- From: Corentin Wallez <cwallez@google.com>
- Date: Tue, 5 Dec 2017 18:32:05 -0500
- To: public-gpu <public-gpu@w3.org>
- Message-ID: <CAGdfWNNZLE34e-AJQDiViRGbymP9CAUhiFZbLQ7i+bALBSSCDw@mail.gmail.com>
Hey all, We updated the NXT buffer mapping <https://docs.google.com/document/d/1HFzMMvDGHFtTgjNT0j-0SQ1fNU9R7woZ4JuNJdAXBjg> doc with a discussion of alternatives for UMA. Please take a look for tomorrow's discussion! Corentin On Tue, Nov 14, 2017 at 11:51 PM, Corentin Wallez <cwallez@google.com> wrote: > Hey all, > > We wrote some document to help everyone reason about NXT's proposals for > memory barriers and resource upload /download. Unfortunately we still don't > have a fleshed out proposal that minimizes the number of copies on UMA. > Instead the docs focus on explaining our current design for resource > upload/download and for memory barriers since they are very tied. > Eventually we'll have these docs in MarkDown in some repo, either WebGPU's > or NXT's. > > - NXT "memory barriers" > <https://docs.google.com/document/d/1k7lPmxP7M7MMQR4g210lNC5TPwmXCMLgKOQWNiuJxzA> > <- Please read this first as buffer mapping depends on it. > - NXT buffer mapping > <https://docs.google.com/document/d/1HFzMMvDGHFtTgjNT0j-0SQ1fNU9R7woZ4JuNJdAXBjg> > > Cheers, > > Corentin >
Received on Tuesday, 5 December 2017 23:32:52 UTC