summaryrefslogtreecommitdiffstats
path: root/libavcodec/nvenc.h
Commit message (Collapse)AuthorAgeFilesLines
* nvenc: Use a fifo to manage the free surface poolBen Chang2017-06-241-2/+1
| | | | | Previously, if a session allocates x surfaces, only x-1 surfaces are used (due to combination of output delay and lock toggle logic).
* add initial QP value optionsKonda Raju2017-03-091-0/+3
| | | | Signed-off-by: Diego Biurrun <diego@biurrun.de>
* nvenc: Explicitly push the cuda context on encodingLuca Barbato2017-01-171-0/+2
| | | | | Make sure that NVENC does not misbehave if other cuda usages happen in the application.
* nvenc: Extended rate-control support as provided by SDK 7Yogender Gupta2016-09-241-0/+10
| | | | | Signed-off-by: Luca Barbato <lu_zero@gentoo.org> Signed-off-by: Diego Biurrun <diego@biurrun.de>
* nvenc: Add support for high bitdepthYogender Gupta2016-09-241-0/+6
| | | | | Signed-off-by: Luca Barbato <lu_zero@gentoo.org> Signed-off-by: Diego Biurrun <diego@biurrun.de>
* nvenc: Add some easier to understand presets that match x264 terminologyYogender Gupta2016-09-241-1/+6
| | | | | | Signed-off-by: Luca Barbato <lu_zero@gentoo.org> Signed-off-by: Diego Biurrun <diego@biurrun.de> Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
* nvenc: drop the hard dependency on CUDAAnton Khirnov2016-05-191-1/+18
| | | | | | | | 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>.
* nvenc: Delay frame output to increase encoding speedTimo Rothenpieler2016-05-191-0/+1
| | | | Signed-off-by: Anton Khirnov <anton@khirnov.net>
* cosmetics: Fix spelling mistakesVittorio Giovara2016-05-041-1/+1
| | | | Signed-off-by: Diego Biurrun <diego@biurrun.de>
* nvenc: support CUDA frames as inputAnton Khirnov2016-02-141-0/+18
|
* Allow linking to CUDA dynamically instead of dlopen()ing it at runtimeAnton Khirnov2016-02-141-0/+4
|
* nvenc: merge input and output surface structsAnton Khirnov2016-02-121-11/+5
| | | | | An input frame always corresponds to exactly one output packet, so there is no point in complicating the situation by managing them separately.
* nvenc: factor out the pixel format listAnton Khirnov2016-02-121-0/+2
|
* nvenc: generate dts properlyAnton Khirnov2016-01-121-1/+4
| | | | | | | | | | When there is a non-zero decoding delay due to reordering, the first dts should be lower than the first pts (since the first packet fed to the decoder does not produce any output). Use the same scheme used in mpegvideo_enc (which comes from x264 originally) -- wait for first two timestamps and extrapolate linearly to the past to produce the first dts value.
* nvenc: H264 and HEVC encodersLuca Barbato2015-05-311-0/+135
Partially based on the work of Timo Rothenpieler <timo@rothenpieler.org> Signed-off-by: Luca Barbato <lu_zero@gentoo.org>
OpenPOWER on IntegriCloud