Re-improve perf of skipping spaces and comments

On my M1 mac this shows as ~25% faster at parsing Num.roc than the old implementation, probably because nobody wrote any NEON code.

Even on my x86_64 linux box (Ryzen 2700x), this shows as 10% faster than the current SSE implementation (running with RUSTFLAGS="-C target-cpu=native").
This commit is contained in:
Joshua Warner 2022-12-08 17:17:42 -08:00
parent 5f29402297
commit e83cd8f191
No known key found for this signature in database
GPG key ID: 89AD497003F93FDD
4 changed files with 195 additions and 6 deletions

View file

@ -1,8 +1,7 @@
use std::path::PathBuf;
use bumpalo::Bump;
use criterion::{black_box, criterion_group, criterion_main, Criterion};
use roc_parse::{module, module::module_defs, parser::Parser, state::State};
use std::path::PathBuf;
pub fn parse_benchmark(c: &mut Criterion) {
c.bench_function("parse false-interpreter", |b| {