[Cryptech Tech] Happier RSA timing numbers

Joachim Strömbergson joachim.strombergson at assured.se
Tue May 22 11:41:18 UTC 2018


-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA256

Aloha!

Rob Austein wrote:
> On Mon, 21 May 2018 13:14:04 -0400, Joachim Strömbergson wrote:
>> There is now a new AES core in the Cryptech repo: aes_speed.
> 
> Thanks!  Will profile if it gets that far (first attempt to
> synthesis the combined bitstream failed, don't know why yet).

The aes_speed core has now been optimized to take one cycle/round for
encipher and decipher operations. I have implemented it in Xilinx ISE
for Artix7 several times and it looks good.  Do you know what caused the
synthesis failed?

The next two possible things to change to optimize the core are to:

1. Optimize the key expansion. But unless you change keys often, this
will not add very much.

2. Pipelining the core. This will increase throughput, but will (I'm
sure) increase the size. Performance for a given single block will of
course not be better.

Since you seemed to use multiple AES cores that basically provides the
same performance increase as (2).

So, right now I don't see any major additional changes to the aes core
itself. Lets get new profile results and then see what we need to
improve. We still haven't increased the core clock speed to 100 MHz
which should increase performance too.

- -- 
Med vänlig hälsning, Yours

Joachim Strömbergson - Assured AB
========================================================================

-----BEGIN PGP SIGNATURE-----
Comment: GPGTools - http://gpgtools.org
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/
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=tze2
-----END PGP SIGNATURE-----


More information about the Tech mailing list