From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <v.shpilevoy@tarantool.org>
Received: from smtp32.i.mail.ru (smtp32.i.mail.ru [94.100.177.92])
 (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits))
 (No client certificate requested)
 by dev.tarantool.org (Postfix) with ESMTPS id 5E03F469710
 for <tarantool-patches@dev.tarantool.org>;
 Tue,  9 Jun 2020 01:33:29 +0300 (MSK)
From: Vladislav Shpilevoy <v.shpilevoy@tarantool.org>
References: <cover.1590622225.git.v.shpilevoy@tarantool.org>
 <c6188bdc4734e30ac313f584e28f56cf2bb07875.1590622225.git.v.shpilevoy@tarantool.org>
 <048601d6352c$3cdb81a0$b69284e0$@tarantool.org>
 <05c14f7d-6f18-05ba-19ad-b5aa4dc91d17@tarantool.org>
Message-ID: <c1c2049e-43a7-290b-052e-8d24fb7764e6@tarantool.org>
Date: Tue, 9 Jun 2020 00:33:26 +0200
MIME-Version: 1.0
In-Reply-To: <05c14f7d-6f18-05ba-19ad-b5aa4dc91d17@tarantool.org>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Subject: Re: [Tarantool-patches] [PATCH v2 04/10] crc32: align memory access
List-Id: Tarantool development patches <tarantool-patches.dev.tarantool.org>
List-Unsubscribe: <https://lists.tarantool.org/mailman/options/tarantool-patches>, 
 <mailto:tarantool-patches-request@dev.tarantool.org?subject=unsubscribe>
List-Archive: <https://lists.tarantool.org/pipermail/tarantool-patches/>
List-Post: <mailto:tarantool-patches@dev.tarantool.org>
List-Help: <mailto:tarantool-patches-request@dev.tarantool.org?subject=help>
List-Subscribe: <https://lists.tarantool.org/mailman/listinfo/tarantool-patches>, 
 <mailto:tarantool-patches-request@dev.tarantool.org?subject=subscribe>
To: Timur Safin <tsafin@tarantool.org>, tarantool-patches@dev.tarantool.org, alyapunov@tarantool.org, korablev@tarantool.org

> diff --git a/src/cpu_feature.c b/src/cpu_feature.c
> index 9bf6223de..7b284fa98 100644
> --- a/src/cpu_feature.c
> +++ b/src/cpu_feature.c
> @@ -69,10 +69,8 @@ crc32c_hw_byte(uint32_t crc, char const *data, unsigned int length)
>  uint32_t
>  crc32c_hw(uint32_t crc, const char *buf, unsigned int len)
>  {
> -	const int align = alignof(unsigned long);
> -	unsigned long addr = (unsigned long)buf;
> -	unsigned int not_aligned_prefix =
> -		((addr - 1 + align) & ~(align - 1)) - addr;
> +	const unsigned int align = alignof(unsigned long);
> +	unsigned int not_aligned_prefix = align - (unsigned long)buf % align;

When the address is aligned, not_aligned_prefix becomes = align.
For 8 byte word it means we will do 8 operations instead of 1.

I fixed it this way:

====================
diff --git a/src/cpu_feature.c b/src/cpu_feature.c
index 7b284fa98..856f054c7 100644
--- a/src/cpu_feature.c
+++ b/src/cpu_feature.c
@@ -70,7 +70,8 @@ uint32_t
 crc32c_hw(uint32_t crc, const char *buf, unsigned int len)
 {
 	const unsigned int align = alignof(unsigned long);
-	unsigned int not_aligned_prefix = align - (unsigned long)buf % align;
+	unsigned int not_aligned_prefix =
+		(align - (unsigned long)buf % align) % align;
 	/*
 	 * Calculate CRC32 for the prefix byte-by-byte so as to
 	 * then use aligned words to calculate the rest. This is

====================
This is fast, because % align is transformed into & (align - 1)
in the assembly.