Skip to content

Commit 46ad16b

Browse files
committed
Auto merge of #85630 - gilescope:to_digit_speedup3, r=nagisa
to_digit simplification (less jumps) I just realised we might be able to make use of the fact that changing case in ascii is easy to help simplify to_digit some more. It looks a bit cleaner and it looks like it's less jumps and there's less instructions in the generated assembly: https://godbolt.org/z/84Erh5dhz The benchmarks don't really tell me much. Maybe a slight improvement on the var radix. Before: ``` test char::methods::bench_to_digit_radix_10 ... bench: 53,819 ns/iter (+/- 8,314) test char::methods::bench_to_digit_radix_16 ... bench: 57,265 ns/iter (+/- 10,730) test char::methods::bench_to_digit_radix_2 ... bench: 55,077 ns/iter (+/- 5,431) test char::methods::bench_to_digit_radix_36 ... bench: 56,549 ns/iter (+/- 3,248) test char::methods::bench_to_digit_radix_var ... bench: 43,848 ns/iter (+/- 3,189) test char::methods::bench_to_digit_radix_10 ... bench: 51,707 ns/iter (+/- 10,946) test char::methods::bench_to_digit_radix_16 ... bench: 52,835 ns/iter (+/- 2,689) test char::methods::bench_to_digit_radix_2 ... bench: 51,012 ns/iter (+/- 2,746) test char::methods::bench_to_digit_radix_36 ... bench: 53,210 ns/iter (+/- 8,645) test char::methods::bench_to_digit_radix_var ... bench: 40,386 ns/iter (+/- 4,711) test char::methods::bench_to_digit_radix_10 ... bench: 54,088 ns/iter (+/- 5,677) test char::methods::bench_to_digit_radix_16 ... bench: 55,972 ns/iter (+/- 17,229) test char::methods::bench_to_digit_radix_2 ... bench: 52,083 ns/iter (+/- 2,425) test char::methods::bench_to_digit_radix_36 ... bench: 54,132 ns/iter (+/- 1,548) test char::methods::bench_to_digit_radix_var ... bench: 41,250 ns/iter (+/- 5,299) ``` After: ``` test char::methods::bench_to_digit_radix_10 ... bench: 48,907 ns/iter (+/- 19,449) test char::methods::bench_to_digit_radix_16 ... bench: 52,673 ns/iter (+/- 8,122) test char::methods::bench_to_digit_radix_2 ... bench: 48,509 ns/iter (+/- 2,885) test char::methods::bench_to_digit_radix_36 ... bench: 50,526 ns/iter (+/- 4,610) test char::methods::bench_to_digit_radix_var ... bench: 38,618 ns/iter (+/- 3,180) test char::methods::bench_to_digit_radix_10 ... bench: 54,202 ns/iter (+/- 6,994) test char::methods::bench_to_digit_radix_16 ... bench: 56,585 ns/iter (+/- 8,448) test char::methods::bench_to_digit_radix_2 ... bench: 50,548 ns/iter (+/- 1,674) test char::methods::bench_to_digit_radix_36 ... bench: 52,749 ns/iter (+/- 2,576) test char::methods::bench_to_digit_radix_var ... bench: 40,215 ns/iter (+/- 3,327) test char::methods::bench_to_digit_radix_10 ... bench: 50,233 ns/iter (+/- 22,272) test char::methods::bench_to_digit_radix_16 ... bench: 50,841 ns/iter (+/- 19,981) test char::methods::bench_to_digit_radix_2 ... bench: 50,386 ns/iter (+/- 4,555) test char::methods::bench_to_digit_radix_36 ... bench: 52,369 ns/iter (+/- 2,737) test char::methods::bench_to_digit_radix_var ... bench: 40,417 ns/iter (+/- 2,766) ``` I removed the likely as it resulted in a few less instructions. (It's not been in there long - I added it in the last to_digit iteration).
2 parents 16e1839 + 9c3d81e commit 46ad16b

File tree

3 files changed

+21
-16
lines changed

3 files changed

+21
-16
lines changed

library/core/src/char/methods.rs

+9-15
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,5 @@
11
//! impl char {}
22
3-
use crate::intrinsics::likely;
43
use crate::slice;
54
use crate::str::from_utf8_unchecked_mut;
65
use crate::unicode::printable::is_printable;
@@ -332,21 +331,16 @@ impl char {
332331
#[inline]
333332
pub fn to_digit(self, radix: u32) -> Option<u32> {
334333
assert!(radix <= 36, "to_digit: radix is too high (maximum 36)");
335-
// the code is split up here to improve execution speed for cases where
336-
// the `radix` is constant and 10 or smaller
337-
let val = if likely(radix <= 10) {
338-
// If not a digit, a number greater than radix will be created.
339-
(self as u32).wrapping_sub('0' as u32)
340-
} else {
341-
match self {
342-
'0'..='9' => self as u32 - '0' as u32,
343-
'a'..='z' => self as u32 - 'a' as u32 + 10,
344-
'A'..='Z' => self as u32 - 'A' as u32 + 10,
345-
_ => return None,
334+
// If not a digit, a number greater than radix will be created.
335+
let mut digit = (self as u32).wrapping_sub('0' as u32);
336+
if radix > 10 {
337+
if digit < 10 {
338+
return Some(digit);
346339
}
347-
};
348-
349-
if val < radix { Some(val) } else { None }
340+
// Force the 6th bit to be set to ensure ascii is lower case.
341+
digit = (self as u32 | 0b10_0000).wrapping_sub('a' as u32).saturating_add(10);
342+
}
343+
(digit < radix).then_some(digit)
350344
}
351345

352346
/// Returns an iterator that yields the hexadecimal Unicode escape of a

library/core/src/lib.rs

+1
Original file line numberDiff line numberDiff line change
@@ -65,6 +65,7 @@
6565
#![feature(allow_internal_unstable)]
6666
#![feature(arbitrary_self_types)]
6767
#![feature(asm)]
68+
#![feature(bool_to_option)]
6869
#![feature(cfg_target_has_atomic)]
6970
#![feature(const_heap)]
7071
#![feature(const_alloc_layout)]

library/core/tests/char.rs

+11-1
Original file line numberDiff line numberDiff line change
@@ -67,10 +67,20 @@ fn test_to_digit() {
6767
assert_eq!('A'.to_digit(16), Some(10));
6868
assert_eq!('b'.to_digit(16), Some(11));
6969
assert_eq!('B'.to_digit(16), Some(11));
70+
assert_eq!('A'.to_digit(36), Some(10));
7071
assert_eq!('z'.to_digit(36), Some(35));
7172
assert_eq!('Z'.to_digit(36), Some(35));
72-
assert_eq!(' '.to_digit(10), None);
73+
assert_eq!('['.to_digit(36), None);
74+
assert_eq!('`'.to_digit(36), None);
75+
assert_eq!('{'.to_digit(36), None);
7376
assert_eq!('$'.to_digit(36), None);
77+
assert_eq!('@'.to_digit(16), None);
78+
assert_eq!('G'.to_digit(16), None);
79+
assert_eq!('g'.to_digit(16), None);
80+
assert_eq!(' '.to_digit(10), None);
81+
assert_eq!('/'.to_digit(10), None);
82+
assert_eq!(':'.to_digit(10), None);
83+
assert_eq!(':'.to_digit(11), None);
7484
}
7585

7686
#[test]

0 commit comments

Comments
 (0)