Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

intel quick sync for jpeg encode acceleration #1666

Closed
totaam opened this issue Oct 18, 2017 · 8 comments
Closed

intel quick sync for jpeg encode acceleration #1666

totaam opened this issue Oct 18, 2017 · 8 comments

Comments

@totaam
Copy link
Collaborator

totaam commented Oct 18, 2017

Issue migrated from trac ticket # 1666

component: encodings | priority: major | resolution: wontfix

2017-10-18 12:24:53: antoine created the issue


Intel Quick Sync Video supports JPEG encode acceleration on Braswell and later. (2016)

JPEG is critical to the performance, especially for the HTML5 client. Let's see if this beats libjpeg-turbo.

Chrome uses it: Chrome Working On JPEG Encode Accelerator With VA-API/V4L2 Support, so that's likely to be a win.

@totaam
Copy link
Collaborator Author

totaam commented Mar 12, 2018

2018-03-12 14:57:57: antoine commented


Re-scheduling as per #451#comment:10.

@totaam
Copy link
Collaborator Author

totaam commented Sep 21, 2019

2019-09-21 13:19:06: antoine commented


[https://trac.ffmpeg.org/wiki/Hardware/QuickSync]

Not many examples around:

@totaam
Copy link
Collaborator Author

totaam commented Jun 13, 2020

2020-06-13 17:28:11: antoine uploaded file qsv.patch (7.5 KiB)

qsv via ffmpeg - no workee :(

@totaam
Copy link
Collaborator Author

totaam commented Jun 13, 2020

2020-06-13 17:57:50: antoine changed status from new to assigned

@totaam
Copy link
Collaborator Author

totaam commented Jun 13, 2020

2020-06-13 17:57:50: antoine commented


Even trying the ffmpeg qsv command line examples fails.

Probably requires that I unplug or turn off the nvidia card and switch back to the intel iGPU. (Intel® HD Graphics 530 found in the i6700k)

libva (#451) might be a better option: it is more generic, supports amd and nvidia too, and this does look like it might work without touching the hardware:

$ vainfo
libva info: VA-API version 1.7.0
libva info: Trying to open /usr/lib64/dri/nvidia_drv_video.so
libva info: Found init function __vaDriverInit_1_5
libva info: va_openDriver() returns 0
vainfo: VA-API version: 1.7 (libva 2.7.1)
vainfo: Driver version: Splitted-Desktop Systems VDPAU backend for VA-API - 0.7.4
vainfo: Supported profile and entrypoints
      VAProfileMPEG2Simple            :	VAEntrypointVLD
      VAProfileMPEG2Main              :	VAEntrypointVLD
      VAProfileMPEG4Simple            :	VAEntrypointVLD
      VAProfileMPEG4AdvancedSimple    :	VAEntrypointVLD
      <unknown profile>               :	VAEntrypointVLD
      VAProfileH264Main               :	VAEntrypointVLD
      VAProfileH264High               :	VAEntrypointVLD
      VAProfileVC1Simple              :	VAEntrypointVLD
      VAProfileVC1Main                :	VAEntrypointVLD
      VAProfileVC1Advanced            :	VAEntrypointVLD

@totaam
Copy link
Collaborator Author

totaam commented Jun 14, 2020

2020-06-14 16:27:25: antoine changed status from assigned to closed

@totaam
Copy link
Collaborator Author

totaam commented Jun 14, 2020

2020-06-14 16:27:25: antoine set resolution to wontfix

@totaam
Copy link
Collaborator Author

totaam commented Jun 14, 2020

2020-06-14 16:27:25: antoine commented


It is nonfree and doesn't work, whereas vaapi does: #451.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant