From: PrasannaKumar Muralidharan Subject: Re: [PATCH v2 2/5] crypto: stm32 - Support for STM32 CRC32 crypto module Date: Fri, 24 Mar 2017 15:30:56 +0530 Message-ID: References: <1490109211-4869-1-git-send-email-fabien.dessenne@st.com> <1490109211-4869-3-git-send-email-fabien.dessenne@st.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: Mark Rutland , "devicetree@vger.kernel.org" , Alexandre TORGUE , Russell King , Rob Herring , "linux-crypto@vger.kernel.org" , Maxime Coquelin , Benjamin GAIGNARD , "David S . Miller" , "linux-arm-kernel@lists.infradead.org" , Herbert Xu To: Fabien DESSENNE Return-path: In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=m.gmane.org@lists.infradead.org List-Id: linux-crypto.vger.kernel.org On 24 March 2017 at 15:26, Fabien DESSENNE wrote: > On 24/03/17 05:28, PrasannaKumar Muralidharan wrote: >> On 21 March 2017 at 20:43, Fabien Dessenne wrote: >>> This module registers a CRC32 ("Ethernet") and a CRC32C (Castagnoli) >>> algorithm that make use of the STMicroelectronics STM32 crypto hardware. >>> >>> Theses algorithms are compatible with the little-endian generic ones. >>> Both algorithms use ~0 as default seed (key). >>> With CRC32C the output is xored with ~0. >>> >>> Using TCRYPT CRC32C speed test, this shows up to 900% speedup compared >>> to the crc32c-generic algorithm. >> Comparing with crc3c-generic alogrithm does not sound like a good >> metric for someone who has to decide between hw crypto or not. >> Wouldn't it be better if the comparison is between crc32 using NEON >> with hw crypto module? It will help in choosing between hw crypto or >> arch optimised crc routiene. > > The STM32 microcontrollers are based on ARM Cortex-M7 (or older core) > that do not have NEON support. I was not aware of the absence of NEON support. Sorry for the noise.