Re: Tiny table AES implementation

karl malbrain wrote:
Right. On Intel machines loads that are back-to-back to the same bank
stall one cycle. Your aes encryption code loads a dword from TE0 and a
byte from s1 back-to-back.

On x86-64 the s1-4 and t1-4 variables are mapped to registers :-)

The only stack hits are the round counter I think. The rest of the
memory hits are key and sboxes.

We have a linux box running here that I would like to test on. Can you
post your rd_clock version for linux?? Thanks, karl m

As I posted in another thread it's the rdtsc() from LTC [which supports
a variety of platforms btw].

As for a "Linux box" if you wanted one you could have just asked me. I
do happen to have one for just this sort of research sitting around.
^_^ grin. [As I've stated before this offer is open to anyone doing
research within reason].

Tom

.