Mirrors/fish-shell
2
0
Fork 0
mirror of https://github.com/fish-shell/fish-shell synced 2025-01-16 23:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity

Add str2wcs optimization for ascii-only inputs

Browse source 
This avoids the heavy hit of __gconv_transform_utf8_internal.

In the worst case, after `is_ascii` returns the string is guaranteed to
be in the CPU cache (assuming realistic input sizes). In the best (and
hopefully extremely common) case, the conversion table lookups are
completely avoided.

In terms of real world gains, simply calling `history` is anywhere from
2x to 3x faster for large history files composed of mostly ascii
content under glibc 2.31 on AMD64.
This commit is contained in:
Mahmoud Al-Qudsi 2020-09-07 19:31:07 -05:00
parent 1365379518
commit 84c72f2817
1 changed files with 28 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

29
src/common.cpp
View file

@ -237,6 +237,33 @@ bool is_windows_subsystem_for_linux() {
}
#endif // HAVE_BACKTRACE_SYMBOLS
template <typename T>
inline __attribute__((always_inline))
constexpr const T * aligned_start(const T *in, uint8_t alignment) {
return (const T *) (((uintptr_t)in + (uintptr_t)(alignment-1)) & ~((uintptr_t) (alignment -1)));
}
inline __attribute__((always_inline))
bool is_ascii (const char *in, int len) {
const char *aligned = aligned_start(in, 64);
char bitmask1 = 0;
for (auto ptr = in; ptr < aligned && ptr < (in + len); ++ptr) {
bitmask1 |= *ptr;
}
uint64_t bitmask2 = 0;
for (auto ptr = (const uint64_t *)aligned; (uintptr_t) ptr < (uintptr_t) (in + len); ++ptr) {
bitmask2 |= *ptr;
}
char bitmask3 = 0;
for (auto ptr = std::max(in, (const char *) ((uintptr_t)(in + len) & ~((uintptr_t)(64-1))));
ptr < (in + len); ++ptr) {
bitmask3 |= *ptr;
}
return (uint64_t(bitmask1 & 0x80) | uint64_t(bitmask3 & 0x80)
| (bitmask2 & 0x8080808080808080ULL)) == 0ULL;
}
/// Converts the narrow character string \c in into its wide equivalent, and return it.
///
/// The string may contain embedded nulls.
@ -251,7 +278,7 @@ static wcstring str2wcs_internal(const char *in, const size_t in_len) {
result.reserve(in_len);
size_t in_pos = 0;
if (MB_CUR_MAX == 1) {
if (MB_CUR_MAX == 1 || is_ascii(in, in_len)) {
// Single-byte locale, all values are legal.
while (in_pos < in_len) {
result.push_back(static_cast<unsigned char>(in[in_pos]));