fast memset/memcpy

From: Mark Grinnell (spamtrap_at_crayne.org)
Date: 11/10/04

  • Next message: Robert Redelmeier: "Re: fast memset/memcpy" 
    Date: Wed, 10 Nov 2004 18:25:16 +0000 (UTC)

    Probably most of the experts in this group know this, but I was surprised to
    find that the rep* instructions I've been using for memset/memcpy type
    operations like
            rep stosd
    are very slow. Does anyone know of any highly optimized routines to
    accomplish this faster? My case is easy, since I know my memory is dword
    aligned and I always set or move a multiple of 4 bytes.

  • Next message: Robert Redelmeier: "Re: fast memset/memcpy"

    Relevant Pages

    • Re: you cant bash Microsoft enough
      ... The math format is 32.32, ... Instructions like sub and mov are ... and the FPGA gets warmer than the CPU. ... serious multiple of the processor lifetime. ...
      (sci.electronics.design)
    • Re: Clear SWks Instructions...Please?
      ... paper & web instructions, got to the end after 3 CDs and said there was ... MULTIPLE instances of bad documentation. ... SWks or SWks Express, which had the information, but I didn't find the ...
      (comp.cad.solidworks)
    • Re: [OT]Re: atomic flag
      ... > You are wrong - at least on systems with multiple processors. ... 'interlocked' machine instructions of the sort TSTI, INCI, DECI, ... etc which are garanteed to use a single bus transaction regardless ... maybe by your compiler. ...
      (comp.lang.cpp)
    • Re: OT: Adding new Windows registry key?
      ... > I'm not clear about interpreting the following instructions I found ... > Type is: DWORD ... as you hold it down while the disk loads up and then spins up. ...
      (sci.electronics.design)
    • Re: RosAsm Team is Still Making Excuses
      ... >> and compare the execution time with this two instructions: ... > four in a DWORD sized "temporary register" internally (e.g. it reads an ... > entire DWORD into this "temporary register" and can thus simply refer to ... > You must really be measuring something _quite different_ here, ...
      (alt.lang.asm)