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>
Reviewed-by: Eric Blake <ebl...@redhat.com>
---
util/cutils.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/util/cutils.c b/util/cutils.c
index 41c627e..0f43c22 100644
--- a/util/cutils.c
+++ b/util/cutils.c
@@ -205,6 +205,11 @@ bool buffer_is_zero(const void *buf, size_t len)
long d0, d1, d2, d3;
const long * const data = buf;
+ /* use vector optimized zero check if possible */
+ if (can_use_buffer_find_nonzero_offset(buf, len)) {
+ return buffer_find_nonzero_offset(buf, len) == len;
+ }
+
assert(len % (4 * sizeof(long)) == 0);
len /= sizeof(long);
--
1.7.9.5
