Auto merge of rust-lang#88834 - the8472:char-count, r=joshtriplett

bors · bors · commit 175b8db73bfd · 2021-10-04T12:49:57.000Z
optimize str::from_utf8() validation when slice contains multibyte chars and str.chars().count() in all cases

The change shows small but consistent improvements across several x86 target feature levels. I also tried to optimize counting with `slice.as_chunks` but that yielded more inconsistent results, bigger improvements for some optimization levels, lesser ones in others.

```
old, -O2, x86-64
test str::str_char_count_emoji                                  ... bench:       1,924 ns/iter (+/- 26)
test str::str_char_count_lorem                                  ... bench:         879 ns/iter (+/- 12)
test str::str_char_count_lorem_short                            ... bench:           5 ns/iter (+/- 0)

new, -O2, x86-64
test str::str_char_count_emoji                                  ... bench:       1,878 ns/iter (+/- 21)
test str::str_char_count_lorem                                  ... bench:         851 ns/iter (+/- 11)
test str::str_char_count_lorem_short                            ... bench:           4 ns/iter (+/- 0)

old, -O2, x86-64-v2
test str::str_char_count_emoji                                  ... bench:       1,477 ns/iter (+/- 46)
test str::str_char_count_lorem                                  ... bench:         675 ns/iter (+/- 15)
test str::str_char_count_lorem_short                            ... bench:           5 ns/iter (+/- 0)

new, -O2, x86-64-v2
test str::str_char_count_emoji                                  ... bench:       1,323 ns/iter (+/- 39)
test str::str_char_count_lorem                                  ... bench:         593 ns/iter (+/- 18)
test str::str_char_count_lorem_short                            ... bench:           4 ns/iter (+/- 0)

old, -O2, x86-64-v3
test str::str_char_count_emoji                                  ... bench:         748 ns/iter (+/- 7)
test str::str_char_count_lorem                                  ... bench:         348 ns/iter (+/- 2)
test str::str_char_count_lorem_short                            ... bench:           5 ns/iter (+/- 0)

new, -O2, x86-64-v3
test str::str_char_count_emoji                                  ... bench:         650 ns/iter (+/- 4)
test str::str_char_count_lorem                                  ... bench:         301 ns/iter (+/- 1)
test str::str_char_count_lorem_short                            ... bench:           5 ns/iter (+/- 0)
```

and for the multibyte-char string validation:

```
old, -O2, x86-64
test str::str_validate_emoji                                    ... bench:       4,606 ns/iter (+/- 64)

new, -O2, x86-64
test str::str_validate_emoji                                    ... bench:       3,837 ns/iter (+/- 60)
```
diff --git a/library/core/benches/lib.rs b/library/core/benches/lib.rs
@@ -15,3 +15,4 @@ mod num;
 mod ops;
 mod pattern;
 mod slice;
+mod str;
diff --git a/library/core/benches/str.rs b/library/core/benches/str.rs
@@ -0,0 +1,33 @@
+use std::str;
+use test::{black_box, Bencher};
+
+const LOREM_SHORT: &str = "Lorem ipsum";
+
+const LOREM: &str = "Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet.
+Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat.
+Ut wisi enim ad minim veniam, quis nostrud exerci tation ullamcorper suscipit lobortis nisl ut aliquip ex ea commodo consequat. Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis at vero eros et accumsan et iusto odio dignissim qui blandit praesent luptatum zzril delenit augue duis dolore te feugait nulla facilisi.
+Nam liber tempor cum soluta nobis eleifend option congue nihil imperdiet doming id quod mazim placerat facer possim assum. Lorem ipsum dolor sit amet, consectetuer adipiscing elit, sed diam nonummy nibh euismod tincidunt ut laoreet dolore magna aliquam erat volutpat. Ut wisi enim ad minim veniam, quis nostrud exerci tation ullamcorper suscipit lobortis nisl ut aliquip ex ea commodo consequat.
+Duis autem vel eum iriure dolor in hendrerit in vulputate velit esse molestie consequat, vel illum dolore eu feugiat nulla facilisis.
+At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, sed diam nonumy eirmod tempor invidunt ut labore et dolore magna aliquyam erat, sed diam voluptua. At vero eos et accusam et justo duo dolores et ea rebum. Stet clita kasd gubergren, no sea takimata sanctus est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur sadipscing elitr, At accusam aliquyam diam diam dolore dolores duo eirmod eos erat, et nonumy sed tempor et et invidunt justo labore Stet clita ea et gubergren, kasd magna no rebum. sanctus sea sed takimata ut vero voluptua. est Lorem ipsum dolor sit amet. Lorem ipsum dolor sit amet, consetetur";
+
+const EMOJI: &str = "😀😃😄😁😆😅🤣😂🙂🙃😉😊😇🥰😍🤩😘😗☺😚😙🥲😋😛😜🤪😝🤑🤗🤭🤫🤔🤐🤨😐😑😶😶‍🌫️😏😒🙄😬😮‍💨🤥😌😔😪🤤😴😷🤒🤕🤢🤮🤧🥵🥶🥴😵😵‍💫🤯🤠🥳🥸😎🤓🧐😕😟🙁☹😮😯😲😳🥺😦😧😨😰😥😢😭😱😖😣😞😓😩😫🥱😤😡😠🤬😈👿💀☠💩🤡👹👺👻👽👾🤖😺😸😹😻😼😽🙀😿😾🙈🙉🙊💋💌💘💝💖💗💓💞💕💟❣💔❤️‍🔥❤️‍🩹❤🧡💛💚💙💜🤎🖤🤍💯💢💥💫💦💨🕳💣💬👁️‍🗨️🗨🗯💭💤👋🤚🖐✋🖖👌🤌🤏✌🤞🤟🤘🤙👈👉👆🖕👇☝👍👎✊👊🤛🤜👏🙌👐🤲🤝🙏✍💅🤳💪🦾🦿🦵🦶👂🦻👃🧠🫀🫁🦷🦴👀👁👅👄👶🧒👦👧🧑👱👨🧔🧔‍♂️🧔‍♀️👨‍🦰👨‍🦱👨‍🦳👨‍🦲👩👩‍🦰🧑‍🦰👩‍🦱🧑‍🦱👩‍🦳🧑‍🦳👩‍🦲🧑‍🦲👱‍♀️👱‍♂️🧓👴👵🙍🙍‍♂️🙍‍♀️🙎🙎‍♂️🙎‍♀️🙅🙅‍♂️🙅‍♀️🙆🙆‍♂️🙆‍♀️💁💁‍♂️💁‍♀️🙋🙋‍♂️🙋‍♀️🧏🧏‍♂️🧏‍♀️🙇🙇‍♂️🙇‍♀️🤦🤦‍♂️🤦‍♀️🤷🤷‍♂️🤷‍♀️🧑‍⚕️👨‍⚕️👩‍⚕️🧑‍🎓👨‍🎓👩‍🎓🧑‍🏫👨‍🏫👩‍🏫🧑‍⚖️👨‍⚖️👩‍⚖️🧑‍🌾👨‍🌾👩‍🌾🧑‍🍳👨‍🍳👩‍🍳🧑‍🔧👨‍🔧👩‍🔧🧑‍🏭👨‍🏭👩‍🏭🧑‍💼👨‍💼👩‍💼🧑‍🔬👨‍🔬👩‍🔬🧑‍💻👨‍💻👩‍💻🧑‍🎤👨‍🎤👩‍🎤🧑‍🎨👨‍🎨👩‍🎨🧑‍✈️👨‍✈️👩‍✈️🧑‍🚀👨‍🚀👩‍🚀🧑‍🚒👨‍🚒👩‍🚒👮👮‍♂️👮‍♀️🕵🕵️‍♂️🕵️‍♀️💂💂‍♂️💂‍♀️🥷👷👷‍♂️👷‍♀️🤴👸👳👳‍♂️👳‍♀️👲🧕🤵🤵‍♂️🤵‍♀️👰👰‍♂️👰‍♀️🤰🤱👩‍🍼👨‍🍼🧑‍🍼👼🎅🤶🧑‍🎄🦸🦸‍♂️🦸‍♀️🦹🦹‍♂️🦹‍♀️🧙🧙‍♂️🧙‍♀️🧚🧚‍♂️🧚‍♀️🧛🧛‍♂️🧛‍♀️🧜🧜‍♂️🧜‍♀️🧝🧝‍♂️🧝‍♀️🧞🧞‍♂️🧞‍♀️🧟🧟‍♂️🧟‍♀️💆💆‍♂️💆‍♀️💇💇‍♂️💇‍♀️🚶🚶‍♂️🚶‍♀️🧍🧍‍♂️🧍‍♀️🧎🧎‍♂️🧎‍♀️🧑‍🦯👨‍🦯👩‍🦯🧑‍🦼👨‍🦼👩‍🦼🧑‍🦽👨‍🦽👩‍🦽🏃🏃‍♂️🏃‍♀️💃🕺🕴👯👯‍♂️👯‍♀️🧖🧖‍♂️🧖‍♀️🧗🧗‍♂️🧗‍♀️🤺🏇⛷🏂🏌🏌️‍♂️🏌️‍♀️🏄🏄‍♂️🏄‍♀️🚣🚣‍♂️🚣‍♀️🏊🏊‍♂️🏊‍♀️⛹⛹️‍♂️⛹️‍♀️🏋🏋️‍♂️🏋️‍♀️🚴🚴‍♂️🚴‍♀️🚵🚵‍♂️🚵‍♀️🤸🤸‍♂️🤸‍♀️🤼🤼‍♂️🤼‍♀️🤽🤽‍♂️🤽‍♀️🤾🤾‍♂️🤾‍♀️🤹🤹‍♂️🤹‍♀️🧘🧘‍♂️🧘‍♀️🛀🛌🧑‍🤝‍🧑👭👫👬💏👩‍❤️‍💋‍👨👨‍❤️‍💋‍👨👩‍❤️‍💋‍👩💑👩‍❤️‍👨👨‍❤️‍👨👩‍❤️‍👩👪👨‍👩‍👦👨‍👩‍👧👨‍👩‍👧‍👦👨‍👩‍👦‍👦👨‍👩‍👧‍👧👨‍👨‍👦👨‍👨‍👧👨‍👨‍👧‍👦👨‍👨‍👦‍👦👨‍👨‍👧‍👧👩‍👩‍👦👩‍👩‍👧👩‍👩‍👧‍👦👩‍👩‍👦‍👦👩‍👩‍👧‍👧👨‍👦👨‍👦‍👦👨‍👧👨‍👧‍👦👨‍👧‍👧👩‍👦👩‍👦‍👦👩‍👧👩‍👧‍👦👩‍👧‍👧🗣👤👥🫂👣🦰🦱🦳🦲🐵🐒🦍🦧🐶🐕🦮🐕‍🦺🐩🐺🦊🦝🐱🐈🐈‍⬛🦁🐯🐅🐆🐴🐎🦄🦓🦌🦬🐮🐂🐃🐄🐷🐖🐗🐽🐏🐑🐐🐪🐫🦙🦒🐘🦣🦏🦛🐭🐁🐀🐹🐰🐇🐿🦫🦔🦇🐻🐻‍❄️🐨🐼🦥🦦🦨🦘🦡🐾🦃🐔🐓🐣🐤🐥🐦🐧🕊🦅🦆🦢🦉🦤🪶🦩🦚🦜🐸🐊🐢🦎🐍🐲🐉🦕🦖🐳🐋🐬🦭🐟🐠🐡🦈🐙🐚🐌🦋🐛🐜🐝🪲🐞🦗🪳🕷🕸🦂🦟🪰🪱🦠💐🌸💮🏵🌹🥀🌺🌻🌼🌷🌱🪴🌲🌳🌴🌵🌾🌿☘🍀🍁🍂🍃🍇🍈🍉🍊🍋🍌🍍🥭🍎🍏🍐🍑🍒🍓🫐🥝🍅🫒🥥🥑🍆🥔🥕🌽🌶🫑🥒🥬🥦🧄🧅🍄🥜🌰🍞🥐🥖🫓🥨🥯🥞🧇🧀🍖🍗🥩🥓🍔🍟🍕🌭🥪🌮🌯🫔🥙🧆🥚🍳🥘🍲🫕🥣🥗🍿🧈🧂🥫🍱🍘🍙🍚🍛🍜🍝🍠🍢🍣🍤🍥🥮🍡🥟🥠🥡🦀🦞🦐🦑🦪🍦🍧🍨🍩🍪🎂🍰🧁🥧🍫🍬🍭🍮🍯🍼🥛☕🫖🍵🍶🍾🍷🍸🍹🍺🍻🥂🥃🥤🧋🧃🧉🧊🥢🍽🍴🥄🔪🏺🌍🌎🌏🌐🗺🗾🧭🏔⛰🌋🗻🏕🏖🏜🏝🏞🏟🏛🏗🧱🪨🪵🛖🏘🏚🏠🏡🏢🏣🏤🏥🏦🏨🏩🏪🏫🏬🏭🏯🏰💒🗼🗽⛪🕌🛕🕍⛩🕋⛲⛺🌁🌃🏙🌄🌅🌆🌇🌉♨🎠🎡🎢💈🎪🚂🚃🚄🚅🚆🚇🚈🚉🚊🚝🚞🚋🚌🚍🚎🚐🚑🚒🚓🚔🚕🚖🚗🚘🚙🛻🚚🚛🚜🏎🏍🛵🦽🦼🛺🚲🛴🛹🛼🚏🛣🛤🛢⛽🚨🚥🚦🛑🚧⚓⛵🛶🚤🛳⛴🛥🚢✈🛩🛫🛬🪂💺🚁🚟🚠🚡🛰🚀🛸🛎🧳⌛⏳⌚⏰⏱⏲🕰🕛🕧🕐🕜🕑🕝🕒🕞🕓🕟🕔🕠🕕🕡🕖🕢🕗🕣🕘🕤🕙🕥🕚🕦🌑🌒🌓🌔🌕🌖🌗🌘🌙🌚🌛🌜🌡☀🌝🌞🪐⭐🌟🌠🌌☁⛅⛈🌤🌥🌦🌧🌨🌩🌪🌫🌬🌀🌈🌂☂☔⛱⚡❄☃⛄☄🔥💧🌊🎃🎄🎆🎇🧨✨🎈🎉🎊🎋🎍🎎🎏🎐🎑🧧🎀🎁🎗🎟🎫🎖🏆🏅🥇🥈🥉⚽⚾🥎🏀🏐🏈🏉🎾🥏🎳🏏🏑🏒🥍🏓🏸🥊🥋🥅⛳⛸🎣🤿🎽🎿🛷🥌🎯🪀🪁🎱🔮🪄🧿🎮🕹🎰🎲🧩🧸🪅🪆♠♥♦♣♟🃏🀄🎴🎭🖼🎨🧵🪡🧶🪢👓🕶🥽🥼🦺👔👕👖🧣🧤🧥🧦👗👘🥻🩱🩲🩳👙👚👛👜👝🛍🎒🩴👞👟🥾🥿👠👡🩰👢👑👒🎩🎓🧢🪖⛑📿💄💍💎🔇🔈🔉🔊📢📣📯🔔🔕🎼🎵🎶🎙🎚🎛🎤🎧📻🎷🪗🎸🎹🎺🎻🪕🥁";
+
+#[bench]
+fn str_char_count_lorem(b: &mut Bencher) {
+    b.iter(|| black_box(LOREM).chars().count());
+}
+
+#[bench]
+fn str_char_count_lorem_short(b: &mut Bencher) {
+    b.iter(|| black_box(LOREM_SHORT).chars().count());
+}
+
+#[bench]
+fn str_char_count_emoji(b: &mut Bencher) {
+    b.iter(|| black_box(EMOJI).chars().count());
+}
+
+#[bench]
+fn str_validate_emoji(b: &mut Bencher) {
+    b.iter(|| str::from_utf8(black_box(EMOJI.as_bytes())));
+}
diff --git a/library/core/src/str/validations.rs b/library/core/src/str/validations.rs
@@ -22,7 +22,7 @@ fn utf8_acc_cont_byte(ch: u32, byte: u8) -> u32 {
 /// bits `10`).
 #[inline]
 pub(super) fn utf8_is_cont_byte(byte: u8) -> bool {
-    (byte & !CONT_MASK) == TAG_CONT_U8
+    (byte as i8) < -64
 }
 
 #[inline]
@@ -163,7 +163,7 @@ pub(super) fn run_utf8_validation(v: &[u8]) -> Result<(), Utf8Error> {
             //               %xF4 %x80-8F 2( UTF8-tail )
             match w {
                 2 => {
-                    if next!() & !CONT_MASK != TAG_CONT_U8 {
+                    if next!() as i8 >= -64 {
                         err!(Some(1))
                     }
                 }
@@ -175,7 +175,7 @@ pub(super) fn run_utf8_validation(v: &[u8]) -> Result<(), Utf8Error> {
                         | (0xEE..=0xEF, 0x80..=0xBF) => {}
                         _ => err!(Some(1)),
                     }
-                    if next!() & !CONT_MASK != TAG_CONT_U8 {
+                    if next!() as i8 >= -64 {
                         err!(Some(2))
                     }
                 }
@@ -184,10 +184,10 @@ pub(super) fn run_utf8_validation(v: &[u8]) -> Result<(), Utf8Error> {
                         (0xF0, 0x90..=0xBF) | (0xF1..=0xF3, 0x80..=0xBF) | (0xF4, 0x80..=0x8F) => {}
                         _ => err!(Some(1)),
                     }
-                    if next!() & !CONT_MASK != TAG_CONT_U8 {
+                    if next!() as i8 >= -64 {
                         err!(Some(2))
                     }
-                    if next!() & !CONT_MASK != TAG_CONT_U8 {
+                    if next!() as i8 >= -64 {
                         err!(Some(3))
                     }
                 }
@@ -258,8 +258,6 @@ pub fn utf8_char_width(b: u8) -> usize {
 
 /// Mask of the value bits of a continuation byte.
 const CONT_MASK: u8 = 0b0011_1111;
-/// Value of the tag bits (tag mask is !CONT_MASK) of a continuation byte.
-const TAG_CONT_U8: u8 = 0b1000_0000;
 
 // truncate `&str` to length at most equal to `max`
 // return `true` if it were truncated, and the new str.

Original file line number	Diff line number	Diff line change
`@@ -22,7 +22,7 @@ fn utf8_acc_cont_byte(ch: u32, byte: u8) -> u32 {`
`22`	`22`	/// bits `10`).
`23`	`23`	`#[inline]`
`24`	`24`	`pub(super) fn utf8_is_cont_byte(byte: u8) -> bool {`
`25`		`- (byte & !CONT_MASK) == TAG_CONT_U8`
	`25`	`+ (byte as i8) < -64`
`26`	`26`	`}`
`27`	`27`
`28`	`28`	`#[inline]`
`@@ -163,7 +163,7 @@ pub(super) fn run_utf8_validation(v: &[u8]) -> Result<(), Utf8Error> {`
`163`	`163`	`// %xF4 %x80-8F 2( UTF8-tail )`
`164`	`164`	`match w {`
`165`	`165`	`2 => {`
`166`		`- if next!() & !CONT_MASK != TAG_CONT_U8 {`
	`166`	`+ if next!() as i8 >= -64 {`
`167`	`167`	`err!(Some(1))`
`168`	`168`	`}`
`169`	`169`	`}`
`@@ -175,7 +175,7 @@ pub(super) fn run_utf8_validation(v: &[u8]) -> Result<(), Utf8Error> {`
`175`	`175`	`\| (0xEE..=0xEF, 0x80..=0xBF) => {}`
`176`	`176`	`_ => err!(Some(1)),`
`177`	`177`	`}`
`178`		`- if next!() & !CONT_MASK != TAG_CONT_U8 {`
	`178`	`+ if next!() as i8 >= -64 {`
`179`	`179`	`err!(Some(2))`
`180`	`180`	`}`
`181`	`181`	`}`
`@@ -184,10 +184,10 @@ pub(super) fn run_utf8_validation(v: &[u8]) -> Result<(), Utf8Error> {`
`184`	`184`	`(0xF0, 0x90..=0xBF) \| (0xF1..=0xF3, 0x80..=0xBF) \| (0xF4, 0x80..=0x8F) => {}`
`185`	`185`	`_ => err!(Some(1)),`
`186`	`186`	`}`
`187`		`- if next!() & !CONT_MASK != TAG_CONT_U8 {`
	`187`	`+ if next!() as i8 >= -64 {`
`188`	`188`	`err!(Some(2))`
`189`	`189`	`}`
`190`		`- if next!() & !CONT_MASK != TAG_CONT_U8 {`
	`190`	`+ if next!() as i8 >= -64 {`
`191`	`191`	`err!(Some(3))`
`192`	`192`	`}`
`193`	`193`	`}`
`@@ -258,8 +258,6 @@ pub fn utf8_char_width(b: u8) -> usize {`
`258`	`258`
`259`	`259`	`/// Mask of the value bits of a continuation byte.`
`260`	`260`	`const CONT_MASK: u8 = 0b0011_1111;`
`261`		`-/// Value of the tag bits (tag mask is !CONT_MASK) of a continuation byte.`
`262`		`-const TAG_CONT_U8: u8 = 0b1000_0000;`
`263`	`261`
`264`	`262`	// truncate `&str` to length at most equal to `max`
`265`	`263`	// return `true` if it were truncated, and the new str.