Re: symbol catenation and montgomery

[phr-2000]

     Thanks.  That's interesting since the OpenSSL timing is about 1.5x
     faster than a 600 mhz Athlon that a friend of mine tested a few months
     ago.

   Perhaps he didn't use GMP 3.1?  We had the redc code in GMP 3.0, but
   the cutoff point between O(n^2) redc and (O(M(n)) division wasn't
   right.

No I mean OpenSSL vs. OpenSSL timings on 600 vs. 750 mhz versions of
the same CPU.  I don't think the OpenSSL x86 arithmetic code has
changed anytime recently.

Btw, you might like looking at some of Dan Bernstein's papers on
fast arithmetic, at http://cr.yp.to.