__BUILTIN_PREFETCH(3)

📦 version 11.0, in nixpkgs unstable

okay bestie, welcome to __BUILTIN_PREFETCH(3) from the Library Functions Manual — this is the group-chat translation, and every fact is staying put 💖

💅 NAME

__builtin_prefetch — GNU extension to prefetch memory ✨

🎀 SYNOPSIS

void
__builtin_prefetch(const void *addr, ...);

🦋 DESCRIPTION

okay so __builtin_prefetch() is the function that prefetches memory from addr. The rationale? minimize cache-miss latency by trying to move data into a cache before accessing the data. Possible use cases include frequently called sections of code in which it is known that the data in a given address is likely to be accessed soon. It's giving “get ahead of the cache miss” energy, fr fr.

Besides addr, there are two optional stdarg(3) arguments, rw and locality.

  • locality — the value of this latter arg should be a compile-time constant integer between 0 and 3. The higher the value, the higher the temporal locality in the data. When locality is 0, it is assumed that there is little or no temporal locality in the data; after access, it is not necessary to leave the data in the cache. The default value is 3.
  • rw — the value is either 0 or 1, corresponding with read and write prefetch, respectively. The default value of rw is 0. Also rw must be a compile-time constant integer.

The __builtin_prefetch() function translates into prefetch instructions only if the architecture has support for these. If there is no support, addr is evaluated only if it includes side effects, although no warnings are issued by gcc(1). Slay, but also noted.

✨ EXAMPLES

The following optimization appears in the heavily used cpu_in_cksum() function that calculates checksums for the inet(4) headers:

       while (mlen >= 32) {
               __builtin_prefetch(data + 32);
               partial += *(uint16_t *)data;
               partial += *(uint16_t *)(data + 2);
               partial += *(uint16_t *)(data + 4);

               ...

               partial += *(uint16_t *)(data + 28);
               partial += *(uint16_t *)(data + 30);

               data += 32;
               mlen -= 32;

               ...

🌈 SEE ALSO

🚨 CAVEATS

bestie, listen: this is a non-standard, compiler-specific extension. That's the caveat. Periodt. 💅
okay bye bestie 🫶 source/version: Debian; date: December 22, 2010; manual page: __BUILTIN_PREFETCH(3). 💖
📦 where this page comes from