fluencelabs/asmble
1
0
Fork 0
mirror of https://github.com/fluencelabs/asmble synced 2025-04-25 06:42:22 +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. 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, 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 `∞|✓`. 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. * 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
This is quite decent since the Rust+WASM version uses `ByteBuffer`s everywhere, has some overflow checks, and in faster. This is quite decent since the Rust+WASM version uses `ByteBuffer`s everywhere, has some overflow checks, and
general there are some impedance mismatches with the WASM bytecode and the JVM bytecode. 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 * 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). 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 * If I were more serious about it, I'd check with other OS's, add more iterations, tweak some compiler options, include