performance gain on SSE2 is approx. 20-25%. altivec
is not tested. performance for unsigned long arithmetic
is unchanged.
Signed-off-by: Peter Lieven <p...@kamp.de>
---
util/cutils.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/util/cutils.c b/util/cutils.c
index a09d8e8..23f0cd6 100644
--- a/util/cutils.c
+++ b/util/cutils.c
@@ -186,6 +186,11 @@ bool buffer_is_zero(const void *buf, size_t len)
* latency.
*/
+ if (((uintptr_t) buf) % sizeof(VECTYPE) == 0
+ && len % 8*sizeof(VECTYPE) == 0) {
+ return buffer_find_nonzero_offset(buf, len)==len;
+ }
+
size_t i;
long d0, d1, d2, d3;
const long * const data = buf;
--
1.7.9.5
