From: Herbert Xu Subject: Re: [PATCH] crypto: serpent - add x86_64/avx assembler implementation Date: Thu, 31 May 2012 07:44:48 +1000 Message-ID: <20120530214448.GA15031@gondor.apana.org.au> References: <20120527145112.GF17705@kronos.redsun> <20120530103025.19252e1urui8sfb4@www.81.fi> <20120530113235.GO17705@kronos.redsun> <20120530153949.GS27374@one.firstfloor.org> <20120530212911.GA14884@gondor.apana.org.au> <20120530214006.GZ27374@one.firstfloor.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Johannes Goetzfried , Jussi Kivilinna , linux-kernel@vger.kernel.org, linux-crypto@vger.kernel.org, Tilo =?iso-8859-1?Q?M=FCller?= To: Andi Kleen Return-path: Received: from sting.hengli.com.au ([178.18.18.71]:42549 "EHLO fornost.hengli.com.au" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1756109Ab2E3Vox (ORCPT ); Wed, 30 May 2012 17:44:53 -0400 Content-Disposition: inline In-Reply-To: <20120530214006.GZ27374@one.firstfloor.org> Sender: linux-crypto-owner@vger.kernel.org List-ID: On Wed, May 30, 2012 at 11:40:06PM +0200, Andi Kleen wrote: > > > What we could do is to use the cpuid-based probing when an algorithm > > is needed to selectively load the relevant implementations instead > > of all of them. However, for most algorithms it won't make that > > big a difference since all the available ones will be loaded anyway. > > Yes cpuid probing does that. I was under the impression that using cpuid meant that the algorithm would be loaded regardless of whether it has been requested, as long as the cpuid matches. If that's not the case then there is certainly no reason to not use cpuid-based loading. Thanks, -- Email: Herbert Xu Home Page: http://gondor.apana.org.au/~herbert/ PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt