aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJeff King <peff@peff.net>2014-02-12 11:48:28 -0500
committerJunio C Hamano <gitster@pobox.com>2014-02-12 11:21:29 -0800
commit6b5b3a27b7faf9d72efec28fa017408daf45cd00 (patch)
treeeed098a0f65d77d4f11d235009abc26f2939503f
parenta201c20b41a2f0725977bcb89a2a66135d776ba2 (diff)
downloadgit-6b5b3a27b7faf9d72efec28fa017408daf45cd00.tar.gz
git-6b5b3a27b7faf9d72efec28fa017408daf45cd00.tar.xz
ewah: unconditionally ntohll ewah data
Commit a201c20 tried to optimize out a loop like: for (i = 0; i < len; i++) data[i] = ntohll(data[i]); in the big-endian case, because we know that ntohll is a noop, and we do not need to pay the cost of the loop at all. However, it mistakenly assumed that __BYTE_ORDER was always defined, whereas it may not be on systems which do not define it by default, and where we did not need to define it to set up the ntohll macro. This includes OS X and Windows. We could muck with the ordering in compat/bswap.h to make sure it is defined unconditionally, but it is simpler to still to just execute the loop unconditionally. That avoids the application code knowing anything about these magic macros, and lets it depend only on having ntohll defined. And since the resulting loop looks like (on a big-endian system): for (i = 0; i < len; i++) data[i] = data[i]; any decent compiler can probably optimize it out. Original report and analysis by Brian Gernhardt. Signed-off-by: Jeff King <peff@peff.net> Signed-off-by: Junio C Hamano <gitster@pobox.com>
-rw-r--r--ewah/ewah_io.c10
1 files changed, 3 insertions, 7 deletions
diff --git a/ewah/ewah_io.c b/ewah/ewah_io.c
index 4a7fae6b8..f7f700ef5 100644
--- a/ewah/ewah_io.c
+++ b/ewah/ewah_io.c
@@ -113,6 +113,7 @@ int ewah_serialize(struct ewah_bitmap *self, int fd)
int ewah_read_mmap(struct ewah_bitmap *self, void *map, size_t len)
{
uint8_t *ptr = map;
+ size_t i;
self->bit_size = get_be32(ptr);
ptr += sizeof(uint32_t);
@@ -135,13 +136,8 @@ int ewah_read_mmap(struct ewah_bitmap *self, void *map, size_t len)
memcpy(self->buffer, ptr, self->buffer_size * sizeof(uint64_t));
ptr += self->buffer_size * sizeof(uint64_t);
-#if __BYTE_ORDER != __BIG_ENDIAN
- {
- size_t i;
- for (i = 0; i < self->buffer_size; ++i)
- self->buffer[i] = ntohll(self->buffer[i]);
- }
-#endif
+ for (i = 0; i < self->buffer_size; ++i)
+ self->buffer[i] = ntohll(self->buffer[i]);
self->rlw = self->buffer + get_be32(ptr);