What makes you think web folks aren't interested in 100x wins?
-
-
Replying to @wycats @andreasgal and
Because I compare what we're doing in stuff like https://news.developer.nvidia.com/goai-gpu-open-analytics-initiative/ … vs. what I read in WebGL2?
1 reply 0 retweets 0 likes -
I was working on WebCL stuff... 5-7 years ago. There are multiple ways to do it, so I'm ok that it failed, but I wouldn't wager on WASM or anything else get there within another few years.
1 reply 0 retweets 0 likes -
I see very few web discussions on things that will do 10X+. Feel free to enumerate! ;-) For us, I focus on wide SIMD client + anything about client<>server + in node world, GOAI (Arrow+Plasma+GPU data frames). Don't compete with native... go beyond it.
1 reply 0 retweets 0 likes -
Replying to @lmeyerov @andreasgal and
To be honest, I don't know your space well enough to say. But I do know that people were trying a lot of moonshots in Servo, and I've been pretty impressed by
@pcwalton's experiments in this area.1 reply 0 retweets 0 likes -
I know what a lot of the words in your description of good experiments mean, but not the combination (especially on Twitter). Can you expand (or provide links)?
1 reply 0 retweets 0 likes -
Replying to @wycats @andreasgal and
For arrow, this is about getting JS to work in a big data / HPC world, both internally + interop, similar to PyData world. Ex: https://arrow.apache.org/blog/2017/08/08/plasma-in-memory-object-store/ … .
1 reply 0 retweets 1 like -
WebCL: it's JS bindings for OpenCL (heterogenous / SIMT C) and adds security layers (ex: zeroing memory), so doing WASM without a parallel track on an equiv of this is just delaying the inevitable.
1 reply 0 retweets 0 likes -
General GPU analytics vendors have bet on GOAI, and the
@graphistry team is involved in bringing to the web/node just so we can use it. So happy to share roadmaps + ways to get it out even faster in 2018. We're in SF: leo@graphistry :)1 reply 0 retweets 0 likes -
WebCL missed the boat, IMO. Might as well go straight to Vulkan—which is what is happening, unfortunately with a different competing proposal from each browser vendor. GPU has a general problem though: it’s too unapproachable for almost anyone, Web *or* native, to use it well.
2 replies 0 retweets 1 like
I agree that GPUs have massive untapped potential, but they have an equally massive pedagogical problem that few are interested in solving. People just assume Unity will solve all the usability problems :(
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.