mindspore.ops.ms_kernel
- mindspore.ops.ms_kernel(fn=None, reg_info=None, compile_attrs=None)[source]
The decorator of the Hybrid DSL function for the Custom Op. When a function written by the Hybrid DSL is decorated by ms_kernel, it can be run as a usual Python function. Also, this function can be used in the api Custom and to create a Custom op, with func_type “hybrid” or “pyfunc”. Creating a custom op with mode “hybrid” by the Hybrid DSL function will enjoy the automatic dtype/shape infer for free.
- Parameters
- Returns
Function, if fn is not None, returns a callable function that will execute the Hybrid DSL function; If fn is None, returns a decorator and when this decorator invokes with a single fn argument, the callable function is equal to the case when fn is not None.
- Supported Platforms:
Ascend
GPU
CPU
Examples
>>> import numpy as np >>> from mindspore import ops, Tensor >>> from mindspore.ops import ms_kernel, DataType, CustomRegOp ... >>> # Create a dict for the compile flags. >>> attrs = { ... "test1": True, ... "test2": "good", ... "test3": 12, ... } >>> # Create the reg info json string. >>> op_gpu_info = CustomRegOp() \ ... .input(0, "a") \ ... .input(0, "b") \ ... .output(0, "y") \ ... .dtype_format(DataType.F32_None, DataType.F32_None, DataType.F32_None) \ ... .target("GPU") \ ... .get_op_info() >>> >>> # Create inputs for the custom op. >>> input_x = np.ones([4, 4]).astype(np.float32) >>> input_y = np.ones([4, 4]).astype(np.float32) ... >>> # Write a Hybrid DSL function through the decorator @ms_kernel. >>> # We can also pass the compile attrs and the reg info through the decorator. >>> @ms_kernel(reg_info=op_gpu_info, compile_attrs=attrs) ... def outer_product(a, b): ... c = output_tensor(a.shape, a.dtype) ... ... with block_realize(c): ... for i0 in range(a.shape[0]): ... for i1 in range(b.shape[1]): ... c[i0, i1] = 0.0 ... for i2 in range(a.shape[1]): ... c[i0, i1] = c[i0, i1] + (a[i0, i2] * b[i2, i1]) ... return c ... >>> # We can use the function directly as a python function. >>> # In this case, the inputs should be numpy arrays. >>> result = outer_product(input_x, input_y) ... >>> # Create a custom op with mode "hybrid" (default value) by the Hybrid DSL function. >>> # In this case, we will enjoy the automatic dtype/shape infer for free. >>> # The inputs should be mindspore tensors. >>> test_op_hybrid = ops.Custom(outer_product) >>> output = test_op_hybrid(Tensor(input_x), Tensor(input_y))