mirror of
https://github.com/SerenityOS/serenity.git
synced 2026-11-07 12:38:38 -10:00
This decreases the boot time on my x86-64 host system from 15 s to 13 s for AArch64 QEMU TCG and 33 s to 30 s for RISC-V QEMU TCG! I additionally measured the performance of this new implementation with this simple benchmark: https://gist.github.com/spholz/b06ea737b435ecc181069cf0d911faa4 Based on to this benchmark, an unroll level 8 seems like a good choice for all tested systems. Here are the speedups for n=0x10000: - Raspberry Pi 5: 7.6 ( 81984 ns -> 10748 ns) - Raspberry Pi 4: 3.3 (131197 ns -> 39704 ns) - StarFive VisionFive 2: 5.5 (279107 ns -> 50650 ns) - AArch64 QEMU TCG: 6.8 (374287 ns -> 54847 ns) - RISC-V QEMU TCG: 6.7 (354195 ns -> 52615 ns) - x86-64 QEMU KVM: 3.8 ( 32443 ns -> 8542 ns)
174 lines
3.9 KiB
C++
174 lines
3.9 KiB
C++
/*
|
|
* Copyright (c) 2018-2020, Andreas Kling <[email protected]>
|
|
*
|
|
* SPDX-License-Identifier: BSD-2-Clause
|
|
*/
|
|
|
|
#include <Kernel/Library/StdLib.h>
|
|
|
|
extern "C" {
|
|
|
|
void* memcpy(void* dest_ptr, void const* src_ptr, size_t n)
|
|
{
|
|
#if ARCH(X86_64)
|
|
size_t dest = (size_t)dest_ptr;
|
|
size_t src = (size_t)src_ptr;
|
|
// FIXME: Support starting at an unaligned address.
|
|
if (!(dest & 0x3) && !(src & 0x3) && n >= 12) {
|
|
size_t size_ts = n / sizeof(size_t);
|
|
n -= size_ts * sizeof(size_t);
|
|
asm volatile(
|
|
"rep movsq\n"
|
|
: "+S"(src), "+D"(dest), "+c"(size_ts)::"memory");
|
|
if (n == 0)
|
|
return dest_ptr;
|
|
}
|
|
asm volatile(
|
|
"rep movsb\n"
|
|
: "+S"(src), "+D"(dest), "+c"(n)::"memory");
|
|
#else
|
|
u8* pd = (u8*)dest_ptr;
|
|
u8 const* ps = (u8 const*)src_ptr;
|
|
for (; n--;)
|
|
*pd++ = *ps++;
|
|
#endif
|
|
return dest_ptr;
|
|
}
|
|
|
|
void* memmove(void* dest, void const* src, size_t n)
|
|
{
|
|
if (dest < src)
|
|
return memcpy(dest, src, n);
|
|
|
|
u8* pd = (u8*)dest;
|
|
u8 const* ps = (u8 const*)src;
|
|
for (pd += n, ps += n; n--;)
|
|
*--pd = *--ps;
|
|
return dest;
|
|
}
|
|
|
|
void* memset(void* dest_ptr, int c, size_t n)
|
|
{
|
|
#if ARCH(X86_64)
|
|
size_t dest = (size_t)dest_ptr;
|
|
// FIXME: Support starting at an unaligned address.
|
|
if (!(dest & 0x3) && n >= 12) {
|
|
size_t size_ts = n / sizeof(size_t);
|
|
size_t expanded_c = explode_byte((u8)c);
|
|
n -= size_ts * sizeof(size_t);
|
|
asm volatile(
|
|
"rep stosq\n"
|
|
: "+D"(dest), "+c"(size_ts)
|
|
: "a"(expanded_c)
|
|
: "memory");
|
|
if (n == 0)
|
|
return dest_ptr;
|
|
}
|
|
asm volatile(
|
|
"rep stosb\n"
|
|
: "+D"(dest), "+c"(n)
|
|
: "a"(c)
|
|
: "memory");
|
|
#else
|
|
auto* dest = static_cast<u8*>(dest_ptr);
|
|
|
|
auto is_word_aligned = [](auto ptr) {
|
|
return reinterpret_cast<FlatPtr>(ptr) % sizeof(FlatPtr) == 0;
|
|
};
|
|
|
|
// Set bytes until destination is word-aligned.
|
|
while (n > 0 && !is_word_aligned(dest)) {
|
|
*dest++ = static_cast<u8>(c);
|
|
n--;
|
|
}
|
|
|
|
// Set in word-sized chunks.
|
|
FlatPtr exploded = explode_byte(c);
|
|
|
|
auto* dest_word = reinterpret_cast<FlatPtr*>(dest);
|
|
|
|
# pragma GCC unroll 8
|
|
while (n >= sizeof(FlatPtr)) {
|
|
*dest_word++ = exploded;
|
|
n -= sizeof(FlatPtr);
|
|
}
|
|
dest = reinterpret_cast<u8*>(dest_word);
|
|
|
|
// Set remaining tail bytes.
|
|
while (n > 0) {
|
|
*dest++ = static_cast<u8>(c);
|
|
n--;
|
|
}
|
|
#endif
|
|
|
|
return dest_ptr;
|
|
}
|
|
|
|
size_t strlen(char const* str)
|
|
{
|
|
size_t len = 0;
|
|
while (*(str++))
|
|
++len;
|
|
return len;
|
|
}
|
|
|
|
size_t strnlen(char const* str, size_t maxlen)
|
|
{
|
|
size_t len = 0;
|
|
for (; len < maxlen && *str; str++)
|
|
len++;
|
|
return len;
|
|
}
|
|
|
|
int strcmp(char const* s1, char const* s2)
|
|
{
|
|
for (; *s1 == *s2; ++s1, ++s2) {
|
|
if (*s1 == 0)
|
|
return 0;
|
|
}
|
|
return *(u8 const*)s1 < *(u8 const*)s2 ? -1 : 1;
|
|
}
|
|
|
|
int memcmp(void const* v1, void const* v2, size_t n)
|
|
{
|
|
auto const* s1 = (u8 const*)v1;
|
|
auto const* s2 = (u8 const*)v2;
|
|
while (n-- > 0) {
|
|
if (*s1++ != *s2++)
|
|
return s1[-1] < s2[-1] ? -1 : 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
int strncmp(char const* s1, char const* s2, size_t n)
|
|
{
|
|
if (!n)
|
|
return 0;
|
|
do {
|
|
if (*s1 != *s2++)
|
|
return *(unsigned char const*)s1 - *(unsigned char const*)--s2;
|
|
if (*s1++ == 0)
|
|
break;
|
|
} while (--n);
|
|
return 0;
|
|
}
|
|
|
|
char* strstr(char const* haystack, char const* needle)
|
|
{
|
|
char nch;
|
|
char hch;
|
|
|
|
if ((nch = *needle++) != 0) {
|
|
size_t len = strlen(needle);
|
|
do {
|
|
do {
|
|
if ((hch = *haystack++) == 0)
|
|
return nullptr;
|
|
} while (hch != nch);
|
|
} while (strncmp(haystack, needle, len) != 0);
|
|
--haystack;
|
|
}
|
|
return const_cast<char*>(haystack);
|
|
}
|
|
}
|