- 26 Nov, 2017 1 commit
-
-
Mark Thompson authored
Reviewed-by:Timo Rothenpieler <timo@rothenpieler.org>
-
- 17 Nov, 2017 1 commit
-
-
Timo Rothenpieler authored
-
- 15 Nov, 2017 1 commit
-
-
Hendrik Leppkes authored
-
- 07 Sep, 2017 1 commit
-
-
Timo Rothenpieler authored
Signed-off-by:
-
- 01 Sep, 2017 1 commit
-
-
Timo Rothenpieler authored
Signed-off-by:
-
- 24 Jun, 2017 1 commit
-
-
Ben Chang authored
Previously, if a session allocates x surfaces, only x-1 surfaces are used (due to combination of output delay and lock toggle logic).
-
- 10 May, 2017 2 commits
-
-
Sumit Agarwal authored
Signed-off-by: -
Ben Chang authored
Signed-off-by:
-
- 09 May, 2017 1 commit
-
-
Timo Rothenpieler authored
-
- 26 Apr, 2017 1 commit
-
-
Ben Chang authored
This patch aims to reduce the number of input/output surfaces NVENC allocates per session. Previous default sets allocated surfaces to 32 (unless there is user specified param or lookahead involved). Having large number of surfaces consumes extra video memory (esp for higher resolution encoding). The patch changes the surfaces calculation for default, B-frames, lookahead scenario respectively. The other change involves surface selection. Previously, if a session allocates x surfaces, only x-1 surfaces are used (due to combination of output delay and lock toggle logic). To prevent unused surfaces, changing surface rotation to using predefined fifo. Signed-off-by:
-
- 23 Mar, 2017 1 commit
-
-
Timo Rothenpieler authored
-
- 09 Mar, 2017 1 commit
-
-
Konda Raju authored
Signed-off-by:Diego Biurrun <diego@biurrun.de>
-
- 01 Mar, 2017 1 commit
-
-
Konda Raju authored
Signed-off-by:
-
- 17 Jan, 2017 1 commit
-
-
Luca Barbato authored
Make sure that NVENC does not misbehave if other cuda usages happen in the application.
-
- 01 Jan, 2017 2 commits
-
-
Miroslav Slugen authored
Signed-off-by: -
Miroslav Slugen authored
Signed-off-by:
-
- 22 Nov, 2016 1 commit
-
-
Timo Rothenpieler authored
-
- 12 Oct, 2016 1 commit
-
-
Timo Rothenpieler authored
-
- 28 Sep, 2016 2 commits
-
-
Yogender Gupta authored
Merged from libav commit by Yogender Gupta: https://git.libav.org/?p=libav.git;a=commitdiff;h=70de2ea4261f860457a04e3d0c58c5543f403325
-
Timo Rothenpieler authored
-
- 24 Sep, 2016 3 commits
-
-
Yogender Gupta authored
Signed-off-by:
Luca Barbato <lu_zero@gentoo.org> Signed-off-by:
-
Yogender Gupta authored
Signed-off-by:
-
Yogender Gupta authored
Signed-off-by:
-
- 07 Sep, 2016 1 commit
-
-
Timo Rothenpieler authored
-
- 28 Aug, 2016 4 commits
-
-
Timo Rothenpieler authored
-
Oliver Collyer authored
Signed-off-by: -
Oliver Collyer authored
Signed-off-by: -
Timo Rothenpieler authored
As Nvidia has put the most recent Video Codec SDK behind a double registration wall, of which one needs manual approval of a lenghty application, bundling this header saves everyone trying to use NVENC from that headache. The header is still MIT licensed and thus fine to bundle with ffmpeg. Not bundling this header would get ffmpeg stuck at SDK v6, which is still freely available, holding back future development of the NVENC encoder.
-
- 31 May, 2016 9 commits
-
-
Timo Rothenpieler authored
Directly adapted from libav
-
Andrey Turkin authored
Use explicit nvenc capability checks instead to determine usable devices instead of SM versions. Signed-off-by: -
Andrey Turkin authored
Signed-off-by: -
Andrey Turkin authored
Signed-off-by: -
Andrey Turkin authored
Signed-off-by: -
Andrey Turkin authored
Signed-off-by: -
Andrey Turkin authored
Signed-off-by: -
Andrey Turkin authored
Signed-off-by: -
Andrey Turkin authored
Signed-off-by:
-
- 19 May, 2016 2 commits
-
-
Anton Khirnov authored
The code needs only a few definitions from cuda.h, so define them directly when CUDA is not enabled. CUDA is still required for accepting HW frames as input. Based on the code by Timo Rothenpieler <timo@rothenpieler.org>.
-
Timo Rothenpieler authored
Signed-off-by:Anton Khirnov <anton@khirnov.net>
-
- 04 May, 2016 1 commit
-
-
Vittorio Giovara authored
Signed-off-by:
-
