From 38c51d7eb68300a56407a487f8b8982839765258 Mon Sep 17 00:00:00 2001 From: diego Date: Fri, 4 Jul 2008 13:14:29 +0000 Subject: whitespace cosmetics git-svn-id: svn://svn.mplayerhq.hu/mplayer/trunk@27188 b3059339-0415-0410-9bf9-f77b7e298cf2 --- libswscale/internal_bfin.S | 85 ++++++++++++++++++++++---------------------- libswscale/yuv2rgb_altivec.c | 78 ++++++++++++++++++++-------------------- 2 files changed, 81 insertions(+), 82 deletions(-) (limited to 'libswscale') diff --git a/libswscale/internal_bfin.S b/libswscale/internal_bfin.S index 2d5c61a14a..7dcd019fae 100644 --- a/libswscale/internal_bfin.S +++ b/libswscale/internal_bfin.S @@ -24,74 +24,73 @@ /* - YUV420 to RGB565 conversion. This routine takes a YUV 420 planar macroblock - and converts it to RGB565. R:5 bits, G:6 bits, B:5 bits.. packed into shorts +YUV420 to RGB565 conversion. This routine takes a YUV 420 planar macroblock +and converts it to RGB565. R:5 bits, G:6 bits, B:5 bits.. packed into shorts - The following calculation is used for the conversion: +The following calculation is used for the conversion: - r = clipz((y-oy)*cy + crv*(v-128)) - g = clipz((y-oy)*cy + cgv*(v-128) + cgu*(u-128)) - b = clipz((y-oy)*cy + cbu*(u-128)) + r = clipz((y-oy)*cy + crv*(v-128)) + g = clipz((y-oy)*cy + cgv*(v-128) + cgu*(u-128)) + b = clipz((y-oy)*cy + cbu*(u-128)) - y,u,v are pre scaled by a factor of 4 i.e. left shifted to gain precision. +y,u,v are pre scaled by a factor of 4 i.e. left shifted to gain precision. - New factorization to eliminate the truncation error which was - occuring due to the byteop3p. +New factorization to eliminate the truncation error which was +occuring due to the byteop3p. - 1) use the bytop16m to subtract quad bytes we use this in U8 this - then so the offsets need to be renormalized to 8bits. +1) use the bytop16m to subtract quad bytes we use this in U8 this + then so the offsets need to be renormalized to 8bits. - 2) scale operands up by a factor of 4 not 8 because Blackfin - multiplies include a shift. +2) scale operands up by a factor of 4 not 8 because Blackfin + multiplies include a shift. - 3) compute into the accumulators cy*yx0, cy*yx1 +3) compute into the accumulators cy*yx0, cy*yx1 - 4) compute each of the linear equations - r = clipz((y-oy)*cy + crv*(v-128)) +4) compute each of the linear equations + r = clipz((y - oy) * cy + crv * (v - 128)) - g = clipz((y-oy)*cy + cgv*(v-128) + cgu*(u-128)) + g = clipz((y - oy) * cy + cgv * (v - 128) + cgu * (u - 128)) - b = clipz((y-oy)*cy + cbu*(u-128)) + b = clipz((y - oy) * cy + cbu * (u - 128)) - reuse of the accumulators requires that we actually multiply - twice once with addition and the second time with a subtaction. + reuse of the accumulators requires that we actually multiply + twice once with addition and the second time with a subtaction. - because of this we need to compute the equations in the order R B - then G saving the writes for B in the case of 24/32 bit color - formats. + because of this we need to compute the equations in the order R B + then G saving the writes for B in the case of 24/32 bit color + formats. - api: yuv2rgb_kind (uint8_t *Y, uint8_t *U, uint8_t *V, int *out, - int dW, uint32_t *coeffs); + api: yuv2rgb_kind (uint8_t *Y, uint8_t *U, uint8_t *V, int *out, + int dW, uint32_t *coeffs); - A B - --- --- - i2 = cb i3 = cr - i1 = coeff i0 = y + A B + --- --- + i2 = cb i3 = cr + i1 = coeff i0 = y - Where coeffs have the following layout in memory. +Where coeffs have the following layout in memory. - uint32_t oy,oc,zero,cy,crv,rmask,cbu,bmask,cgu,cgv; +uint32_t oy,oc,zero,cy,crv,rmask,cbu,bmask,cgu,cgv; - coeffs is a pointer to oy. +coeffs is a pointer to oy. - the {rgb} masks are only utilized by the 565 packing algorithm. Note the data - replication is used to simplify the internal algorithms for the dual mac architecture - of BlackFin. +the {rgb} masks are only utilized by the 565 packing algorithm. Note the data +replication is used to simplify the internal algorithms for the dual mac architecture +of BlackFin. - All routines are exported with _ff_bfin_ as a symbol prefix +All routines are exported with _ff_bfin_ as a symbol prefix - rough performance gain compared against -O3: +rough performance gain compared against -O3: - 2779809/1484290 187.28% - - which translates to ~33c/pel to ~57c/pel for the reference vs 17.5 - c/pel for the optimized implementations. Not sure why there is such a - huge variation on the reference codes on Blackfin I guess it must have - to do with the memory system. +2779809/1484290 187.28% +which translates to ~33c/pel to ~57c/pel for the reference vs 17.5 +c/pel for the optimized implementations. Not sure why there is such a +huge variation on the reference codes on Blackfin I guess it must have +to do with the memory system. */ #define mL3 .text diff --git a/libswscale/yuv2rgb_altivec.c b/libswscale/yuv2rgb_altivec.c index de6390001a..3583e4bf65 100644 --- a/libswscale/yuv2rgb_altivec.c +++ b/libswscale/yuv2rgb_altivec.c @@ -21,63 +21,63 @@ */ /* - convert I420 YV12 to RGB in various formats, - it rejects images that are not in 420 formats - it rejects images that don't have widths of multiples of 16 - it rejects images that don't have heights of multiples of 2 - reject defers to C simulation codes. +convert I420 YV12 to RGB in various formats, + it rejects images that are not in 420 formats + it rejects images that don't have widths of multiples of 16 + it rejects images that don't have heights of multiples of 2 +reject defers to C simulation codes. - lots of optimizations to be done here +lots of optimizations to be done here - 1. need to fix saturation code, I just couldn't get it to fly with packs and adds. - so we currently use max min to clip +1. need to fix saturation code, I just couldn't get it to fly with packs and adds. + so we currently use max min to clip - 2. the inefficient use of chroma loading needs a bit of brushing up +2. the inefficient use of chroma loading needs a bit of brushing up - 3. analysis of pipeline stalls needs to be done, use shark to identify pipeline stalls +3. analysis of pipeline stalls needs to be done, use shark to identify pipeline stalls - MODIFIED to calculate coeffs from currently selected color space. - MODIFIED core to be a macro which you spec the output format. - ADDED UYVY conversion which is never called due to some thing in SWSCALE. - CORRECTED algorithim selection to be strict on input formats. - ADDED runtime detection of altivec. +MODIFIED to calculate coeffs from currently selected color space. +MODIFIED core to be a macro which you spec the output format. +ADDED UYVY conversion which is never called due to some thing in SWSCALE. +CORRECTED algorithim selection to be strict on input formats. +ADDED runtime detection of altivec. - ADDED altivec_yuv2packedX vertical scl + RGB converter +ADDED altivec_yuv2packedX vertical scl + RGB converter - March 27,2004 - PERFORMANCE ANALYSIS +March 27,2004 +PERFORMANCE ANALYSIS - The C version use 25% of the processor or ~250Mips for D1 video rawvideo used as test - The ALTIVEC version uses 10% of the processor or ~100Mips for D1 video same sequence +The C version use 25% of the processor or ~250Mips for D1 video rawvideo used as test +The ALTIVEC version uses 10% of the processor or ~100Mips for D1 video same sequence - 720*480*30 ~10MPS +720*480*30 ~10MPS - so we have roughly 10clocks per pixel this is too high something has to be wrong. +so we have roughly 10clocks per pixel this is too high something has to be wrong. - OPTIMIZED clip codes to utilize vec_max and vec_packs removing the need for vec_min. +OPTIMIZED clip codes to utilize vec_max and vec_packs removing the need for vec_min. - OPTIMIZED DST OUTPUT cache/dma controls. we are pretty much - guaranteed to have the input video frame it was just decompressed so - it probably resides in L1 caches. However we are creating the - output video stream this needs to use the DSTST instruction to - optimize for the cache. We couple this with the fact that we are - not going to be visiting the input buffer again so we mark it Least - Recently Used. This shaves 25% of the processor cycles off. +OPTIMIZED DST OUTPUT cache/dma controls. we are pretty much +guaranteed to have the input video frame it was just decompressed so +it probably resides in L1 caches. However we are creating the +output video stream this needs to use the DSTST instruction to +optimize for the cache. We couple this with the fact that we are +not going to be visiting the input buffer again so we mark it Least +Recently Used. This shaves 25% of the processor cycles off. - Now MEMCPY is the largest mips consumer in the system, probably due - to the inefficient X11 stuff. +Now MEMCPY is the largest mips consumer in the system, probably due +to the inefficient X11 stuff. - GL libraries seem to be very slow on this machine 1.33Ghz PB running - Jaguar, this is not the case for my 1Ghz PB. I thought it might be - a versioning issues, however I have libGL.1.2.dylib for both - machines. ((We need to figure this out now)) +GL libraries seem to be very slow on this machine 1.33Ghz PB running +Jaguar, this is not the case for my 1Ghz PB. I thought it might be +a versioning issues, however I have libGL.1.2.dylib for both +machines. ((We need to figure this out now)) - GL2 libraries work now with patch for RGB32 +GL2 libraries work now with patch for RGB32 - NOTE quartz vo driver ARGB32_to_RGB24 consumes 30% of the processor +NOTE quartz vo driver ARGB32_to_RGB24 consumes 30% of the processor - Integrated luma prescaling adjustment for saturation/contrast/brightness adjustment. +Integrated luma prescaling adjustment for saturation/contrast/brightness adjustment. */ #include -- cgit v1.2.3