* [PATCH] reduce branches for size class calculation
@ 2024-04-05 21:40 Eric Wong
0 siblings, 0 replies; only message in thread
From: Eric Wong @ 2024-04-05 21:40 UTC (permalink / raw)
To: spew
We can use bit twiddling to find the next power-of-two without
branching for each iteration of the loop (since the new loop
is simple enough for a compiler to unroll).
---
mwrap_core.h | 16 ++++++----------
1 file changed, 6 insertions(+), 10 deletions(-)
diff --git a/mwrap_core.h b/mwrap_core.h
index 6467f1c..02b42ad 100644
--- a/mwrap_core.h
+++ b/mwrap_core.h
@@ -686,17 +686,13 @@ static inline size_t size_class_pad(size_t bytes)
* minimize fragmentation. This means we pay a 0-20% overhead on
* the initial allocations to improve the likelyhood of reuse.
*/
- size_t max = sizeof(void *) << 5;
- size_t nxt;
- do {
- if (bytes <= max) {
- size_t sc_bytes = size_align(bytes, max >> 3);
- return sc_bytes <= mm_thresh ? sc_bytes : bytes;
- }
- nxt = max << 1;
- } while (nxt > max && nxt < mm_thresh && (max = nxt));
+ size_t np2 = bytes - 1;
+ for (size_t i = 1; i < sizeof(size_t) * CHAR_BIT; i <<= 1)
+ np2 |= np2 >> i;
+ ++np2; // next power-of-two
- return bytes;
+ size_t sc_bytes = size_align(bytes, np2 >> 3);
+ return sc_bytes < mm_thresh ? sc_bytes : mm_thresh;
}
void *malloc(size_t size)
^ permalink raw reply related [flat|nested] only message in thread
only message in thread, other threads:[~2024-04-05 21:40 UTC | newest]
Thread overview: (only message) (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2024-04-05 21:40 [PATCH] reduce branches for size class calculation Eric Wong
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).