There's no real knowledge of the cacheline size,
just prefetching one loop ahead.
Signed-off-by: Richard Henderson <r...@twiddle.net>
---
util/cutils.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/util/cutils.c b/util/cutils.c
index 4d2edd6..0f1ce1d 100644
--- a/util/cutils.c
+++ b/util/cutils.c
@@ -173,6 +173,8 @@ NAME(const void *buf, size_t len)
\
do { \
const VECTYPE *p = buf; \
VECTYPE t; \
+ __builtin_prefetch(buf + SIZE); \
+ barrier(); \
if (SIZE == sizeof(VECTYPE) * 4) { \
t = (p[0] | p[1]) | (p[2] | p[3]); \
} else if (SIZE == sizeof(VECTYPE) * 8) { \
@@ -376,6 +378,9 @@ bool buffer_is_zero(const void *buf, size_t len)
return true;
}
+ /* Fetch the beginning of the buffer while we select the accelerator. */
+ __builtin_prefetch(buf);
+
/* Use an optimized zero check if possible. Note that this also
includes a check for an unrolled loop over longs, as well as
the unsized, unaligned fallback to buffer_zero_base. */
--
2.7.4
