From: Herbert Xu Subject: Re: {twofish,aes}-{x86_64,i586} versus C implementations Date: Mon, 20 Aug 2007 09:01:57 +0800 Message-ID: References: <200708200234.25620.ak@suse.de> Cc: linux-crypto@vger.kernel.org To: ak@suse.de (Andi Kleen) Return-path: Received: from rhun.apana.org.au ([64.62.148.172]:3050 "EHLO arnor.apana.org.au" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1750941AbXHTBPU (ORCPT ); Sun, 19 Aug 2007 21:15:20 -0400 In-Reply-To: <200708200234.25620.ak@suse.de> Sender: linux-crypto-owner@vger.kernel.org List-Id: linux-crypto.vger.kernel.org Andi Kleen wrote: > Hallo, > > Currently there are two twofish and two aes implementions on x86. > Worse when both are enabled as modules a modprobe aes > will get the C version which seems to be slower on K8 > and about the same speed on Core2 on my tests. Hi Andi: Are you sure you get the C version when both are built-in or loaded as modules? If so then we have a bug in the priority code. If you only have the C version loaded then that is understandable since the module loading code doesn't know about the other one. > Is there a specific reason why anybody would prefer the C functions > over the assembler functions? We don't, but the system is meant to allow multiple implementations to coexist and picking the best one at run-time. Cheers, -- Visit Openswan at http://www.openswan.org/ Email: Herbert Xu ~{PmV>HI~} Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt