On Sun, Feb 4, 2018 at 9:26 AM, James Almer <jamr...@gmail.com> wrote:
> On 2/3/2018 7:51 PM, Muhammad Faiz wrote:
>> Precalculate and constify ff_square_tab.
>>
>> Signed-off-by: Muhammad Faiz <mfc...@gmail.com>
>> ---
>> libavcodec/me_cmp.c | 51
>> +++++++++++++++++++++++++++++++++-----------
>> libavcodec/me_cmp.h | 4 +---
>> libavcodec/mpegvideo_enc.c | 2 +-
>> libavcodec/mpegvideoencdsp.c | 2 +-
>> libavcodec/snowenc.c | 2 +-
>> libavcodec/utils.c | 13 -----------
>> 6 files changed, 43 insertions(+), 31 deletions(-)
>>
>> diff --git a/libavcodec/me_cmp.c b/libavcodec/me_cmp.c
>> index 5e34a11593..67a5bb5c71 100644
>> --- a/libavcodec/me_cmp.c
>> +++ b/libavcodec/me_cmp.c
>> @@ -22,6 +22,7 @@
>>
>> #include "libavutil/attributes.h"
>> #include "libavutil/internal.h"
>> +#include "libavutil/thread.h"
>
> Unused?
>
>> #include "avcodec.h"
>> #include "copy_block.h"
>> #include "simple_idct.h"
>> @@ -29,13 +30,47 @@
>> #include "mpegvideo.h"
>> #include "config.h"
>>
>> -uint32_t ff_square_tab[512] = { 0, };
>> +/* (i - 256) * (i - 256) */
>> +const uint32_t ff_square_tab[512] = {
>> + 65536, 65025, 64516, 64009, 63504, 63001, 62500, 62001, 61504, 61009,
>> 60516, 60025, 59536, 59049, 58564, 58081,
>> + 57600, 57121, 56644, 56169, 55696, 55225, 54756, 54289, 53824, 53361,
>> 52900, 52441, 51984, 51529, 51076, 50625,
>> + 50176, 49729, 49284, 48841, 48400, 47961, 47524, 47089, 46656, 46225,
>> 45796, 45369, 44944, 44521, 44100, 43681,
>> + 43264, 42849, 42436, 42025, 41616, 41209, 40804, 40401, 40000, 39601,
>> 39204, 38809, 38416, 38025, 37636, 37249,
>> + 36864, 36481, 36100, 35721, 35344, 34969, 34596, 34225, 33856, 33489,
>> 33124, 32761, 32400, 32041, 31684, 31329,
>> + 30976, 30625, 30276, 29929, 29584, 29241, 28900, 28561, 28224, 27889,
>> 27556, 27225, 26896, 26569, 26244, 25921,
>> + 25600, 25281, 24964, 24649, 24336, 24025, 23716, 23409, 23104, 22801,
>> 22500, 22201, 21904, 21609, 21316, 21025,
>> + 20736, 20449, 20164, 19881, 19600, 19321, 19044, 18769, 18496, 18225,
>> 17956, 17689, 17424, 17161, 16900, 16641,
>> + 16384, 16129, 15876, 15625, 15376, 15129, 14884, 14641, 14400, 14161,
>> 13924, 13689, 13456, 13225, 12996, 12769,
>> + 12544, 12321, 12100, 11881, 11664, 11449, 11236, 11025, 10816, 10609,
>> 10404, 10201, 10000, 9801, 9604, 9409,
>> + 9216, 9025, 8836, 8649, 8464, 8281, 8100, 7921, 7744, 7569,
>> 7396, 7225, 7056, 6889, 6724, 6561,
>> + 6400, 6241, 6084, 5929, 5776, 5625, 5476, 5329, 5184, 5041,
>> 4900, 4761, 4624, 4489, 4356, 4225,
>> + 4096, 3969, 3844, 3721, 3600, 3481, 3364, 3249, 3136, 3025,
>> 2916, 2809, 2704, 2601, 2500, 2401,
>> + 2304, 2209, 2116, 2025, 1936, 1849, 1764, 1681, 1600, 1521,
>> 1444, 1369, 1296, 1225, 1156, 1089,
>> + 1024, 961, 900, 841, 784, 729, 676, 625, 576, 529,
>> 484, 441, 400, 361, 324, 289,
>> + 256, 225, 196, 169, 144, 121, 100, 81, 64, 49,
>> 36, 25, 16, 9, 4, 1,
>> + 0, 1, 4, 9, 16, 25, 36, 49, 64, 81,
>> 100, 121, 144, 169, 196, 225,
>> + 256, 289, 324, 361, 400, 441, 484, 529, 576, 625,
>> 676, 729, 784, 841, 900, 961,
>> + 1024, 1089, 1156, 1225, 1296, 1369, 1444, 1521, 1600, 1681,
>> 1764, 1849, 1936, 2025, 2116, 2209,
>> + 2304, 2401, 2500, 2601, 2704, 2809, 2916, 3025, 3136, 3249,
>> 3364, 3481, 3600, 3721, 3844, 3969,
>> + 4096, 4225, 4356, 4489, 4624, 4761, 4900, 5041, 5184, 5329,
>> 5476, 5625, 5776, 5929, 6084, 6241,
>> + 6400, 6561, 6724, 6889, 7056, 7225, 7396, 7569, 7744, 7921,
>> 8100, 8281, 8464, 8649, 8836, 9025,
>> + 9216, 9409, 9604, 9801, 10000, 10201, 10404, 10609, 10816, 11025,
>> 11236, 11449, 11664, 11881, 12100, 12321,
>> + 12544, 12769, 12996, 13225, 13456, 13689, 13924, 14161, 14400, 14641,
>> 14884, 15129, 15376, 15625, 15876, 16129,
>> + 16384, 16641, 16900, 17161, 17424, 17689, 17956, 18225, 18496, 18769,
>> 19044, 19321, 19600, 19881, 20164, 20449,
>> + 20736, 21025, 21316, 21609, 21904, 22201, 22500, 22801, 23104, 23409,
>> 23716, 24025, 24336, 24649, 24964, 25281,
>> + 25600, 25921, 26244, 26569, 26896, 27225, 27556, 27889, 28224, 28561,
>> 28900, 29241, 29584, 29929, 30276, 30625,
>> + 30976, 31329, 31684, 32041, 32400, 32761, 33124, 33489, 33856, 34225,
>> 34596, 34969, 35344, 35721, 36100, 36481,
>> + 36864, 37249, 37636, 38025, 38416, 38809, 39204, 39601, 40000, 40401,
>> 40804, 41209, 41616, 42025, 42436, 42849,
>> + 43264, 43681, 44100, 44521, 44944, 45369, 45796, 46225, 46656, 47089,
>> 47524, 47961, 48400, 48841, 49284, 49729,
>> + 50176, 50625, 51076, 51529, 51984, 52441, 52900, 53361, 53824, 54289,
>> 54756, 55225, 55696, 56169, 56644, 57121,
>> + 57600, 58081, 58564, 59049, 59536, 60025, 60516, 61009, 61504, 62001,
>> 62500, 63001, 63504, 64009, 64516, 65025,
>> +};
>>
>> static int sse4_c(MpegEncContext *v, uint8_t *pix1, uint8_t *pix2,
>> ptrdiff_t stride, int h)
>> {
>> int s = 0, i;
>> - uint32_t *sq = ff_square_tab + 256;
>> + const uint32_t *sq = ff_square_tab + 256;
>>
>> for (i = 0; i < h; i++) {
>> s += sq[pix1[0] - pix2[0]];
>> @@ -52,7 +87,7 @@ static int sse8_c(MpegEncContext *v, uint8_t *pix1,
>> uint8_t *pix2,
>> ptrdiff_t stride, int h)
>> {
>> int s = 0, i;
>> - uint32_t *sq = ff_square_tab + 256;
>> + const uint32_t *sq = ff_square_tab + 256;
>>
>> for (i = 0; i < h; i++) {
>> s += sq[pix1[0] - pix2[0]];
>> @@ -73,7 +108,7 @@ static int sse16_c(MpegEncContext *v, uint8_t *pix1,
>> uint8_t *pix2,
>> ptrdiff_t stride, int h)
>> {
>> int s = 0, i;
>> - uint32_t *sq = ff_square_tab + 256;
>> + const uint32_t *sq = ff_square_tab + 256;
>>
>> for (i = 0; i < h; i++) {
>> s += sq[pix1[0] - pix2[0]];
>> @@ -977,14 +1012,6 @@ WRAPPER8_16_SQ(quant_psnr8x8_c, quant_psnr16_c)
>> WRAPPER8_16_SQ(rd8x8_c, rd16_c)
>> WRAPPER8_16_SQ(bit8x8_c, bit16_c)
>>
>> -av_cold void ff_me_cmp_init_static(void)
>> -{
>> - int i;
>> -
>> - for (i = 0; i < 512; i++)
>> - ff_square_tab[i] = (i - 256) * (i - 256);
>> -}
>> -
>> int ff_check_alignment(void)
>> {
>> static int did_fail = 0;
>> diff --git a/libavcodec/me_cmp.h b/libavcodec/me_cmp.h
>> index 0dbbcbb1d9..0a589e3c3d 100644
>> --- a/libavcodec/me_cmp.h
>> +++ b/libavcodec/me_cmp.h
>> @@ -23,7 +23,7 @@
>>
>> #include "avcodec.h"
>>
>> -extern uint32_t ff_square_tab[512];
>> +extern const uint32_t ff_square_tab[512];
>>
>>
>> /* minimum alignment rules ;)
>> @@ -79,8 +79,6 @@ typedef struct MECmpContext {
>> me_cmp_func median_sad[6];
>> } MECmpContext;
>>
>> -void ff_me_cmp_init_static(void);
>> -
>> int ff_check_alignment(void);
>>
>> void ff_me_cmp_init(MECmpContext *c, AVCodecContext *avctx);
>> diff --git a/libavcodec/mpegvideo_enc.c b/libavcodec/mpegvideo_enc.c
>> index f1f4989231..979e138b88 100644
>> --- a/libavcodec/mpegvideo_enc.c
>> +++ b/libavcodec/mpegvideo_enc.c
>> @@ -2713,7 +2713,7 @@ static inline void encode_mb_hq(MpegEncContext *s,
>> MpegEncContext *backup, MpegE
>> }
>>
>> static int sse(MpegEncContext *s, uint8_t *src1, uint8_t *src2, int w, int
>> h, int stride){
>> - uint32_t *sq = ff_square_tab + 256;
>> + const uint32_t *sq = ff_square_tab + 256;
>> int acc=0;
>> int x,y;
>>
>> diff --git a/libavcodec/mpegvideoencdsp.c b/libavcodec/mpegvideoencdsp.c
>> index 0af3d8bef8..a34ab3553e 100644
>> --- a/libavcodec/mpegvideoencdsp.c
>> +++ b/libavcodec/mpegvideoencdsp.c
>> @@ -81,7 +81,7 @@ static int pix_sum_c(uint8_t *pix, int line_size)
>> static int pix_norm1_c(uint8_t *pix, int line_size)
>> {
>> int s = 0, i, j;
>> - uint32_t *sq = ff_square_tab + 256;
>> + const uint32_t *sq = ff_square_tab + 256;
>>
>> for (i = 0; i < 16; i++) {
>> for (j = 0; j < 16; j += 8) {
>> diff --git a/libavcodec/snowenc.c b/libavcodec/snowenc.c
>> index 4fec377591..61a658fa44 100644
>> --- a/libavcodec/snowenc.c
>> +++ b/libavcodec/snowenc.c
>> @@ -179,7 +179,7 @@ static int pix_sum(uint8_t * pix, int line_size, int w,
>> int h)
>> static int pix_norm1(uint8_t * pix, int line_size, int w)
>> {
>> int s, i, j;
>> - uint32_t *sq = ff_square_tab + 256;
>> + const uint32_t *sq = ff_square_tab + 256;
>>
>> s = 0;
>> for (i = 0; i < w; i++) {
>> diff --git a/libavcodec/utils.c b/libavcodec/utils.c
>> index 4c718432ad..aefe631590 100644
>> --- a/libavcodec/utils.c
>> +++ b/libavcodec/utils.c
>> @@ -104,18 +104,6 @@ AVCodec *av_codec_next(const AVCodec *c)
>> return first_avcodec;
>> }
>>
>> -static av_cold void avcodec_init(void)
>> -{
>> - static int initialized = 0;
>> -
>> - if (initialized != 0)
>> - return;
>> - initialized = 1;
>> -
>> - if (CONFIG_ME_CMP)
>> - ff_me_cmp_init_static();
>> -}
>> -
>> int av_codec_is_encoder(const AVCodec *codec)
>> {
>> return codec && (codec->encode_sub || codec->encode2
>> ||codec->send_frame);
>> @@ -131,7 +119,6 @@ static AVMutex codec_register_mutex =
>> AV_MUTEX_INITIALIZER;
>> av_cold void avcodec_register(AVCodec *codec)
>> {
>> AVCodec **p;
>> - avcodec_init();
>>
>> ff_mutex_lock(&codec_register_mutex);
>> p = last_avcodec;
>
> LGTM, should considerably simplify implementing whatever new decoder
> registration/listing we introduce.
Applied.
Thank's.
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
http://ffmpeg.org/mailman/listinfo/ffmpeg-devel
