netdev
[Top] [All Lists]

Re: Asynchronous crypto layer.

To: Evgeniy Polyakov <johnpol@xxxxxxxxxxx>
Subject: Re: Asynchronous crypto layer.
From: Eugene Surovegin <ebs@xxxxxxxxxxx>
Date: Sat, 30 Oct 2004 13:35:50 -0700
Cc: hadi@xxxxxxxxxx, netdev@xxxxxxxxxxx, cryptoapi@xxxxxxxxxxxxxx
In-reply-to: <20041029180652.113f0f6e@zanzibar.2ka.mipt.ru>
Mail-followup-to: Evgeniy Polyakov <johnpol@xxxxxxxxxxx>, hadi@xxxxxxxxxx, netdev@xxxxxxxxxxx, cryptoapi@xxxxxxxxxxxxxx
References: <1099030958.4944.148.camel@uganda> <1099053738.1024.104.camel@jzny.localdomain> <20041029180652.113f0f6e@zanzibar.2ka.mipt.ru>
Sender: netdev-bounce@xxxxxxxxxxx
User-agent: Mutt/1.5.5.1i
On Fri, Oct 29, 2004 at 06:06:52PM +0400, Evgeniy Polyakov wrote:
> If we have a hardware accelerator chip, than we _already_ have improvements 
> with even the worst async crypto layer, since software and hardware 
> will work in parrallel.

This is not true. 

For example, if chip request setup and PCI transfer takes more than 
just using sw implementation. This is reality for AES and short 
packets.

--
Eugene

<Prev in Thread] Current Thread [Next in Thread>