leezu opened a new issue #17886: Boolean tvm operators broken on gpu
URL: https://github.com/apache/incubator-mxnet/issues/17886
 
 
   ## Description
   For example, `less_scalar_gpufloat32_2bool_2` is missing causing mxnet to 
crash.
   Works fine for cpu.
   
   ### Error Message
   
   ```
   Traceback (most recent call last):
     File "/home/ubuntu/test.py", line 4, in <module>
       x[x < 2]
     File "/home/ubuntu/src/mxnet-master/python/mxnet/numpy/multiarray.py", 
line 729, in __getitem__
       return self._get_np_boolean_indexing(key_before_expaned)
     File "/home/ubuntu/src/mxnet-master/python/mxnet/numpy/multiarray.py", 
line 490, in _get_np_boolean_indexing
       after_mask = _reshape_view(_npi.boolean_mask(data, mask), -1, 
*remaining_shapes)
     File "<string>", line 53, in boolean_mask
     File "/home/ubuntu/src/mxnet-master/python/mxnet/_ctypes/ndarray.py", line 
82, in _imperative_invoke
       check_call(_LIB.MXImperativeInvokeEx(
     File "/home/ubuntu/src/mxnet-master/python/mxnet/base.py", line 246, in 
check_call
       raise get_last_ffi_error()
   mxnet.base.MXNetError: Traceback (most recent call last):
     File "../3rdparty/tvm/src/runtime/module.cc", line 123
     File "../3rdparty/tvm/src/runtime/library_module.cc", line 91
   TVMError: Check failed: ret == 0 (-1 vs. 0) : Check failed: f != nullptr: 
Cannot find function less_scalar_gpufloat32_2bool_2_kernel0 in the imported 
modules or global registry
   ```
   
   ## To Reproduce
   ### Steps to reproduce
   
   Compile MXNet with `USE_TVMOP=1`.
   
   Run 
   ```
   import mxnet as mx
   
   x = mx.np.array([[0, 1], [1, 1], [2, 2]], ctx=mx.gpu())
   idx = x < 2
   x[idx]
   ```

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to