Commit graph

171 commits

Author SHA1 Message Date
Matthew Waters
8dac91537d cuda/nvcodec: Add support for importing and producing embedded NVMM memory
As produced on the Nvidia Jetson series of devices.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/7274>
2024-08-02 01:59:07 +00:00
Seungha Yang
afb62e98c7 cuda: Enable x86 NVMM support again
It was broken since memory copy helper function was moved to gst-libs.
Also, adding "cuda-nvmm" and "cuda-nvmm-include-path" build options
to en/disable NVMM support in gstcuda library

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6978>
2024-06-06 12:16:50 +00:00
Brad Reitmeyer
a564440020 nvcodec: Accept progressive-high profiles for h264
Videos using progressive-high used to work on 1.16 before the parser added progressive-high. It looks like partial
support was added to nvcodec in https://gitlab.freedesktop.org/gstreamer/gst-plugins-bad/-/merge_requests/1634
but accidentally ommited gstnvh264dec

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6862>
2024-05-16 16:05:52 -05:00
Seungha Yang
15c24abf5d nvcodec: Add AV1 encoder
Adding CUDA mode "nvav1enc", D3D11 mode "nvd3d11av1enc" and auto GPU
mode "nvautogpuav1enc" elements

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6754>
2024-05-15 14:35:52 +00:00
Seungha Yang
da019bf137 nvcodec: Rename nvcuda{h264,h265}enc to nv{h264,h265}enc
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6754>
2024-05-15 14:35:52 +00:00
Seungha Yang
b74422dcbc nvcodec: Remove old nvenc implementation
Stop shipping deprecated implementation

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6754>
2024-05-15 14:35:52 +00:00
Seungha Yang
0ffbe20d31 nvcodec: Bump minimum supported SDK version to 10.0
New preset (i.e., P1 ~ P7) requires SDK 10.0 or newer

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6754>
2024-05-15 14:35:52 +00:00
Seungha Yang
60637b96c8 nvcodec: Update SDK header to 12.0.16
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6754>
2024-05-15 14:35:52 +00:00
Seungha Yang
ff6d6e1b3c nvencoder: Enhance lagacy encoding profile mapping
Updated based on the NVENC Preset Migration Guide

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6754>
2024-05-15 14:35:52 +00:00
Seungha Yang
cfd92819d9 nvencoder: Update property names and default value
... to be the same as old NVENC elements

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6754>
2024-05-15 14:35:51 +00:00
Seungha Yang
99b1f5ddd2 nvencoder: Fix maximum QP value setting
Fixing typo

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6827>
2024-05-12 09:38:29 +00:00
Seungha Yang
84f4068036 nvh265encoder: Fix crash with RGBx and BGRx
Both formats need to be handled in switch

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6752>
2024-04-28 23:34:37 +09:00
Seungha Yang
106187cc59 nvencoder: Add support for RGB formats
Adding RGBA, RGBx, BGRA, BGRx, VUYA and RGB10A2_LE format support for performance.
However, these formats are not still recommended if upstream can support
native YUV formats (e.g., NV12, P010) since NVENC does not expose
conversion related optiones. Note that VUYA format is 4:4:4 YUV format
already but NVENC runtime will convert it to 4:2:0 format internally

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6417>
2024-04-02 13:07:29 +00:00
Seungha Yang
e6f496a240 cuda: Add support for VUYA format
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6417>
2024-04-02 13:07:29 +00:00
Michiel Westerbeek
a4aa9e197e gstcudaconvertscale, gstvavpp, videoconvertscale: downgrade 'Can't keep DAR' to debug
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5730>
2024-03-13 16:06:56 +00:00
Seungha Yang
5d62f408f2 nvcodec: Add plugin status message
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6167>
2024-02-22 23:30:29 +00:00
Seungha Yang
cfa8386dd0 nvdecoder: Enable zero-copy only if explicitly enabled
Keep pre-1.24 behavior unless user specifies the number of
output surface size. We are calculating output surface size
conservatively, and it can result in over allocation.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6102>
2024-02-13 12:37:07 +00:00
Seungha Yang
59358e439d nvh265dec: Don't convert unknown video format to string
gst_video_format_to_string() method does not allow unknown format

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6102>
2024-02-13 12:37:06 +00:00
Seungha Yang
d444fe3fdc nvcodec: Update plugin cache
Updating plugin cache for IPC elements, JPEG encoder, and newly added
properties. Also removing Gst*SLDec which does not exist anymore
but renamed to Gst*Dec.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6070>
2024-02-07 22:06:39 +00:00
Seungha Yang
6dc902a962 nvcodec: Add JPEG encoder
Adding nvJPEG library based JPEG encoder element

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6021>
2024-01-31 12:51:28 +00:00
Seungha Yang
fc4b136ac8 nvcodec: Move runtime compiler check to plugin init function
Required information for other elements

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6021>
2024-01-31 12:51:28 +00:00
Seungha Yang
51162acc31 cuda: Report device open error
Call gst_cuda_result() with CUDA_ERROR_NO_DEVICE error code if
we could not open device, so that application can catch the error

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6006>
2024-01-30 14:30:41 +00:00
Seungha Yang
07ba225183 cudaipc: Add support for custom meta forwarding
Forward custom meta to peer ipcsrc elements

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/6006>
2024-01-30 14:30:41 +00:00
Seungha Yang
abe1f5044d cuda: Prefer CUBIN over PTX
System installed NVRTC library might be newer version than
driver, then generate PTX can be incompatible with the driver.
Instead of the intermediate code PTX, use actual assembly code
directly.

Fixes: https://gitlab.freedesktop.org/gstreamer/gstreamer/-/issues/3108
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5639>
2024-01-02 10:10:09 +00:00
Seungha Yang
012222bcb3 cudaipcsink: Fix deadlock on stop
Manually close connection if client does not hold any shared memory
on stop.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5747>
2023-12-06 16:09:27 +00:00
Seungha Yang
b168647073 nvdec: Fix division by zero when calculating buffer duration
Don't try to calculate buffer duration from variable framerate

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5764>
2023-12-06 13:38:09 +00:00
Seungha Yang
0a05ba3f62 nvencoder: Add support for new preset/tune/multi-pass options
Adding new P1 ~ P7 presets and deprecate old preset values.
Also adding tune and multi-pass properties.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5428>
2023-10-14 11:03:40 +00:00
James Oliver
aeef97d81b nvh265encoder: fix bounds for auto-select GPU enumeration
Fixes the bounds-check for encoder auto-select GPU enumeration to be
between 0-7 instead of 0-6. This should allow 8-GPU machines to work
with nvautogpuh265enc for the last enumerated GPU.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5438>
2023-10-05 13:37:36 +08:00
James Oliver
54074af8ec nvh264encoder: fix bounds for auto-select GPU enumeration
Fixes the bounds-check for encoder auto-select GPU enumeration to be
between 0-7 instead of 0-6. This should allow 8-GPU machines to work
with nvautogpuh264enc for the last enumerated GPU.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5438>
2023-10-05 13:37:32 +08:00
Seungha Yang
2cd81eb1ac nvdecoder: Handle output surface alignment in decoder helper object
Output resolution might not be an even number. Set output resolution
without round up but consider the alignment inside of decoder

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5409>
2023-09-29 12:36:01 +00:00
Seungha Yang
42560c24df nvdecoder: Add support for D3D11 output
Since DXVA does not support some profiles such as HEVC RExt,
vendor specific decoding API is still required.
When decoder is negotiated with d3d11 caps, decoder will convert
semi-planar frame to planar since semi-planar format (e.g.,
DXGI_FORMAT_NV12) is not supported by CUDA/D3D11 interop.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5409>
2023-09-29 12:36:01 +00:00
Seungha Yang
57e0a0bd61 nvdecoder: Handle GstContext in helper object
... and move common code to helper object

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5409>
2023-09-29 12:36:01 +00:00
Seungha Yang
c818906236 cuda: Add support for I420_12LE format
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5409>
2023-09-29 12:36:01 +00:00
Seungha Yang
c5bd0faee3 nvdecoder: Add support for HEVC GBR output
... and use P012 format for 12bits instead of P016

Fixes: https://gitlab.freedesktop.org/gstreamer/gstreamer/-/issues/2991
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5375>
2023-09-23 13:12:56 +00:00
Seungha Yang
907c507680 nvh265encoder: Add support for RGB encoding
Adding GBR format support to nv{autogpu,cuda,d3d11}h265enc.
Note that the only difference between GBR and Y444 encoding
is matrix_coeffs value written in VUI.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5375>
2023-09-23 13:12:56 +00:00
Seungha Yang
a80f542f66 cuda: Add support for P012_LE and Y444/GBR high bitdepth formats
Adding P012, Y444_10, Y444_12, GBR_10, GBR_12 and GBR_16 formats support

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5375>
2023-09-23 13:12:55 +00:00
Seungha Yang
bd25c2738e nvdecoder: Copy output frame if needed
Even if decoder is negotiated with CUDA memory feature, if downstream
proposed no buffer pool, assume that the pool size is unknown.
And disable zero-copy if there's no more free output surface.
Or, in case of reverse playback, always copy frames.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5338>
2023-09-17 00:15:47 +09:00
Seungha Yang
c5a5dcdf18 nvh265dec: Reconfigure decoder on max-dpb-size change
Decoder should create new picture pool for larger DPB size

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5338>
2023-09-16 23:00:11 +09:00
Seungha Yang
f9169c5431 nvdecoder: Move common logic to decoder helper object
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5285>
2023-09-08 11:51:23 +00:00
Seungha Yang
97fc02cfe3 av1decoder: Port to GstCodecPicture struct
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5285>
2023-09-08 11:51:23 +00:00
Seungha Yang
a73c6d7fb6 vp9decoder: Port to GstCodecPicture struct
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5285>
2023-09-08 11:51:23 +00:00
Seungha Yang
4571fac946 vp8decoder: Port to GstCodecPicture struct
... and remove unused "pts" variable from GstVp8Picture struct

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5285>
2023-09-08 11:51:23 +00:00
Seungha Yang
6e7cab43be h265decoder: Port to GstCodecPicture struct
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5285>
2023-09-08 11:51:23 +00:00
Seungha Yang
ea3dfadbed h264decoder: Port to GstCodecPicture struct
Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5285>
2023-09-08 11:51:23 +00:00
Seungha Yang
6fa405c1e2 cudaipcclient: Protect IPC handle import/close with global lock
Protect import/close with signle lock to avoid importing a IPC handle
while it's being closed by another cudaipcsrc from other thread.
Also fixing cuda context leak

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5230>
2023-08-25 10:06:58 +00:00
Seungha Yang
315cfaf2d8 nvencoder: Fix negotiation error when interlace-mode is unspecified
Use GST_PAD_SET_ACCEPT_INTERSECT() to accept caps without interlace-mode
field

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5229>
2023-08-24 14:58:25 +00:00
L. E. Segovia
b1a5707fcb windows: Fix mutexes leaking into the exports table
Translation unit-local variables must be marked static on Windows,
otherwise they're made available to the whole binary.

See:

https://learn.microsoft.com/en-us/cpp/cpp/program-and-linkage-cpp?view=msvc-170#external-vs-internal-linkage

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/5185>
2023-08-16 08:17:05 +00:00
Seungha Yang
7b6023d9cf nvcodec: Add support for CUDA IPC
Adding cudaipc{src,sink} element for CUDA IPC support.

Implementation note:
* For the communication between end points, Win32 named-pipe
and unix domain socket will be used on Windows and Linux respectively.

* cudaipcsink behaves as a server, and all GPU resources will be owned by
the server process and exported for other processes, then cudaipcsrc
(client) will import each exported handle.

* User can select IPC mode via "ipc-mode" property of cudaipcsink.
There are two IPC mode, one is "legacy" which uses legacy CUDA IPC
method and the other is "mmap" which uses CUDA virtual memory API
with OS's resource handle sharing method such as DuplicateHandle()
on Windows. The "mmap" mode might be better than "legacy" in terms
of stability since it relies on OS's resource management but
it would consume more GPU memory than "legacy" mode.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/4510>
2023-08-14 13:41:01 +00:00
Seungha Yang
cf2cd20ba0 nvdecoder: Add max-display-delay property
The same as in old nvdec implementation so that user can control
the number of delayed output frames.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/4841>
2023-08-10 11:58:42 +00:00
Seungha Yang
19ee5f6dc4 nvdecoder: Reduce DPB size
Decoder will copy decoded picture to downstream buffer or output CUDA
memory even in case of zero-copy mode. Additional margin should be unnecessary
unless baseclass passed wrong max DPB size.

Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/4841>
2023-08-10 11:58:42 +00:00