Cameron Gutman
a7171d77db
Reduce CPU usage with Linux NVENC
...
The internal assembly routines inside libswscale perform the
RGB->YUV conversion using a fully planar output format, then
have to perform an additional YUV420->NV12 conversion step.
NVENC can directly consume YUV420 input frames, so we can
completely avoid this NV12 conversion and save quite a bit of
CPU time in the process.
2021-07-10 11:24:13 -05:00
..
2021-07-09 08:13:05 -05:00
2021-06-22 22:26:11 +02:00
2021-06-22 22:26:11 +02:00
2021-06-20 15:29:51 +02:00
2021-06-20 15:29:51 +02:00
2021-07-09 23:45:59 -05:00
2021-06-30 15:25:08 +02:00
2021-06-30 15:25:08 +02:00
2021-06-30 15:25:08 +02:00
2021-07-09 12:27:38 +02:00
2021-07-09 12:27:38 +02:00
2021-06-30 15:25:08 +02:00
2021-06-30 15:25:08 +02:00
2021-06-24 20:53:19 +02:00
2021-06-24 20:53:19 +02:00
2021-07-04 16:06:03 +02:00
2021-06-30 15:25:08 +02:00
2021-05-17 21:21:57 +02:00
2021-06-28 21:05:52 +02:00
2021-05-17 21:21:57 +02:00
2021-07-09 08:47:44 -05:00
2021-06-30 15:25:08 +02:00
2021-05-29 22:06:28 +02:00
2021-05-17 21:21:57 +02:00
2021-05-17 21:21:57 +02:00
2021-07-04 21:25:10 +02:00
2021-06-30 15:25:08 +02:00
2021-07-10 17:30:51 +02:00
2021-07-03 23:38:45 -05:00
2021-05-17 21:21:57 +02:00
2021-05-17 21:21:57 +02:00
2021-05-17 21:21:57 +02:00
2021-06-22 22:26:11 +02:00
2021-07-04 18:57:55 +02:00
2021-06-29 22:42:06 +02:00
2021-07-05 20:58:53 +02:00
2021-05-17 21:21:57 +02:00
2021-07-10 11:24:13 -05:00
2021-07-06 20:54:29 +02:00