pycuda_example.py 文件源码

def perform(self, node, inputs, out):
        # TODO support broadcast!
        # TODO assert all input have the same shape
        z, = out
        if (z[0] is None or
                z[0].shape != inputs[0].shape or
                not z[0].is_c_contiguous()):
            z[0] = theano.sandbox.cuda.CudaNdarray.zeros(inputs[0].shape)
        if inputs[0].shape != inputs[1].shape:
            raise TypeError("PycudaElemwiseSourceModuleOp:"
                            " inputs don't have the same shape!")

        if inputs[0].size > 512:
            grid = (int(numpy.ceil(inputs[0].size / 512.)), 1)
            block = (512, 1, 1)
        else:
            grid = (1, 1)
            block = (inputs[0].shape[0], inputs[0].shape[1], 1)
        self.pycuda_fct(inputs[0], inputs[1], z[0],
                        numpy.intc(inputs[1].size), block=block, grid=grid)