Abstract: The present disclosure discloses a hundred-kilowatts-level monolithic fiber laser based on auxiliary lasers and hybrid cladding pumping scheme. Multi-wavelength auxiliary lasers and a signal laser are simultaneously coupled into a core of a gain fiber, and the gain fiber provides gains for the auxiliary lasers and the signal laser under multi-wavelength cladding pumping. The multi-wavelength auxiliary lasers and the signal laser are sequentially amplified under the action of gain competition, and the amplification of signal laser is suppressed at a front segment of the gain fiber, while the signal laser is effectively amplified at a rear segment of the gain fiber after the multi-wavelength auxiliary lasers are reabsorbed; quantum defects generated are reduced, and uniformly distributed thermal loads will be achieved, and the bearing capacity of laser power is improved, thereby further achieving inhibition on the transverse mode instability effect.

Abstract: There is provided methods and devices for computing a tile size for software optimization. A method includes receiving, by a computing device, information indicative of one or more of a set of loop bounds and a set of data shapes; processing, by the computing device, the information to determine a computation configuration based on the obtained information, the computation configuration implementable by a compiler, said processing including evaluating at least the computation configuration based on a build cost model, the build cost model representative of a data transfer cost and a data efficiency of the computation configuration; and transmitting, by the computing device, instructions directing the compiler to implement the computation configuration.

Abstract: There is provided methods and devices for computing a tile size for software optimization. A method includes receiving, by a computing device, information indicative of one or more of a set of loop bounds and a set of data shapes; processing, by the computing device, the information to determine a computation configuration based on the obtained information, the computation configuration implementable by a compiler, said processing including evaluating at least the computation configuration based on a build cost model, the build cost model representative of a data transfer cost and a data efficiency of the computation configuration; and transmitting, by the computing device, instructions directing the compiler to implement the computation configuration.

Abstract: A computer implemented method, a system and a non-transitory storage medium are provided for efficiently processing probability distributions in a neural network using a probabilistic programming language. Probability distribution data structures are provided, as well as corresponding distribution-APIs. Each probability distribution data structure comprises an identification of a distribution type and a list of parameters representative of said distribution type. The distribution data structures correspond to parametric representations of the probability distributions. The distribution data structures are inputted as distribution tensors into the layers, processed within the layer and outputted as modified tensors to downstream layers of the neural network. If needed, distribution class objects can be assembled and dissembled within the layers, but distribution tensors are still inputted or outputted by the layers, thereby limiting dataflow in between the layers of the neural network.