Auto_scheduler error

Environment: OS win 10 x64, tvm 0.8, python 3.8.10

While running Optimizing Operators with Auto-scheduling, the following error raises:

==================================================
No: 5   GFLOPS: 0.00 / 0.00     results: MeasureResult(error_type:RuntimeDeviceError, error_msg:Traceback (most recent call last):
  File "E:\Work\code\tvm\python\tvm\auto_scheduler\utils.py", line 295, in call_func_with_timeout
    res = worker.recv()
  File "E:\Work\code\tvm\python\tvm\contrib\popen_pool.py", line 271, in recv
    raise value
Permi
...
nsafe
    onerror(os.unlink, fullname, sys.exc_info())
  File "D:\Work\python\lib\shutil.py", line 616, in _rmtree_unsafe
    os.unlink(fullname)
PermissionError: [WinError 5] 鎷掔粷璁块棶銆? 'C:\\Users\\shiy10\\AppData\\Local\\Temp\\tmp8m5zn9cb\\tmp_func.tar.so'

, all_cost:10.34, Tstamp:1639403202.14)
==================================================
Placeholder: A, B
parallel i.0@j.0@ (0,64)
  matmul.local auto_unroll: 64
  for i_c.1 (0,8)
    for k.0 (0,1024)
      for j_c.2 (0,2)
        for i_c.3 (0,32)
          for j_c.3 (0,32)
            matmul.local = ...
  for i.1 (0,256)
    for j.1 (0,64)
      matmul = ...

Time elapsed for measurement: 6.26 s
----------------------------------------------------------------------
------------------------------  [ Done ]
----------------------------------------------------------------------
No valid state found in this search round. Check if it has traversed all of the search space.
Traceback (most recent call last):
  File ".\auto_gemm_relay.py", line 52, in <module>
    sch, args = task.apply_best(log_file)
  File "E:\Work\code\tvm\python\tvm\auto_scheduler\search_task.py", line 521, in apply_best
    raise RuntimeError(
RuntimeError: Cannot find any valid schedule for ["matmul", 1024, 1024, 1024, "float32"] in file matmul.json

Then I try run this script as administrator, but the error still exists. Any suggestions how to solve this?

Did you have the xgboost module installed?