commit d2e1e1c35c43ea9c90c9211be6202143b69b35b9 Author: Guillaume Poirier Date: Tue Apr 21 21:18:44 2009 +0000 fix "incompatible types in initialization" compilation issues with GCC 4.3 (which is stricter than previous compiler version) common/ppc/pixel.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-) commit 4fc8c03ad568efe3dd2f57db33b0863d29cb63a0 Author: Guillaume Poirier Date: Tue Apr 21 17:32:21 2009 +0200 fix conversions between vectors with differing element types or numbers of subparts errors common/ppc/pixel.c | 4 ++-- 1 files changed, 2 insertions(+), 2 deletions(-) commit 755470584932877c4d5ea1b51c2cc2dbd044b7ca Author: Jason Garrett-Glaser Date: Sat Apr 18 16:07:53 2009 -0700 Add "coded blocks" stat to output information. This measures the total percentage of blocks, intra and inter, which have nonzero coefficients. "y,uvAC,uvDC" refers to luma, chroma DC, and chroma AC blocks. Note that skip blocks are included in this stat. common/common.h | 2 ++ encoder/encoder.c | 31 ++++++++++++++++++++++++++----- 2 files changed, 28 insertions(+), 5 deletions(-) commit a908c88f0bbd4250afbd16b6c55b3c9f613af96d Author: Jason Garrett-Glaser Date: Fri Apr 17 23:38:29 2009 -0700 Enable asm predict_8x8_filter I'm not entirely sure how this snuck its way out of holger's intra pred patch. common/predict.c | 8 ++++---- common/predict.h | 5 +---- encoder/analyse.c | 2 +- encoder/macroblock.c | 2 +- encoder/slicetype.c | 2 +- 5 files changed, 8 insertions(+), 11 deletions(-) commit c74726e1ed0312e2073f0ea8c45804a870512579 Author: Jason Garrett-Glaser Date: Fri Apr 17 06:00:39 2009 -0700 Remove various bits of dead code found by CLANG. encoder/analyse.c | 7 ------- encoder/encoder.c | 1 - encoder/me.c | 4 +--- muxers.c | 5 ++--- 4 files changed, 3 insertions(+), 14 deletions(-) commit 37424f87a43a2dcecba61bc24b46506ced32307c Author: Jason Garrett-Glaser Date: Tue Apr 14 14:47:02 2009 -0700 Slightly faster SSE4 SA8D, SSE4 Hadamard_AC, SSE2 SSIM shufps is the most underrated SSE instruction on x86. common/x86/pixel-a.asm | 63 +++++++++++++++++++++++++++++------------------- 1 files changed, 38 insertions(+), 25 deletions(-) commit 1024283b0321e53a3e08fddb1411429330bf1731 Author: Jason Garrett-Glaser Date: Thu Apr 9 02:14:41 2009 -0700 Various CABAC optimizations Move calculation of b_intra out of the core residual loop and hardcode it where applicable. Inlining cabac_mb_mvd was unnecessary and wasted tremendous amounts of code size. Inlining only cache_mvd is faster and significantly smaller. encoder/cabac.c | 55 ++++++++++++++++++++++++++++++++----------------------- 1 files changed, 32 insertions(+), 23 deletions(-) commit fe11a6f39e4e8235d685591ec9c0ec86eca4fee9 Author: Jason Garrett-Glaser Date: Wed Apr 8 05:45:03 2009 -0700 CAVLC optimizations faster bs_write_te, port CABAC context selection optimization to CAVLC. common/bs.h | 6 ++---- encoder/analyse.c | 2 +- encoder/cavlc.c | 35 +++++++++++++++++++++-------------- 3 files changed, 24 insertions(+), 19 deletions(-) commit 1fda88277f6b2eda27a0f741d58b31532ad0664d Author: Jason Garrett-Glaser Date: Sun Apr 5 13:01:42 2009 -0700 Faster CABAC RDO Since the bypass case is quite unlikely, especially when doing merged sigmap/level coding, it's faster to use a branch than a cmov. encoder/cabac.c | 44 ++++++++++++++++++++++++++++---------------- 1 files changed, 28 insertions(+), 16 deletions(-) commit 3f9ba82b9788231c879d31d9c4c8ebf4518d07fe Author: Jason Garrett-Glaser Date: Tue Mar 31 10:36:57 2009 -0700 Activate intra_sad_x3_8x8c in lookahead encoder/slicetype.c | 6 +++--- 1 files changed, 3 insertions(+), 3 deletions(-) commit 9d0c378b235182341edd2e95f01d4fd25132ad50 Author: Jason Garrett-Glaser Date: Tue Mar 31 10:34:35 2009 -0700 MBAFF interlaced coding is not allowed in baseline profile encoder/set.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-) commit b8808bf0a35b83c2fac05e07a504ad164c931960 Author: Jason Garrett-Glaser Date: Mon Mar 30 19:30:59 2009 -0700 intra_sad_x3_8x8 assembly common/pixel.c | 1 + common/pixel.h | 2 + common/x86/pixel.h | 1 + common/x86/sad-a.asm | 68 ++++++++++++++++++++++++++++++++++++++++++++++++++ encoder/analyse.c | 4 +- tools/checkasm.c | 1 + 6 files changed, 75 insertions(+), 2 deletions(-) commit 8df40a4c41eb5e79d0055f2e5af4b214285b9c8c Author: Jason Garrett-Glaser Date: Mon Mar 30 16:37:46 2009 -0700 intra_sad_x3_4x4 assembly common/pixel.c | 1 + common/pixel.h | 2 ++ common/x86/pixel.h | 1 + common/x86/sad-a.asm | 47 +++++++++++++++++++++++++++++++++++++++++++++++ encoder/analyse.c | 2 +- encoder/encoder.c | 1 + tools/checkasm.c | 1 + 7 files changed, 54 insertions(+), 1 deletions(-) commit d39f8ae1730b07286f1bb281a22d8cd57d0f90b9 Author: Jason Garrett-Glaser Date: Mon Mar 30 04:07:50 2009 -0700 intra_sad_x3_8x8c assembly Also fix intra_sad_x3_16x16's use of "n" as a loop variable (broke SWAP) common/pixel.c | 4 +- common/pixel.h | 2 + common/x86/pixel.h | 2 + common/x86/sad-a.asm | 127 ++++++++++++++++++++++++++++++++++++++++++++++++- encoder/analyse.c | 7 ++- encoder/encoder.c | 1 + tools/checkasm.c | 1 + 7 files changed, 137 insertions(+), 7 deletions(-) commit d3ca4647a247186c2df7760be2a9c649efe34815 Author: Jason Garrett-Glaser Date: Sun Mar 29 18:27:32 2009 -0700 Shave one instruction off CABAC encode_decision range_lps>>6 ranges from 4-7, so (range_lps>>6)-4 == (range_lps>>6) & 3 common/cabac.c | 2 +- common/x86/cabac-a.asm | 3 +-- 2 files changed, 2 insertions(+), 3 deletions(-)