ffmpeg/libavutil
Ganesh Ajjanagadde 5989add4ab lavu/x86/lls: add fma3 optimizations for update_lls
This improves accuracy (very slightly) and speed for processors having
fma3.

Sample benchmark (fate flac-16-lpc-cholesky, Haswell):
old:
5993610 decicycles in ff_lpc_calc_coefs,      64 runs,      0 skips
5951528 decicycles in ff_lpc_calc_coefs,     128 runs,      0 skips

new:
5252410 decicycles in ff_lpc_calc_coefs,      64 runs,      0 skips
5232869 decicycles in ff_lpc_calc_coefs,     128 runs,      0 skips

Tested with FATE and --disable-fma3, also examined contents of
lavu/lls-test.

Reviewed-by: James Almer <jamrial@gmail.com>
Reviewed-by: Henrik Gramner <henrik@gramner.com>
Signed-off-by: Ganesh Ajjanagadde <gajjanagadde@gmail.com>
2016-01-15 16:46:13 -05:00
..
2014-04-07 01:31:02 +02:00
2015-12-15 14:16:28 +01:00
2015-12-15 14:16:28 +01:00
2015-10-28 09:38:21 -05:00
2015-08-19 16:15:13 +00:00
2015-08-22 10:07:05 -07:00
2014-08-05 01:54:47 +02:00
2014-07-12 22:33:27 +02:00
2014-07-12 22:33:27 +02:00
2015-11-01 19:35:01 -05:00
2014-04-29 13:24:11 +02:00
2015-09-05 18:07:20 +02:00
2015-09-05 18:07:20 +02:00
2015-10-11 18:03:10 -04:00
2016-01-13 20:00:19 -05:00
2014-10-11 12:15:26 +02:00
2015-12-15 14:16:28 +01:00
2015-11-18 22:05:16 +01:00
2015-11-18 22:05:16 +01:00
2015-12-07 20:28:30 +01:00
2015-10-17 01:16:50 -07:00
2015-11-07 16:04:09 +01:00
2014-08-05 21:05:52 +02:00
2015-05-26 18:31:53 +02:00
2015-12-03 04:09:48 +01:00
2013-11-22 17:16:11 +01:00
2016-01-11 20:53:11 -08:00