Thread (4 messages) flat view 4 messages, 1 author, 2016-06-15
DORMANTno replies

[PATCH 1/4] pack-objects: mark add_to_write_order() as inline

From: Dan McGee <hidden>
Date: 2016-06-15 22:52:17
Subsystem: the rest · Maintainer: Linus Torvalds

This function is a whole 26 bytes when compiled on x86_64, but is
currently invoked over 1.037 billion times when running pack-objects on
the Linux kernel git repository. This is hitting the point where
micro-optimizations do make a difference, and inlining it only increases
the object file size by 38 bytes.

As reported by perf, this dropped task-clock from 84183 to 83373 ms, and
total cycles from 223.5 billion to 221.6 billion. Not astronomical, but
worth getting for adding one word.

Signed-off-by: Dan McGee <redacted>
---
 builtin/pack-objects.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index 2b18de5..0ab3a3b 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -454,7 +454,7 @@ static int mark_tagged(const char *path, const unsigned char *sha1, int flag,
 	return 0;
 }
 
-static void add_to_write_order(struct object_entry **wo,
+static inline void add_to_write_order(struct object_entry **wo,
 			       int *endp,
 			       struct object_entry *e)
 {
-- 
1.7.7
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help