From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([208.118.235.92]:55379) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UKQgx-0005Dm-3l for qemu-devel@nongnu.org; Tue, 26 Mar 2013 06:01:26 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1UKQgq-0006PU-T3 for qemu-devel@nongnu.org; Tue, 26 Mar 2013 06:01:19 -0400 Received: from [2a02:248:0:30:223:aeff:fefe:7f1c] (port=48979 helo=dns.kamp-intra.net) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UKQgq-0006P4-NK for qemu-devel@nongnu.org; Tue, 26 Mar 2013 06:01:12 -0400 From: Peter Lieven Date: Tue, 26 Mar 2013 10:58:33 +0100 Message-Id: <1364291919-19563-5-git-send-email-pl@kamp.de> In-Reply-To: <1364291919-19563-1-git-send-email-pl@kamp.de> References: <1364291919-19563-1-git-send-email-pl@kamp.de> Subject: [Qemu-devel] [PATCHv5 04/10] buffer_is_zero: use vector optimizations if possible List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: quintela@redhat.com, Stefan Hajnoczi , Peter Lieven , Orit Wasserman , Paolo Bonzini performance gain on SSE2 is approx. 20-25%. altivec is not tested. performance for unsigned long arithmetic is unchanged. Signed-off-by: Peter Lieven Reviewed-by: Eric Blake Reviewed-by: Orit Wasserman --- util/cutils.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/util/cutils.c b/util/cutils.c index 0314a18..daf032a 100644 --- a/util/cutils.c +++ b/util/cutils.c @@ -215,6 +215,11 @@ 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