From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-5.3 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,MAILING_LIST_MULTI,NICE_REPLY_A,SPF_HELO_NONE, SPF_PASS,URIBL_BLOCKED,USER_AGENT_SANE_1 autolearn=no autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 97A7FC433ED for ; Mon, 17 May 2021 19:12:11 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 64A7E611BD for ; Mon, 17 May 2021 19:12:11 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231847AbhEQTN1 (ORCPT ); Mon, 17 May 2021 15:13:27 -0400 Received: from mx2.suse.de ([195.135.220.15]:48178 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231161AbhEQTN0 (ORCPT ); Mon, 17 May 2021 15:13:26 -0400 X-Virus-Scanned: by amavisd-new at test-mx.suse.de Received: from relay2.suse.de (unknown [195.135.221.27]) by mx2.suse.de (Postfix) with ESMTP id 95131B2A0; Mon, 17 May 2021 19:12:07 +0000 (UTC) To: Arnd Bergmann , Dave Airlie , Greg Kroah-Hartman , Maciej Kwapulinski , Jonathan Corbet , Derek Kiernan , Dragan Cvetic , Andy Shevchenko , Linux Kernel Mailing List , "open list:DOCUMENTATION" , DRI Development References: <20210513110040.2268-1-maciej.kwapulinski@linux.intel.com> From: Thomas Zimmermann Subject: Re: [PATCH v3 00/14] Driver of Intel(R) Gaussian & Neural Accelerator Message-ID: <503d101d-7273-757a-2809-e272db93c45d@suse.de> Date: Mon, 17 May 2021 21:12:03 +0200 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101 Thunderbird/78.10.0 MIME-Version: 1.0 In-Reply-To: Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="W9kAtv8EBXbI79dSBRez5c5Y3UeS7TbN9" Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --W9kAtv8EBXbI79dSBRez5c5Y3UeS7TbN9 Content-Type: multipart/mixed; boundary="0PmeoxnQa7yBXIDt9dyKmLw8B2Gp4ZCR0"; protected-headers="v1" From: Thomas Zimmermann To: Arnd Bergmann , Dave Airlie , Greg Kroah-Hartman , Maciej Kwapulinski , Jonathan Corbet , Derek Kiernan , Dragan Cvetic , Andy Shevchenko , Linux Kernel Mailing List , "open list:DOCUMENTATION" , DRI Development Message-ID: <503d101d-7273-757a-2809-e272db93c45d@suse.de> Subject: Re: [PATCH v3 00/14] Driver of Intel(R) Gaussian & Neural Accelerator References: <20210513110040.2268-1-maciej.kwapulinski@linux.intel.com> In-Reply-To: --0PmeoxnQa7yBXIDt9dyKmLw8B2Gp4ZCR0 Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: quoted-printable Hi Am 17.05.21 um 09:40 schrieb Daniel Vetter: > On Fri, May 14, 2021 at 11:00:38AM +0200, Arnd Bergmann wrote: >> On Fri, May 14, 2021 at 10:34 AM Greg Kroah-Hartman >> wrote: >>> On Thu, May 13, 2021 at 01:00:26PM +0200, Maciej Kwapulinski wrote: >>>> Dear kernel maintainers, >>>> >>>> This submission is a kernel driver to support Intel(R) Gaussian & Ne= ural >>>> Accelerator (Intel(R) GNA). Intel(R) GNA is a PCI-based neural co-pr= ocessor >>>> available on multiple Intel platforms. AI developers and users can o= ffload >>>> continuous inference workloads to an Intel(R) GNA device in order to=20 free >>>> processor resources and save power. Noise reduction and speech recog= nition >>>> are the examples of the workloads Intel(R) GNA deals with while its = usage >>>> is not limited to the two. >>> >>> How does this compare with the "nnpi" driver being proposed here: >>> https://lore.kernel.org/r/20210513085725.45528-1-guy.zadicar= io@intel.com >>> >>> Please work with those developers to share code and userspace api and= >>> tools. Having the community review two totally different apis and >>> drivers for the same type of functionality from the same company is >>> totally wasteful of our time and energy. >> >> Agreed, but I think we should go further than this and work towards a >> subsystem across companies for machine learning and neural networks >> accelerators for both inferencing and training. >=20 > We have, it's called drivers/gpu. Feel free to rename to drivers/xpu or= > think G as in General, not Graphisc. I hope this was a joke. Just some thoughts: AFAICT AI first came as an application of GPUs, but has now=20 evolved/specialized into something of its own. I can imagine sharing=20 some code among the various subsystems, say GEM/TTM internals for memory = management. Besides that there's probably little that can be shared in=20 the userspace interfaces. A GPU is device that puts an image onto the=20 screen and an AI accelerator isn't. Treating both as the same, even if=20 they share similar chip architectures, seems like a stretch. They might=20 evolve in different directions and fit less and less under the same=20 umbrella. And as Dave mentioned, these devices are hard to obtain. We don't really = know what we sign up for. Just my 2 cents. Best regards Thomas --=20 Thomas Zimmermann Graphics Driver Developer SUSE Software Solutions Germany GmbH Maxfeldstr. 5, 90409 N=C3=BCrnberg, Germany (HRB 36809, AG N=C3=BCrnberg) Gesch=C3=A4ftsf=C3=BChrer: Felix Imend=C3=B6rffer --0PmeoxnQa7yBXIDt9dyKmLw8B2Gp4ZCR0-- --W9kAtv8EBXbI79dSBRez5c5Y3UeS7TbN9 Content-Type: application/pgp-signature; name="OpenPGP_signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="OpenPGP_signature" -----BEGIN PGP SIGNATURE----- wsF5BAABCAAjFiEExndm/fpuMUdwYFFolh/E3EQov+AFAmCiwAMFAwAAAAAACgkQlh/E3EQov+DJ XhAAyCyCre9HcN6z8zECZZaTWBLe0cqcMokVsLXDTngNMFJGBTEoUFqYGtFrcCR+1SqbG6u4kECD m+oAp9Ew5nw97eMZIHvYaUuOd6Sv21n4gwMsBy6u6R2iLOJ3xVTdobCea6IgP3si53dM7MJeUhNA aunSycxlvyg3p5yNZzcZtkEDmP9FkT4Ynt+x2ddstBVSgq3vfKmKwq10yu97c+4DMP5dU1LT9aOR tKT+9NgcnxvAjDiVLwtuNEbbTWa5IilCcPMVijGQYkvlHqLwchi+7IY4N8v7SU3Tns+GR/VAKoqg 45mSUxUTHpbeO48VPHufqGA0uqaDaBSK1q76KrP2gLiKirO/FnMKj2jBTL6cI/tLblM5OxJtNeV1 8lXb/oZKQVjTCVxTUKS2/4RhjX/fXbwUNf8mgMJWLReLzv6kTTVvokhcMF1leu75JajowOWv0KgV Ht3NYy+CV18PdZ2KS/cAnteBdlf11W9ehk8hTMA9tpkrxlOI9zmuchwVEcwCygLJkziQFBSdkdOK HblrUo9iOtZukQTMrs/GeH0YmFlPEbMiGeuB/UTlMx1+hzBcXGk20GarhL2lxAhbfsecbETYmK0r 0pQA3bC+oKfnzBb7uDZFOAfzOgeDZVnBETUXHNzWOHxAI1hCGixpASbDOL5HzVfXCWud2/zSri68 aT0= =TrzX -----END PGP SIGNATURE----- --W9kAtv8EBXbI79dSBRez5c5Y3UeS7TbN9--