Author Topic: AES 256 FPGA core  (Read 1650 times)

0 Members and 1 Guest are viewing this topic.

Offline Guy ShemeshTopic starter

  • Contributor
  • Posts: 16
  • Country: il
AES 256 FPGA core
« on: December 29, 2020, 02:14:12 pm »
Hi

I need a recommendation free AES256 FPGA core - for a project involving software and hardware co-processing on a Xilinx Zynq ultrascale+ device.
no further requirements (i.e ECB mode is enough, without authentication as the rest is done in software).

Anyone who did it can recommend on a working and stable core ?

Thank you
Guy
ePiccolo Engineering
 

Offline rstofer

  • Super Contributor
  • ***
  • Posts: 9914
  • Country: us
Re: AES 256 FPGA core
« Reply #1 on: December 31, 2020, 01:29:20 am »
OpenCores.org has one under Project -> Crypto.  I don't know anything about it.
 
The following users thanked this post: Guy Shemesh

Offline dolbeau

  • Regular Contributor
  • *
  • Posts: 90
  • Country: fr
Re: AES 256 FPGA core
« Reply #2 on: December 31, 2020, 05:49:48 pm »
I'm using the one from https://github.com/secworks/aes for AES128, planning to add/move to AES256 (core does both, encrypt & decrypt). I'm instantiating the aes_core not the high-level aes. Works for me...
 
The following users thanked this post: Guy Shemesh

Offline Guy ShemeshTopic starter

  • Contributor
  • Posts: 16
  • Country: il
Re: AES 256 FPGA core
« Reply #3 on: January 25, 2021, 02:49:34 pm »
Thank you very much dolbeau for the recomendation,

I have used the Secworks and it's working great. Simple, working and easy to use.  :)

Guy
 

Offline dolbeau

  • Regular Contributor
  • *
  • Posts: 90
  • Country: fr
Re: AES 256 FPGA core
« Reply #4 on: January 25, 2021, 07:17:37 pm »
Thank you very much dolbeau for the recomendation,
I have used the Secworks and it's working great. Simple, working and easy to use.  :)

Excellent :-) BTW I since discovered an updated implementation of the same core - the 'aes-speed' from https://trac.cryptech.is/wiki/GitRepositories. It's larger but faster (cycles-wise), with the same interface. Depending on your requirements it might be an option.

They also have a bunch of FPGA-proven implementations for other algorithms.
 
The following users thanked this post: Guy Shemesh

Offline Guy ShemeshTopic starter

  • Contributor
  • Posts: 16
  • Country: il
Re: AES 256 FPGA core
« Reply #5 on: February 09, 2021, 05:24:33 pm »
Wow!

Sorry only now I see this, it looks amazing!

Indeed the other AES took 72 cycles/block, now I see it's down to 20 cycles/block !

I had already finished my project for this so I could not test it. And regarding the relatively long encryption/decryption time, I hid it -:) We also have a software SHA256 which takes quite alot from the processor, so I let these processes work in parallel (PL-AES / SW-SHA).

Thanks dolbeau, I'll keep this link as I see there are many other interesting implementations there

Best Regards and keep safe
Guy

 


Share me

Digg  Facebook  SlashDot  Delicious  Technorati  Twitter  Google  Yahoo
Smf