Mercurial > libavcodec.hg

comparison avcodec.h @ 12197:fbf4d5b1b664 libavcodec

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Remove FF_MM_SSE2/3 flags for CPUs where this is generally not faster than regular MMX code. Examples of this are the Core1 CPU. Instead, set a new flag, FF_MM_SSE2/3SLOW, which can be checked for particular SSE2/3 functions that have been checked specifically on such CPUs and are actually faster than their MMX counterparts. In addition, use this flag to enable particular VP8 and LPC SSE2 functions that are faster than their MMX counterparts. Based on a patch by Loren Merritt <lorenm AT u washington edu>.
author rbultje
date Mon, 19 Jul 2010 22:38:23 +0000
parents fb2f04f70afe
children 8de66be22d87
comparison
equal deleted inserted replaced
12196:552c7c10bc73 12197:fbf4d5b1b664
1654 #define FF_MM_MMXEXT 0x0002 ///< SSE integer functions or AMD MMX ext 1654 #define FF_MM_MMXEXT 0x0002 ///< SSE integer functions or AMD MMX ext
1655 #endif 1655 #endif
1656 #define FF_MM_MMX2 0x0002 ///< SSE integer functions or AMD MMX ext 1656 #define FF_MM_MMX2 0x0002 ///< SSE integer functions or AMD MMX ext
1657 #define FF_MM_SSE 0x0008 ///< SSE functions 1657 #define FF_MM_SSE 0x0008 ///< SSE functions
1658 #define FF_MM_SSE2 0x0010 ///< PIV SSE2 functions 1658 #define FF_MM_SSE2 0x0010 ///< PIV SSE2 functions
1659 #define FF_MM_SSE2SLOW 0x40000000 ///< SSE2 supported, but usually not faster
1660 ///< than regular MMX/SSE (e.g. Core1)
1659 #define FF_MM_3DNOWEXT 0x0020 ///< AMD 3DNowExt 1661 #define FF_MM_3DNOWEXT 0x0020 ///< AMD 3DNowExt
1660 #define FF_MM_SSE3 0x0040 ///< Prescott SSE3 functions 1662 #define FF_MM_SSE3 0x0040 ///< Prescott SSE3 functions
1663 #define FF_MM_SSE3SLOW 0x20000000 ///< SSE3 supported, but usually not faster
1664 ///< than regular MMX/SSE (e.g. Core1)
1661 #define FF_MM_SSSE3 0x0080 ///< Conroe SSSE3 functions 1665 #define FF_MM_SSSE3 0x0080 ///< Conroe SSSE3 functions
1662 #define FF_MM_SSE4 0x0100 ///< Penryn SSE4.1 functions 1666 #define FF_MM_SSE4 0x0100 ///< Penryn SSE4.1 functions
1663 #define FF_MM_SSE42 0x0200 ///< Nehalem SSE4.2 functions 1667 #define FF_MM_SSE42 0x0200 ///< Nehalem SSE4.2 functions
1664 #define FF_MM_IWMMXT 0x0100 ///< XScale IWMMXT 1668 #define FF_MM_IWMMXT 0x0100 ///< XScale IWMMXT
1665 #define FF_MM_ALTIVEC 0x0001 ///< standard AltiVec 1669 #define FF_MM_ALTIVEC 0x0001 ///< standard AltiVec