1. 05 11月, 2020 1 次提交
  2. 28 9月, 2020 1 次提交
  3. 27 9月, 2020 1 次提交
  4. 25 9月, 2020 1 次提交
  5. 18 9月, 2020 2 次提交
  6. 17 9月, 2020 1 次提交
  7. 14 9月, 2020 1 次提交
  8. 12 9月, 2020 1 次提交
  9. 10 9月, 2020 1 次提交
  10. 30 8月, 2020 1 次提交
  11. 29 8月, 2020 1 次提交
  12. 28 8月, 2020 1 次提交
  13. 21 8月, 2020 2 次提交
  14. 19 8月, 2020 2 次提交
  15. 17 8月, 2020 2 次提交
  16. 16 8月, 2020 2 次提交
  17. 13 8月, 2020 1 次提交
    • A
      XSSimTop: for normal memory access, we should use FakeTLLLC. · 577a2028
      Allen 提交于
      **NaiveTLToAXI4 has not been finished yet**.
      None of them fully support tilelink.
      FakeTLLLC supports:
      * AcquireBlock on channel A for permission acquire
      * ReleaseData on channel C for dcache eviction and writeback
      
      It's supposed to work with L1 dcache.
      Now, we still don't have a fully functional TL to AXI converter,
      starving for diplomacy!!!
      577a2028
  18. 11 8月, 2020 2 次提交
  19. 10 8月, 2020 1 次提交
  20. 05 8月, 2020 1 次提交
  21. 04 8月, 2020 1 次提交
  22. 02 8月, 2020 4 次提交
  23. 14 7月, 2020 2 次提交
  24. 13 7月, 2020 2 次提交
    • L
      e90f638a
    • Z
      xiangshan,utils,LogUtils: optimize wires · f96a1430
      Zihao Yu 提交于
      * Remove assert(), since they can be done at cpp files if needed
      * Calculate `(GTimer() >= disp_begin) && (GTimer() <= disp_end)` at the
        top level module only once, and wire such bool signal to where XSLog()
        is called. This can reduce the number of instances of counter created
        while GTimer() is callled.
      * Remove xsLogLevel. It seems meaningless, since we either need all logs
        for debugging, or no logs for running tests only.
      * With the above optimizion, running microbench with test input spends
        120s on 9900k with log completely disabled (comment out the log code),
        but only spends 147s on 9900k with log enabled.
      f96a1430
  25. 11 7月, 2020 1 次提交
  26. 09 7月, 2020 1 次提交
  27. 29 6月, 2020 1 次提交
  28. 27 6月, 2020 1 次提交
  29. 25 6月, 2020 1 次提交