From 05c04cdf54fee9332d337380fd4cd8502bdac2be Mon Sep 17 00:00:00 2001 From: Jason Garrett-Glaser Date: Thu, 12 Aug 2010 01:11:32 +0000 Subject: [PATCH] VP5/6/8: ~7% faster arithmetic decoding Grab from the bitstream in 16-bit chunks instead of 8-bit chunks. TODO: grab in 32-bit chunks on 64-bit systems. Originally committed as revision 24783 to svn://svn.ffmpeg.org/ffmpeg/trunk --- libavcodec/vp56.h | 10 +++++----- libavcodec/vp56rac.c | 4 ++-- libavcodec/x86/vp56_arith.h | 2 +- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/libavcodec/vp56.h b/libavcodec/vp56.h index 50a39f75bc..da6b1b64b8 100644 --- a/libavcodec/vp56.h +++ b/libavcodec/vp56.h @@ -194,8 +194,8 @@ static av_always_inline unsigned int vp56_rac_renorm(VP56RangeCoder *c) code_word <<= shift; bits += shift; if(bits >= 0 && c->buffer < c->end) { - code_word |= *c->buffer++ << bits; - bits -= 8; + code_word |= bytestream_get_be16(&c->buffer) << bits; + bits -= 16; } c->bits = bits; return code_word; @@ -211,7 +211,7 @@ static av_always_inline int vp56_rac_get_prob(VP56RangeCoder *c, uint8_t prob) { unsigned int code_word = vp56_rac_renorm(c); unsigned int low = 1 + (((c->high - 1) * prob) >> 8); - unsigned int low_shift = low << 8; + unsigned int low_shift = low << 16; int bit = code_word >= low_shift; c->high = bit ? c->high - low : low; @@ -226,7 +226,7 @@ static av_always_inline int vp56_rac_get_prob_branchy(VP56RangeCoder *c, int pro { unsigned long code_word = vp56_rac_renorm(c); unsigned low = 1 + (((c->high - 1) * prob) >> 8); - unsigned low_shift = low << 8; + unsigned low_shift = low << 16; if (code_word >= low_shift) { c->high -= low; @@ -244,7 +244,7 @@ static av_always_inline int vp56_rac_get(VP56RangeCoder *c) unsigned int code_word = vp56_rac_renorm(c); /* equiprobable */ int low = (c->high + 1) >> 1; - unsigned int low_shift = low << 8; + unsigned int low_shift = low << 16; int bit = code_word >= low_shift; if (bit) { c->high -= low; diff --git a/libavcodec/vp56rac.c b/libavcodec/vp56rac.c index 752a42bc6b..f11531de24 100644 --- a/libavcodec/vp56rac.c +++ b/libavcodec/vp56rac.c @@ -40,8 +40,8 @@ const uint8_t ff_vp56_norm_shift[256]= { void ff_vp56_init_range_decoder(VP56RangeCoder *c, const uint8_t *buf, int buf_size) { c->high = 255; - c->bits = -8; + c->bits = -16; c->buffer = buf; c->end = buf + buf_size; - c->code_word = bytestream_get_be16(&c->buffer); + c->code_word = bytestream_get_be24(&c->buffer); } diff --git a/libavcodec/x86/vp56_arith.h b/libavcodec/x86/vp56_arith.h index ae3bc3dc77..ddbf38b1a9 100644 --- a/libavcodec/x86/vp56_arith.h +++ b/libavcodec/x86/vp56_arith.h @@ -31,7 +31,7 @@ static av_always_inline int vp56_rac_get_prob(VP56RangeCoder *c, uint8_t prob) unsigned int code_word = vp56_rac_renorm(c); unsigned int high = c->high; unsigned int low = 1 + (((high - 1) * prob) >> 8); - unsigned int low_shift = low << 8; + unsigned int low_shift = low << 16; int bit = 0; __asm__(