Re: WebML WG Teleconference – 24 March 2022 - 15:00-16:00 UTC+0

Reminder to the US and Canadian participant:

24 March 2022 call will exceptionally take place an hour later than usual at 8am Pacific / 11am Eastern. You have an extra hour to brew your morning coffee :-)

For the rest of the world, the usual schedule.

Please consult the timezone table below for details.

The agenda has been adjusted slightly:

I added Integration with real-time video processing topic to the agenda to introduce and discuss the background blur sample prototype that uses mediacapture-transform, WebGL and WebGPU/WebNN processing pipelines, as well as the WebNN Chromium prototype that implements WebNN/WebGPU interop API. As usual, the latest agenda is at:

https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-24-wg-agenda.md


Looking forward to our discussion.

Thanks,

-Anssi

On 17. Mar 2022, at 10.46, Kostiainen, Anssi <anssi.kostiainen@intel.com<mailto:anssi.kostiainen@intel.com>> wrote:

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-24-wg-agenda.md


WebML WG Teleconference – 24 March 2022 - 15:00-16:00 UTC+0

‼️ This meeting happens 1 hour later than usual in the US and Canada due to Daylight Saving Time<https://www.timeanddate.com/time/dst/2022a.html> adjustment. Most of the US and Canada moved their clocks forward on Sunday, 13 March. This is two weeks earlier than Europe. Most European clocks will move 1 hour forward on Sunday, 27 March.

See the timezone table ...
San Francisco (U.S.A. - California)     Thu, 24 March 2022      08:00   UTC-7 hours ‼️
Boston (U.S.A. - Massachusetts) Thu, 24 March 2022      11:00   UTC-4 hours ‼️
London (United Kingdom - England)       Thu, 24 March 2022      15:00   UTC+0 hours
Berlin (Germany)        Thu, 24 March 2022      16:00   UTC+1 hours
Helsinki (Finland)      Thu, 24 March 2022      17:00   UTC+2 hours
Shanghai (China)        Thu, 24 March 2022      23:00   UTC+8 hours
Tokyo (Japan)   Fri, 25 March 2021      00:00   UTC+9 hours
Corresponding UTC (GMT) Thu, 24 March 2022      15:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20220324T15


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-24-wg-agenda.md#logistics>Logistics

  *   Chair: Anssi
  *   Scribe: ? (see howto<https://github.com/webmachinelearning/meetings/blob/main/scribe-howto.md>, volunteers welcome!)
  *   IRC: irc://irc.w3.org:6667/#webmachinelearning

  *   IRC web client: https://irc.w3.org/?channels=#webmachinelearning

  *   Call-in details: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2020Apr/0000.html

  *   Minutes: https://www.w3.org/2022/03/24-webmachinelearning-minutes.html


________________________________
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-24-wg-agenda.md#%E2%84%B9%EF%B8%8F-security-considerations---last-call-for-review>ℹ️ Security considerations - last call for review
Review the PR that is the group's response to security questions from Chrome Security team.

  *    issue: General Security Questions: webmachinelearning/webnn#241<https://github.com/webmachinelearning/webnn/issues/241>
  *    PR: Update Security Considerations per review feedback: webmachinelearning/webnn#251<https://github.com/webmachinelearning/webnn/pull/251>
  *    All security-tracker issues: https://github.com/webmachinelearning/webnn/issues?q=label%3Asecurity-tracker+


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-24-wg-agenda.md#%E2%84%B9%EF%B8%8F-context-based-graph-execution-methods-for-different-threading-models>ℹ️ Context-based graph execution methods for different threading models
Review the new proposal for context-based graph execution methods that is an improved design and considers feedback received from the group for the earlier proposal.

  *    issue: Should WebNN support async APIs? webmachinelearning/webnn#230<https://github.com/webmachinelearning/webnn/issues/230>
  *    PR: Context-based graph execution methods for different threading models webmachinelearning/webnn#257<https://github.com/webmachinelearning/webnn/pull/257>

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-24-wg-agenda.md#%E2%84%B9%EF%B8%8F-candidate-recommendation-proposed-new-features>ℹ️ Candidate Recommendation proposed new features
CR expectation is that the spec is considered technically complete and fit for purpose. Review the new proposed CR issues targeting this milestone. Discuss any blockers or new information that might suggest we need to adjust our scope and/or timeline.

Proposed new CR issues:

  *    WebNN should support int8 quantized models webmachinelearning/webnn#128<https://github.com/webmachinelearning/webnn/issues/128>
  *    WebNN / WebGPU interop gpuweb/gpuweb#2500<https://github.com/gpuweb/gpuweb/issues/2500>
     *   Related: Integration with real-time video processing webmachinelearning/webnn#226<https://github.com/webmachinelearning/webnn/issues/226>

(All "cr" issues https://github.com/webmachinelearning/webnn/labels/cr)

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-24-wg-agenda.md#%E2%84%B9%EF%B8%8F-proposed-new-use-cases>ℹ️ Proposed new use cases
Review the proposed new use cases.

  *    Performance Adaptation webmachinelearning/webnn#207<https://github.com/webmachinelearning/webnn/pull/207>
  *    Ethical Content Filtering webmachinelearning/webnn#253<https://github.com/webmachinelearning/webnn/pull/253>

<https://github.com/webmachinelearning/meetings/blob/main/telcons/2022-03-24-wg-agenda.md#%E2%84%B9%EF%B8%8F-open-issues-and-pull-requests>ℹ️ Open issues and pull requests
Discuss/resolve open issues and review open PRs pending review, time permitting.

  *   Open issues: https://github.com/webmachinelearning/webnn/issues

  *   Open PRs: https://github.com/webmachinelearning/webnn/pulls