fluencelabs/asmble
1
0
Fork 0
mirror of https://github.com/fluencelabs/asmble synced 2025-04-24 22:32:19 +00:00
Code Issues Projects Releases Wiki Activity

Example README word fix

Browse Source
This commit is contained in:
Chad Retz 2017-12-06 03:38:59 -06:00
parent 7c61edf257
commit bc980b1e81
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
examples/rust-regex/README.md
View File

@ -125,9 +125,9 @@ To keep from making this a big long post like most benchmark posts tend to be, h
accessible heap before the benchmark started to be fair.
* Like the unit test, I excluded `[a-q][^u-z]{13}x` because Rust is really slow at it (Java wins by a mile here). Also
like the unit test, `?|?` is actually `∞|✓`.
* Of the ones tested, Rust is faster in 6 and Java is faster in the other 10. And where it is faster, it is much faster.
This is quite decent since the Rust+WASM version uses `ByteBuffer`s everywhere, has some overflow checks, and in
general there are some impedance mismatches with the WASM bytecode and the JVM bytecode.
* Of the ones tested, Rust is faster in 6 and Java is faster in the other 10. And where Rust is faster, it is much
faster. This is quite decent since the Rust+WASM version uses `ByteBuffer`s everywhere, has some overflow checks, and
in general there are some impedance mismatches with the WASM bytecode and the JVM bytecode.
* Notice the low error numbers on the Rust versions. The error number is the deviation between invocations. This shows
the WASM-to-JVM ends up quite deterministic (or maybe, that there is just too much cruft to JIT, heh).
* If I were more serious about it, I'd check with other OS's, add more iterations, tweak some compiler options, include