README 780 B

12345678910111213141516
  1. RIPEMD-160
  2. http://www.esat.kuleuven.ac.be/~bosselae/ripemd160.html
  3. This is my implementation of RIPEMD-160. The pentium assember is a little
  4. off the pace since I only get 1050 cycles, while the best is 1013.
  5. I have a few ideas for how to get another 20 or so cycles, but at
  6. this point I will not bother right now. I believe the trick will be
  7. to remove my 'copy X array onto stack' until inside the RIP1() finctions the
  8. first time round. To do this I need another register and will only have one
  9. temporary one. A bit tricky.... I can also cleanup the saving of the 5 words
  10. after the first half of the calculation. I should read the origional
  11. value, add then write. Currently I just save the new and read the origioal.
  12. I then read both at the end. Bad.
  13. eric (20-Jan-1998)