel span, ie, the perspective correction was almost 'free'). "
    >
    >What does that mean "explicitly paralellizing"?[/color]

    That's not a standard term in either assembly languge or C++, as far
    as I'm aware.

    What it means is just that they used the x87 math coprocessor to
    execute some arithmetic in parallell with the rendering code.

    A good C++ compiler may do that optimization, and many other low-level
    optimizations, automatically for you.

    Comment

    Working...