rust/library/core/src/str
Samuel Tardieu 460a627b83
Rollup merge of #143907 - Kijewski:pr-inline-split_at_unchecked, r=Mark-Simulacrum
core: make `str::split_at_unchecked()` inline

This PR adds `#[inline]` to the method `str::split_at_unchecked()`. This is done for two reasons:

1. The method is tiny, e.g. on AMD-64 (<https://godbolt.org/z/ba68fdfxn>):

   ```asm
   movq    %rdi, %rax
   subq    %rcx, %rdx
   movq    %rsi, (%rdi)
   addq    %rcx, %rsi
   movq    %rcx, 8(%rdi)
   movq    %rsi, 16(%rdi)
   movq    %rdx, 24(%rdi)
   retq
   ```

2. More importantly, inlining the method enables further automatic optimizations. E.g. if you split at index 3, then in the compiler (rustc, llvm or both) knows that this code cannot fail, and the panicking path is omitted in the generated code:

   ```rust
   pub fn punctuation(i: &str) -> Result<(), ()> {
       const THREE_CHARS: &[[u8; 3]] = &[*b"<<=", *b">>=", *b"...", *b"..="];

       if let Some((head, _)) = i.split_at_checked(3)
           && THREE_CHARS.contains(&head.as_bytes().try_into().unwrap())
       {
           Ok(())
       } else {
           Err(())
       }
   }
   ```

   <details>
   <summary>Without PR</summary>

   <https://play.rust-lang.org/?version=stable&mode=release&edition=2024&gist=0234de8158f467eebd73286f20d6e27a>

   ```asm
   playground::punctuation:
           subq    $40, %rsp
           movq    %rsi, %rdx
           movq    %rdi, %rsi
           movb    $1, %al
           cmpq    $3, %rdx
           ja      .LBB2_2
           je      .LBB2_3
   .LBB2_11:
           addq    $40, %rsp
           retq
   .LBB2_2:
           cmpb    $-64, 3(%rsi)
           jl      .LBB2_11
   .LBB2_3:
           leaq    8(%rsp), %rdi
           movl    $3, %ecx
           callq   *core::str::<impl str>::split_at_unchecked@GOTPCREL(%rip)
           movq    8(%rsp), %rcx
           movb    $1, %al
           testq   %rcx, %rcx
           je      .LBB2_11
           cmpq    $3, 16(%rsp)
           jne     .LBB2_12
           movzwl  (%rcx), %edx
           movzbl  2(%rcx), %ecx
           shll    $16, %ecx
           orl     %edx, %ecx
           cmpl    $4013115, %ecx
           jg      .LBB2_8
           cmpl    $3026478, %ecx
           je      .LBB2_10
           cmpl    $4009518, %ecx
           je      .LBB2_10
           jmp     .LBB2_11
   .LBB2_8:
           cmpl    $4013630, %ecx
           je      .LBB2_10
           cmpl    $4013116, %ecx
           jne     .LBB2_11
   .LBB2_10:
           xorl    %eax, %eax
           addq    $40, %rsp
           retq
   .LBB2_12:
           leaq    .Lanon.d98a7fbb86d10a97c24516e267466134.2(%rip), %rdi
           leaq    .Lanon.d98a7fbb86d10a97c24516e267466134.1(%rip), %rcx
           leaq    .Lanon.d98a7fbb86d10a97c24516e267466134.6(%rip), %r8
           leaq    7(%rsp), %rdx
           movl    $43, %esi
           callq   *core::result::unwrap_failed@GOTPCREL(%rip)
   ```
   </details>

   <details>
   <summary>With PR</summary>

   <https://play.rust-lang.org/?version=stable&mode=release&edition=2024&gist=5d4058c79ce0f6cb1a434190427d2055>

   ```asm
   playground::punctuation:
           movb    $1, %al
           cmpq    $3, %rsi
           ja      .LBB0_2
           je      .LBB0_3
   .LBB0_9:
           retq
   .LBB0_2:
           cmpb    $-64, 3(%rdi)
           jl      .LBB0_9
   .LBB0_3:
           movzwl  (%rdi), %eax
           movzbl  2(%rdi), %ecx
           shll    $16, %ecx
           orl     %eax, %ecx
           movb    $1, %al
           cmpl    $4013115, %ecx
           jg      .LBB0_6
           cmpl    $3026478, %ecx
           je      .LBB0_8
           cmpl    $4009518, %ecx
           je      .LBB0_8
           jmp     .LBB0_9
   .LBB0_6:
           cmpl    $4013630, %ecx
           je      .LBB0_8
           cmpl    $4013116, %ecx
           jne     .LBB0_9
   .LBB0_8:
           xorl    %eax, %eax
           retq
   ```
   </details>
2025-07-15 12:52:41 +02:00
..
converts.rs std: note that std::str::from_utf8* functions are aliases to std::<str>::from_utf8* methods 2025-05-31 22:37:59 +08:00
count.rs use is_multiple_of instead of manual modulo 2025-07-05 10:55:35 +02:00
error.rs add FIXME(const-hack) 2024-09-08 23:08:40 +02:00
iter.rs use div_ceil instead of manual logic 2025-07-05 10:55:42 +02:00
lossy.rs docs: alias limit to Iterator::take, cite [u8]::utf8_chunks in Utf8Chunks 2025-05-02 23:41:52 +02:00
mod.rs Rollup merge of #143907 - Kijewski:pr-inline-split_at_unchecked, r=Mark-Simulacrum 2025-07-15 12:52:41 +02:00
pattern.rs Revert "increase perf of charsearcher for single ascii characters" 2025-05-28 09:29:12 +02:00
traits.rs FromStr: Rework explanation of FromStr/Display round-tripping 2025-06-03 15:41:47 -07:00
validations.rs use is_multiple_of instead of manual modulo 2025-07-05 10:55:35 +02:00