~/talk

A Snapshot of the Performance of Wasm Backends for Managed Languages

on YouTube 24m
Talkat MPLR 2025 · on Tuesday, 2025-10-14· [webassembly, compilers-and-language-design]

speakers

name:Manuel Serrano
links:none on file
name:Robert Bruce Findler
links:none on file

resources

video:https://youtu.be/Lm53oPq7R6Q
slides:none on file

summary

Compares six managed-language Wasm backends to their native counterparts and to each other, reporting concrete slowdowns: the best backends average 1.4× slower than native, some backends exceed 8× slowdown, and Bigloo-compiled code sits around 1.5–2× native. Measures effects of choices: generating Wasm without the relooper optimization roughly doubles cost, using V8’s unsafe mode gives ~30% speedup at crash risk, and double runtime type checks and missing stack ops remain practical limitations.

AI-written summary · about

chapters (6)

  1. 0:00WebAssembly intro
  2. 6:46Managed language performance
  3. 13:28Wasm compilation strategies
  4. 17:18Wasm type safety limits
  5. 18:01Wasm potential final thoughts
  6. 20:12Q&A benchmarks & startup

related talks

~/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.