Home

nevrax.com

Nevrax.org News Mailing-list Documentation CVS Bugs License

Documentation                       Search   NLMISC::CFastMem Class Reference Functions for Fast Memory manipulation with Pentium-class processors. More... #include <fast_mem.h> List of all members. Static Public Methods void  precache (const void *src, uint nbytes)   Fast precaching of memory in L1 cache using SSE or MMX where available (NB: others methods don't do the test) nbytes should not override 4K. More... void *  memcpySSE (void *dst, const void *src, size_t nbytes)   Fast memcpy using SSE instructions: prefetchnta and movntq. More... void  precacheSSE (const void *src, uint nbytes)   Fast precaching of memory in L1 cache using MMX/SSE instructions: movq and prefetchnta Result is typically 880 Mo/s (surely slower because of overhead). More... void  precacheMMX (const void *src, uint nbytes)   Fast precaching of memory in L1 cache using MMX instructions only: movq Result is typically 720 Mo/s (surely slower because of overhead). More... Detailed Description Functions for Fast Memory manipulation with Pentium-class processors. From http://www.sgi.com/developers/technology/irix/resources/asc_cpu.html Author: Lionel Berenguier , Nevrax France Date: 2002 Definition at line 44 of file fast_mem.h. Member Function Documentation void * NLMISC::CFastMem::memcpySSE (  void *    dst, const void *    src, size_t    nbytes )  [static]   Fast memcpy using SSE instructions: prefetchnta and movntq. Can be called only if SSE and MMX is supported NB: Copy per block of 4K through L1 cache Result is typically 420 Mo/s instead of 150 Mo/s. Definition at line 205 of file fast_mem.cpp. References src. void NLMISC::CFastMem::precache (  const void *    src, uint    nbytes )  [static]   Fast precaching of memory in L1 cache using SSE or MMX where available (NB: others methods don't do the test) nbytes should not override 4K. Definition at line 218 of file fast_mem.cpp. References src. void NLMISC::CFastMem::precacheMMX (  const void *    src, uint    nbytes )  [static]   Fast precaching of memory in L1 cache using MMX instructions only: movq Result is typically 720 Mo/s (surely slower because of overhead). Hence prefer precacheSSE() when available. nbytes should not override 4K Definition at line 214 of file fast_mem.cpp. References src. void NLMISC::CFastMem::precacheSSE (  const void *    src, uint    nbytes )  [static]   Fast precaching of memory in L1 cache using MMX/SSE instructions: movq and prefetchnta Result is typically 880 Mo/s (surely slower because of overhead). nbytes should not override 4K Definition at line 210 of file fast_mem.cpp. References src. The documentation for this class was generated from the following files: fast_mem.h fast_mem.cpp