[Cryptech Tech] First hash via EIM

Joachim Strömbergson joachim at secworks.se
Fri Feb 6 06:21:55 UTC 2015


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

Aloha!

Paul Selkirk wrote:
> The one strange thing I found (which you can see in core_selector.v)
> is that I wasn't able to use (sys_eim_wr|sys_eim_rd) for cs, but had
> to rely solely on sys_eim_addr. I noticed that Joachim basically did
> the same thing in his earlier version. I haven't looked to see if the
> timing is different for the rd/wr controls vs the address. Maybe
> Pavel can shed some light on this?

having separate flags for read and write is excessive unless one wants
to do them both at the same time. Right now I don't see that we have any
timing issues with the mux logic.

One thing we need to consider is how we handle the availabe address
space. Most cores have an 8-bit address space. With 14-bit addresses
going in it gives us room for 2**6=64 cores. But the TRNHG for example
allocates 12 bits of addresses. And the modexp core (for RSA, D-H etc)
requires something like 12 bits too.

Also, if we want to not redo SW mapping we should probably decide on at
least a provisional FPGA address map, where the cores will be, about
now. There will probably be things that we want to redo later on, but a
first attempt now would be good.

- -- 
Med vänlig hälsning, Yours

Joachim Strömbergson - Alltid i harmonisk svängning.
========================================================================
 Joachim Strömbergson          Secworks AB          joachim at secworks.se
========================================================================
-----BEGIN PGP SIGNATURE-----
Version: GnuPG/MacGPG2 v2
Comment: GPGTools - http://gpgtools.org
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/
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=WCmf
-----END PGP SIGNATURE-----


More information about the Tech mailing list