On Mon, Mar 25, 2019 at 09:10:08AM +0000, Pascal Van Leeuwen wrote: > As someone who has been working on crypto acceleration hardware for the better > part of the past 20 years, I feel compelled to respond to this, in defence of > the crypto API (which we're really happy with ...). Thanks for joining in. > We have done plenty of measurements, on both power and performance, to prove > you wrong there. Typically our HW needs *at least* a full order of a magnitude > less power to do the actual work. The CPU load for handing the interrupts etc. > tends to be around 20%. So assuming the CPU goes to sleep for the other 80% > of the time, the combined solution would need about 1/3rd of the power of a > CPU only solution. It's one of our biggest selling points. I actually have the kind of (relatively) low-power system with your crypto accelerator IP. But it doesn't matter how great performance or energy saving I would get from using crypto offloading. I will continue to use CPU only solution for the foreseeable future. Because of one tiny problem: The firmware files for eip197(?) crypto accelerator are secrets we are not allowed download anywhere from. > Pascal van Leeuwen, > Silicon IP Architect @ Inside Secure Riku
|