From bd9c58756a50b52e495b748d6ea6b0aafe397c25 Mon Sep 17 00:00:00 2001 From: Ganesh Ajjanagadde Date: Mon, 29 Feb 2016 22:16:16 -0500 Subject: [PATCH] lavc/aacenc_utils: replace sqrtf(Q*sqrtf(Q)) by precomputed value It makes no sense whatsoever to do this at each function call; we already have a table for this. Yields a 2x improvement in find_min_book (x86-64, Haswell+GCC): ffmpeg -i sin.flac -acodec aac -y sin.aac find_min_book old 605 decicycles in find_min_book, 8388453 runs, 155 skips.9x 606 decicycles in find_min_book,16776912 runs, 304 skips.9x 607 decicycles in find_min_book,33553819 runs, 613 skips.2x 607 decicycles in find_min_book,67107668 runs, 1196 skips.3x 607 decicycles in find_min_book,134215360 runs, 2368 skips3x new 359 decicycles in find_min_book, 8388552 runs, 56 skips.3x 360 decicycles in find_min_book,16777112 runs, 104 skips.1x 361 decicycles in find_min_book,33554218 runs, 214 skips.4x 361 decicycles in find_min_book,67108381 runs, 483 skips.5x 361 decicycles in find_min_book,134216725 runs, 1003 skips5x and more importantly a non-negligible speedup (~ 8%) to overall AAC encoding: old: ffmpeg -i sin.flac -acodec aac -strict -2 -y sin_new.aac 6.82s user 0.03s system 104% cpu 6.565 total new: ffmpeg -i sin.flac -acodec aac -strict -2 -y sin_old.aac 6.24s user 0.03s system 104% cpu 5.993 total This also improves accuracy of the expression by ~ 2 ulp in some cases. Reviewed-by: Derek Buitenhuis Reviewed-by: Rostislav Pehlivanov Signed-off-by: Ganesh Ajjanagadde --- libavcodec/aacenc_utils.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/libavcodec/aacenc_utils.h b/libavcodec/aacenc_utils.h index cb5bc8da12..c2a2c2ec68 100644 --- a/libavcodec/aacenc_utils.h +++ b/libavcodec/aacenc_utils.h @@ -90,8 +90,7 @@ static inline float find_max_val(int group_len, int swb_size, const float *scale static inline int find_min_book(float maxval, int sf) { - float Q = ff_aac_pow2sf_tab[POW_SF2_ZERO - sf + SCALE_ONE_POS - SCALE_DIV_512]; - float Q34 = sqrtf(Q * sqrtf(Q)); + float Q34 = ff_aac_pow34sf_tab[POW_SF2_ZERO - sf + SCALE_ONE_POS - SCALE_DIV_512]; int qmaxval, cb; qmaxval = maxval * Q34 + C_QUANT; if (qmaxval >= (FF_ARRAY_ELEMS(aac_maxval_cb)))