~/talk

Distributed Computation with WASM and WASI

slides:none on file

Claims a concrete path to "move compute to data" by shipping WASM modules into storage engines rather than pulling 82 million rows to a laptop, demonstrating a sentiment‑analysis WASM compiled from Rust and run locally with Dask and distributed in Google Cloud on SingleStore to produce bucketed analytics and trend lines. Presents a Rust reference implementation and a macro that emits WASI bindings (via witx bindgen), links code on GitHub, and discusses resource control using gas‑like accounting and possible throttling. WASI-data proposal underlies the design, with a SingleStore + Dask demo showing 82 million rows processed.

AI-written summary · about

  1. 0:00Intro
  2. 0:51Let's talk about apps
  3. 1:16Modern apps = data explosion
  4. 1:42leading to data everywhere
  5. 2:41WASM to the rescue
  6. 4:26Introducing wasi-data
  7. 6:07Lambda functions
  8. 7:34Procedural extensions
  9. 8:32Relational extensions
  10. 10:16Workflow extensions
  11. 18:10works with the ecosystem
  12. 18:51Conclusion
  13. 19:26Questions?
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.