WebML WG Teleconference – 16 February 2023 - 15:00-16:00 UTC

WebML WG Teleconference – 16 February 2023 - 15:00-16:00 UTC
San Francisco (U.S.A. - California)     Thu, 16 February 2023   07:00   UTC-8 hours
Boston (U.S.A. - Massachusetts) Thu, 16 February 2023   10:00   UTC-5 hours
London (United Kingdom - England)       Thu, 16 February 2023   15:00   UTC+0 hours (adjusted for DST)
Berlin (Germany)        Thu, 16 February 2023   16:00   UTC+1 hours (adjusted for DST)
Helsinki (Finland)      Thu, 16 February 2023   17:00   UTC+2 hours (adjusted for DST)
Shanghai (China)        Thu, 16 February 2023   23:00   UTC+8 hours (adjusted for DST)
Tokyo (Japan)   Fri, 17 February 2023   00:00   UTC+9 hours (adjusted for DST)
Corresponding UTC (GMT) Thu, 16 February 2023   15:00 UTC

Other locations: https://www.timeanddate.com/worldclock/fixedtime.html?iso=20230216T15


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-02-16-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

  *   Joining instructions: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2020Apr/0000.html

  *   Minutes: https://www.w3.org/2023/02/16-webmachinelearning-minutes.html


<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-02-16-wg-agenda.md#agenda>Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2023-02-16-wg-agenda.md#%E2%84%B9%EF%B8%8F-webnn-api-open-prs-and-issues>ℹ️ WebNN API open PRs and issues
Review open PRs and discuss issues. Identify and fast track any priority changes that should get into the initial CR release train.

  *   Simplify MLContext creation: remove MLDeviceType, remove "high-performance" from MLPowerPreference

     *    PR: webmachinelearning/webnn#322<https://github.com/webmachinelearning/webnn/pull/322>
     *    PR: webmachinelearning/webnn#340<https://github.com/webmachinelearning/webnn/pull/340>
  *   Rework the sync and async algorithms

     *    issue: webmachinelearning/webnn#316<https://github.com/webmachinelearning/webnn/issues/316>
     *    PR: webmachinelearning/webnn#329<https://github.com/webmachinelearning/webnn/pull/329>
     *   Related PR: webmachinelearning/webnn#323<https://github.com/webmachinelearning/webnn/pull/323>
  *   Add internal slots to MLOperand and MLActivation

     *    issue: webmachinelearning/webnn#336<https://github.com/webmachinelearning/webnn/issues/336>
     *    PR: webmachinelearning/webnn#337<https://github.com/webmachinelearning/webnn/pull/337>
  *   Improve batchNorm

     *    issue: webmachinelearning/webnn#334<https://github.com/webmachinelearning/webnn/issues/334>
     *    PR: webmachinelearning/webnn#339<https://github.com/webmachinelearning/webnn/pull/339> (depends on PR #337)
     *   Note: We establish a blueprint here for formal op steps to be applied to all ops.
  *   Simplify the operand layout support of conv2d and pooling 2d operations

     *    issue: webmachinelearning/webnn#324<https://github.com/webmachinelearning/webnn/issues/324>
  *   Define the algorithm of calculating the effective padding for "same-upper" and "same-lower" option

     *    issue: webmachinelearning/webnn#326<https://github.com/webmachinelearning/webnn/issues/326>
  *   Clarify the usage of 32 bit floating point type and consider using double

     *    webmachinelearning/webnn#325<https://github.com/webmachinelearning/webnn/issues/325>