[Qemu-devel] [PATCH] is_not_zero() optimization in qemu-img

[Dmitry Konishchev <konishchev@gmail.com>]

Please sorry - I've sent the previous email via Thunderbird which promised that won't wrap the lines but it did. :(
Sending this via git send-email.

Signed-off-by: Dmitry Konishchev <konishchev@gmail.com>
---
 qemu-img.c |   29 ++++++++++++++++++++++++++---
 1 files changed, 26 insertions(+), 3 deletions(-)

diff --git a/qemu-img.c b/qemu-img.c
index e825123..c849c6f 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -496,14 +496,37 @@ static int img_commit(int argc, char **argv)
     return 0;
 }
 
+/*
+ * Checks whether the sector is not a zero sector.
+ *
+ * Attention! The len must be a multiple of 4 * sizeof(long) due to
+ * restriction of optimizations in this function.
+ */
 static int is_not_zero(const uint8_t *sector, int len)
 {
+    /*
+     * Use long as the biggest available internal data type that fits into the
+     * CPU register and unroll the loop to smooth out the effect of memory
+     * latency.
+     */
+
     int i;
-    len >>= 2;
-    for(i = 0;i < len; i++) {
-        if (((uint32_t *)sector)[i] != 0)
+    long d0, d1, d2, d3;
+    const long * const data = (const long *) sector;
+
+    len /= sizeof(long);
+
+    for(i = 0; i < len; i += 4) {
+        d0 = data[i + 0];
+        d1 = data[i + 1];
+        d2 = data[i + 2];
+        d3 = data[i + 3];
+
+        if (d0 || d1 || d2 || d3) {
             return 1;
+        }
     }
+
     return 0;
 }
 
-- 
1.7.4.1