Received-SPF: pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
User-Agent: Cyrus-JMAP/3.5.0-alpha0-4778-g14fba9972e-fm-20220217.001-g14fba997
Mime-Version: 1.0
Message-Id: <ba4b74eb-29b9-43b0-9e94-09b696f18961@www.fastmail.com>
In-Reply-To: <0a21fe4d-b135-3696-71f0-aa14ca715d51@intel.com>
References: <1611386920-28579-1-git-send-email-megha.dey@intel.com>
 <CALCETrU06cuvUF5NDSm8--dy3dOkxYQ88cGWaakOQUE4Vkz88w@mail.gmail.com>
 <3878af8d-ac1e-522a-7c9f-fda4a1f5b967@intel.com>
 <CALCETrUWgLwp6yfu9ODY1UYufHeAgsnOOCOAwXZQK6FJk_YdUA@mail.gmail.com>
 <e8ce1146-3952-6977-1d0e-a22758e58914@intel.com>
 <0a10e16b-df77-9a7f-6964-8dc3e114b30b@intel.com>
 <0a21fe4d-b135-3696-71f0-aa14ca715d51@intel.com>
Date:   Sat, 05 Mar 2022 10:37:56 -0800
From:   "Andy Lutomirski" <luto@kernel.org>
To:     "Dey, Megha" <megha.dey@intel.com>,
        "Dave Hansen" <dave.hansen@intel.com>,
        "Herbert Xu" <herbert@gondor.apana.org.au>
Cc:     "Tony Luck" <tony.luck@intel.com>,
        "Asit K Mallick" <asit.k.mallick@intel.com>,
        "H. Peter Anvin" <hpa@zytor.com>,
        "Linux Crypto Mailing List" <linux-crypto@vger.kernel.org>,
        "David S. Miller" <davem@davemloft.net>,
        "Shankar, Ravi V" <ravi.v.shankar@intel.com>,
        "Chen, Tim C" <tim.c.chen@intel.com>,
        "Kleen, Andi" <andi.kleen@intel.com>, greg.b.tucker@intel.com,
        rajendrakumar.chinnaiyan@intel.com, tomasz.kantecki@intel.com,
        ryan.d.saffores@intel.com, "Ira Weiny" <ira.weiny@intel.com>,
        "Eric Biggers" <ebiggers@kernel.org>,
        "Ard Biesheuvel" <ardb@kernel.org>,
        "the arch/x86 maintainers" <x86@kernel.org>,
        anirudh.venkataramanan@intel.com
Subject: Re: [RFC V2 0/5] Introduce AVX512 optimized crypto algorithms
Content-Type: text/plain
Precedence: bulk


On Thu, Feb 24, 2022, at 11:31 AM, Dey, Megha wrote:
> Hi all,
>
> On 1/31/2022 11:18 AM, Dave Hansen wrote:
>> On 1/31/22 10:43, Dey, Megha wrote:
>>> With this implementation, we see a 1.5X improvement on ICX/ICL for 16KB
>>> buffers compared to the existing kernel AES-GCM implementation that
>>> works on 128-bit XMM registers.
>> What is your best guess about how future-proof this implementation is?
>>
>> Will this be an ICL/ICX one-off?  Or, will implementations using 256-bit
>> YMM registers continue to enjoy a frequency advantage over the 512-bit
>> implementations for a long time?
>
> Dave,
>
> This would not be an ICL/ICX one off. For the foreseeable future, 
> AVX512VL YMM implementations will enjoy a frequency advantage over 
> AVX512L ZMM implementations.
>
> Although, over time, ZMM and YMM will converge when it comes to performance.
>
> Herbert/Andy,
>
> Could you please let us know if this approach is a viable one and would 
> be acceptable by the community?
>
> Optimizing crypto algorithms using AVX512VL instructions gives a 1.5X 
> performance improvement over existing AES-GCM algorithm in the 
> kernel(using XMM registers) with no frequency drop.

I'm assuming this would be enabled automatically without needing any special command line options.  If so, it seems reasonable to me.

--Andy