1. 20 3月, 2018 1 次提交
  2. 19 3月, 2018 1 次提交
  3. 09 3月, 2018 1 次提交
  4. 19 2月, 2018 1 次提交
  5. 13 2月, 2018 1 次提交
  6. 12 2月, 2018 1 次提交
  7. 22 12月, 2017 1 次提交
  8. 13 11月, 2017 1 次提交
  9. 12 11月, 2017 1 次提交
  10. 30 10月, 2017 1 次提交
  11. 18 10月, 2017 1 次提交
  12. 13 10月, 2017 1 次提交
  13. 10 9月, 2017 1 次提交
    • A
      sha/asm/keccak1600-armv8.pl: fix return value buglet and ... · 236dd463
      Andy Polyakov 提交于
      ... script data load.
      
      On related note an attempt was made to merge rotations with logical
      operations. I mean as we know, ARM ISA has merged rotate-n-logical
      instructions which can be used here. And they were used to improve
      keccak1600-armv4 performance. But not here. Even though this approach
      resulted in improvement on Cortex-A53 proportional to reduction of
      amount of instructions, ~8%, it didn't exactly worked out on
      non-Cortex cores. Presumably because they break merged instructions
      to separate μ-ops, which results in higher *operations* count. X-Gene
      and Denver went ~20% slower and Apple A7 - 40%. The optimization was
      therefore dismissed.
      Reviewed-by: NRich Salz <rsalz@openssl.org>
      236dd463
  14. 17 8月, 2017 1 次提交
  15. 12 8月, 2017 1 次提交
  16. 03 8月, 2017 1 次提交
  17. 31 7月, 2017 1 次提交
  18. 25 7月, 2017 1 次提交
  19. 21 7月, 2017 2 次提交
  20. 16 7月, 2017 2 次提交
  21. 10 7月, 2017 2 次提交
  22. 07 7月, 2017 1 次提交
  23. 04 7月, 2017 3 次提交
  24. 30 6月, 2017 5 次提交
  25. 24 6月, 2017 2 次提交
  26. 21 6月, 2017 3 次提交
  27. 16 6月, 2017 1 次提交
  28. 09 6月, 2017 1 次提交