Message-ID: <aea24370-2526-7f43-ca5f-55d1d8b8c4bb@loongson.cn>
Date:   Thu, 9 Feb 2023 09:16:09 +0800
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.6.0
Subject: Re: [PATCH] LoongArch: add checksum optimization for 64-bit system
To:     David Laight <David.Laight@ACULAB.COM>,
        'WANG Xuerui' <kernel@xen0n.name>,
        Huacai Chen <chenhuacai@kernel.org>
Cc:     Jiaxun Yang <jiaxun.yang@flygoat.com>,
        "loongarch@lists.linux.dev" <loongarch@lists.linux.dev>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
References: <20230207040148.1801169-1-maobibo@loongson.cn>
 <8fa91bca5e624861b190917933951c7e@AcuMS.aculab.com>
 <5b3c9b61-7fd5-f50c-32ba-e857090b71bc@xen0n.name>
 <7636a7bebfd44e378c5b16d6fd355232@AcuMS.aculab.com>
Content-Language: en-US
From:   maobibo <maobibo@loongson.cn>
In-Reply-To: <7636a7bebfd44e378c5b16d6fd355232@AcuMS.aculab.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Precedence: bulk


在 2023/2/8 22:19, David Laight 写道:
> From: WANG Xuerui
>> Sent: 08 February 2023 13:48
> ...
>> Yeah LoongArch can do rotates, and your suggestion can indeed reduce one
>> insn from every invocation of csum_fold.
>>
>>  From this:
>>
>> 000000000000096c <csum_fold>:
>>          sum += (sum >> 16) | (sum << 16);
>>   96c:   004cc08c        rotri.w         $t0, $a0, 0x10
>>   970:   00101184        add.w           $a0, $t0, $a0
>>          return ~(__force __sum16)(sum >> 16);
>>   974:   0044c084        srli.w          $a0, $a0, 0x10
>>   978:   00141004        nor             $a0, $zero, $a0
>> }
>>   97c:   006f8084        bstrpick.w      $a0, $a0, 0xf, 0x0
>>   980:   4c000020        jirl            $zero, $ra, 0
>>
>> To:
>>
>> 0000000000000984 <csum_fold2>:
>>          return (~sum - rol32(sum, 16)) >> 16;
>>   984:   0014100c        nor             $t0, $zero, $a0
>>          return (x << amt) | (x >> (32 - amt));
>>   988:   004cc084        rotri.w         $a0, $a0, 0x10
>>          return (~sum - rol32(sum, 16)) >> 16;
>>   98c:   00111184        sub.w           $a0, $t0, $a0
>> }
>>   990:   00df4084        bstrpick.d      $a0, $a0, 0x1f, 0x10
>>   994:   4c000020        jirl            $zero, $ra, 0
> 
> It is actually slightly better than that.
> In the csum_fold2 version the first two instructions
> are independent - so can execute in parallel on some cpu.
> 
> 	David
>

Thanks for the good suggestion.
Will send the second version soon.

regards
bibo,mao
> -
> Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
> Registration No: 1397386 (Wales)