公开(公告)号：US20210256348A1

公开(公告)日：2021-08-19

申请号：US17306171

申请日：2021-05-03

Applicant: NVIDIA Corporation

Inventor： Szymon Migacz ,  Hao Wu ,  Dilip Sequeira ,  Ujval Kapasi ,  Maxim Milakov ,  Slawomir Kierat ,  Zacky Zhou ,  Yilin Zhang ,  Alex Fit-Florea

IPC: G06N3/04 ,  G06N3/08

Abstract: Aspects of the present invention are directed to computer-implemented techniques for performing data compression and conversion between data formats of varying degrees of precision, and more particularly for improving the inferencing (application) of artificial neural networks using a reduced precision (e.g., INT8) data format. Embodiments of the present invention generate candidate conversions of data output, then employ a relative measure of quality to identify the candidate conversion with the greatest accuracy (i.e., least divergence from the original higher precision values). The representation can be then be used during inference to perform computations on the resulting output data.

公开(公告)号：US20200151571A1

公开(公告)日：2020-05-14

申请号：US16191201

申请日：2018-11-14

Applicant: NVIDIA Corporation

Inventor： Hao Wu

IPC: G06N3/08

Abstract: Machine learning systems that implement neural networks typically operate in an inference mode or a training mode. In the training mode, inference operations are performed to help guide the training process. Inference mode operation typically involves forward propagation and intensive access to certain sparse matrices, encoded as a set of vectors. Back propagation and intensive access to transposed versions of the same sparse matrices provide training refinements. Generating a transposed version of a sparse matrix can consume significant additional memory and computation resources. In one embodiment, two additional encoding vectors are generated, providing efficient operations on sparse matrices and also on transposed representations of the same sparse matrices. In a neural network the efficient operations can reduce the amount of memory needed for backpropagation and reduce power consumption.