From: Huang Ying Subject: Re: Accelerate GCM with PCLMULQDQ-NI Date: Mon, 30 Mar 2009 09:36:35 +0800 Message-ID: <1238376995.6639.80.camel@yhuang-dev.sh.intel.com> References: <1237366332.24215.260.camel@yhuang-dev.sh.intel.com> <20090329074326.GB11735@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="=-ZT24eGYiBapoGWK5d4tS" Cc: Sebastian Andrzej Siewior , "linux-kernel@vger.kernel.org" , "linux-crypto@vger.kernel.org" To: Herbert Xu Return-path: In-Reply-To: <20090329074326.GB11735@gondor.apana.org.au> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-crypto.vger.kernel.org --=-ZT24eGYiBapoGWK5d4tS Content-Type: text/plain Content-Transfer-Encoding: quoted-printable On Sun, 2009-03-29 at 15:43 +0800, Herbert Xu wrote: > On Wed, Mar 18, 2009 at 04:52:12PM +0800, Huang Ying wrote: > > > > To accelerate GCM with it, I make the following design: > >=20 > > 1. Implement ghash as an ahash algorithm, Use ghash in gcm > > implementation. > > 2. Provide a new implementation of ghash with PCLMULQDQ-NI. > >=20 > > What do you think about that? >=20 > Sounds OK to me. I presume the choice of ahash instead of shash > is due to the use of XMM registers, just like AES? Yes, because PCLMULQDQ touches XMMs too. Just like AES, there is a raw shash: ghash-clmul and an ahash via cryptd(ghash-clmul). Best Regards, Huang Ying --=-ZT24eGYiBapoGWK5d4tS Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.9 (GNU/Linux) iEYEABECAAYFAknQIh8ACgkQKhFGF+eHlpjiyQCdGZnZKSWJiZpyQET0G2m66wvC UAsAnii91nPpLBW1pHWMKdt5aAIhMn0+ =PIwQ -----END PGP SIGNATURE----- --=-ZT24eGYiBapoGWK5d4tS--