qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Alexander Monakov <amonakov@ispras.ru>
To: qemu-devel@nongnu.org
Cc: Mikhail Romanov <mmromanov@ispras.ru>,
	Richard Henderson <richard.henderson@linaro.org>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Alexander Monakov <amonakov@ispras.ru>
Subject: [PATCH v3 6/6] util/bufferiszero: improve scalar variant
Date: Tue,  6 Feb 2024 23:48:09 +0300	[thread overview]
Message-ID: <20240206204809.9859-7-amonakov@ispras.ru> (raw)
In-Reply-To: <20240206204809.9859-1-amonakov@ispras.ru>

Take into account that the inline wrapper ensures len >= 4.

Use __attribute__((may_alias)) for accesses via non-char pointers.

Avoid using out-of-bounds pointers in loop boundary conditions by
reformulating the 'for' loop as 'if (...) do { ... } while (...)'.

Signed-off-by: Alexander Monakov <amonakov@ispras.ru>
Signed-off-by: Mikhail Romanov <mmromanov@ispras.ru>
---
 util/bufferiszero.c | 30 +++++++++++-------------------
 1 file changed, 11 insertions(+), 19 deletions(-)

diff --git a/util/bufferiszero.c b/util/bufferiszero.c
index d752edd8cc..1f4cbfaea4 100644
--- a/util/bufferiszero.c
+++ b/util/bufferiszero.c
@@ -29,35 +29,27 @@
 bool
 buffer_is_zero_len_4_plus(const void *buf, size_t len)
 {
-    if (unlikely(len < 8)) {
-        /* For a very small buffer, simply accumulate all the bytes.  */
-        const unsigned char *p = buf;
-        const unsigned char *e = buf + len;
-        unsigned char t = 0;
-
-        do {
-            t |= *p++;
-        } while (p < e);
-
-        return t == 0;
+    if (unlikely(len <= 8)) {
+        /* Our caller ensures len >= 4.  */
+        return (ldl_he_p(buf) | ldl_he_p(buf + len - 4)) == 0;
     } else {
-        /* Otherwise, use the unaligned memory access functions to
-           handle the beginning and end of the buffer, with a couple
+        /* Use unaligned memory access functions to handle
+           the beginning and end of the buffer, with a couple
            of loops handling the middle aligned section.  */
-        uint64_t t = ldq_he_p(buf);
-        const uint64_t *p = (uint64_t *)(((uintptr_t)buf + 8) & -8);
-        const uint64_t *e = (uint64_t *)(((uintptr_t)buf + len) & -8);
+        uint64_t t = ldq_he_p(buf) | ldq_he_p(buf + len - 8);
+        typedef uint64_t uint64_a __attribute__((may_alias));
+        const uint64_a *p = (void *)(((uintptr_t)buf + 8) & -8);
+        const uint64_a *e = (void *)(((uintptr_t)buf + len - 1) & -8);
 
-        for (; p + 8 <= e; p += 8) {
+        if (e - p >= 8) do {
             if (t) {
                 return false;
             }
             t = p[0] | p[1] | p[2] | p[3] | p[4] | p[5] | p[6] | p[7];
-        }
+        } while ((p += 8) <= e - 8);
         while (p < e) {
             t |= *p++;
         }
-        t |= ldq_he_p(buf + len - 8);
 
         return t == 0;
     }
-- 
2.32.0



  parent reply	other threads:[~2024-02-06 20:50 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-02-06 20:48 [PATCH v3 0/6] Optimize buffer_is_zero Alexander Monakov
2024-02-06 20:48 ` [PATCH v3 1/6] util/bufferiszero: remove SSE4.1 variant Alexander Monakov
2024-02-06 22:24   ` Richard Henderson
2024-02-06 20:48 ` [PATCH v3 2/6] util/bufferiszero: introduce an inline wrapper Alexander Monakov
2024-02-06 22:44   ` Richard Henderson
2024-02-07  7:13     ` Alexander Monakov
2024-02-08 20:07       ` Richard Henderson
2024-02-06 20:48 ` [PATCH v3 3/6] util/bufferiszero: remove AVX512 variant Alexander Monakov
2024-02-06 22:28   ` Richard Henderson
2024-02-06 23:56   ` Elena Ufimtseva
2024-02-07  6:29     ` Alexander Monakov
2024-02-07 10:38       ` Joao Martins
2024-02-06 20:48 ` [PATCH v3 4/6] util/bufferiszero: remove useless prefetches Alexander Monakov
2024-02-06 22:29   ` Richard Henderson
2024-02-06 20:48 ` [PATCH v3 5/6] util/bufferiszero: optimize SSE2 and AVX2 variants Alexander Monakov
2024-02-06 23:10   ` Richard Henderson
2024-02-06 20:48 ` Alexander Monakov [this message]
2024-02-06 22:34   ` [PATCH v3 6/6] util/bufferiszero: improve scalar variant Richard Henderson
2024-02-06 22:46     ` Richard Henderson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240206204809.9859-7-amonakov@ispras.ru \
    --to=amonakov@ispras.ru \
    --cc=mmromanov@ispras.ru \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).