Padlock accelerated SHA on Via C7

2009-04-14 Thread John Arnold
Hi All, Has anybody been able to get Padlock accelerated SHA1 working on a C7 or is this not currently possible? The CPU has the capability: OpenBSD 4.4 (GENERIC) #1021: Tue Aug 12 17:16:55 MDT 2008 dera...@i386.openbsd.org:/usr/src/sys/arch/i386/compile/GENERIC cpu0: VIA C7 Processor 1800MHz

Re: Padlock accelerated SHA on Via C7

2009-04-15 Thread John Arnold
> It isn't worth using it. The overhead is too high. > > OK, thanks for the response. That being the case, can anybody give me any advice on what hardware I would need to achieve gigabit VPN throughput (aes/3des & md5/sha1) with ipsec?

Re: Padlock accelerated SHA on Via C7

2009-04-16 Thread John Arnold
> Specifically: Via botched the implementation - their instruction set > does not allow the data to be hashed to be fed in multiple chunks, which > is how most applications work. > > There are ways around this but they are too ugly to mention. > > -d > > OK that makes sense! Thanks to everyo

Hardware recommendations for gigabit throughput ipsec

2009-04-16 Thread John Arnold
Hi all, I'm looking for any advice on what hardware would be suitable to achieve a gigabit capable point to point ipsec vpn (using aes/3des & sha1/md5). Has anybody done this? Many thanks!

Re: Hardware recommendations for gigabit throughput ipsec

2009-04-28 Thread John Arnold
> They all did 60+ MB/s, meaning I got at least 60% out of the gig links, > without resorting to jumbo frames, creative recv/sendspace sysctls or > anything, and also I did generate and sink the traffic on the end nodes, > so that also "adds" to the load for them. > > Given that they costed som

Broadcom 5862 support

2009-05-11 Thread John Arnold
Hi All, I have a Silicom PESB62 card (based on Broadcom 5862 chip). www.openbsd.org/crypto.html says: "Support for the BCM5825, BCM5860, BCM5861, and BCM5862 including support for AES with the BCM5823 or newer was added before 4.5." However it doesnt seem to be recognised properly: vendor "Br