admin/git
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'am/xdiff-hash-tweak'

Browse Source 
Inspired by Ezekiel's recent effort to showcase Rust interface, the
hash function implementation used to hash lines have been updated
to the one used for ELF symbol lookup by Glibc.

* am/xdiff-hash-tweak:
  xdiff: optimize xdl_hash_record_verbatim
  xdiff: refactor xdl_hash_record()
This commit is contained in:
Junio C Hamano
2025-09-08 14:54:34 -07:00
parent 8d5e4290a7 a4bbe8af0b
commit 9e3d0bd1e1
2 changed files with 65 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
xdiff/xutils.c
View File

@@ -249,7 +249,7 @@ int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags)
return 1;
}
static unsigned long xdl_hash_record_with_whitespace(char const **data,
unsigned long xdl_hash_record_with_whitespace(char const **data,
char const *top, long flags) {
unsigned long ha = 5381;
char const *ptr = *data;
@@ -294,19 +294,67 @@ static unsigned long xdl_hash_record_with_whitespace(char const **data,
return ha;
}
unsigned long xdl_hash_record(char const **data, char const *top, long flags) {
unsigned long ha = 5381;
/*
* Compiler reassociation barrier: pretend to modify X and Y to disallow
* changing evaluation order with respect to following uses of X and Y.
*/
#ifdef __GNUC__
#define REASSOC_FENCE(x, y) __asm__("" : "+r"(x), "+r"(y))
#else
#define REASSOC_FENCE(x, y)
#endif
unsigned long xdl_hash_record_verbatim(char const **data, char const *top) {
unsigned long ha = 5381, c0, c1;
char const *ptr = *data;
if (flags & XDF_WHITESPACE_FLAGS)
return xdl_hash_record_with_whitespace(data, top, flags);
#if 0
/*
* The baseline form of the optimized loop below. This is the djb2
* hash (the above function uses a variant with XOR instead of ADD).
*/
for (; ptr < top && *ptr != '\n'; ptr++) {
ha += (ha << 5);
ha ^= (unsigned long) *ptr;
ha += (unsigned long) *ptr;
}
*data = ptr < top ? ptr + 1: ptr;
#else
/* Process two characters per iteration. */
if (top - ptr >= 2) do {
if ((c0 = ptr[0]) == '\n') {
*data = ptr + 1;
return ha;
}
if ((c1 = ptr[1]) == '\n') {
*data = ptr + 2;
c0 += ha;
REASSOC_FENCE(c0, ha);
ha = ha * 32 + c0;
return ha;
}
/*
* Combine characters C0 and C1 into the hash HA. We have
* HA = (HA * 33 + C0) * 33 + C1, and we want to ensure
* that dependency chain over HA is just one multiplication
* and one addition, i.e. we want to evaluate this as
* HA = HA * 33 * 33 + (C0 * 33 + C1), and likewise prefer
* (C0 * 32 + (C0 + C1)) for the expression in parenthesis.
*/
ha *= 33 * 33;
c1 += c0;
REASSOC_FENCE(c1, c0);
c1 += c0 * 32;
REASSOC_FENCE(c1, ha);
ha += c1;
ptr += 2;
} while (ptr < top - 1);
*data = top;
if (ptr < top && (c0 = ptr[0]) != '\n') {
c0 += ha;
REASSOC_FENCE(c0, ha);
ha = ha * 32 + c0;
}
#endif
return ha;
}

10
xdiff/xutils.h
View File

@@ -34,7 +34,15 @@ void *xdl_cha_alloc(chastore_t *cha);
long xdl_guess_lines(mmfile_t *mf, long sample);
int xdl_blankline(const char *line, long size, long flags);
int xdl_recmatch(const char *l1, long s1, const char *l2, long s2, long flags);
unsigned long xdl_hash_record(char const **data, char const *top, long flags);
unsigned long xdl_hash_record_verbatim(char const **data, char const *top);
unsigned long xdl_hash_record_with_whitespace(char const **data, char const *top, long flags);
static inline unsigned long xdl_hash_record(char const **data, char const *top, long flags)
{
if (flags & XDF_WHITESPACE_FLAGS)
return xdl_hash_record_with_whitespace(data, top, flags);
else
return xdl_hash_record_verbatim(data, top);
}
unsigned int xdl_hashbits(unsigned int size);
int xdl_num_out(char *out, long val);
int xdl_emit_hunk_hdr(long s1, long c1, long s2, long c2,