Qing Yang

Title: Innovations of Qing Yang in Matrix Computations

Introduction

Qing Yang is a notable inventor based in Santa Clara, CA (US). She has made significant contributions to the field of matrix computations, particularly in the context of data pattern processing using tensor cores. Her innovative work has implications for improving the efficiency of matrix multiplication operations.

Latest Patents

Qing Yang holds a patent for "Non-rectangular matrix computations and data pattern processing using tensor cores." This patent describes a method where matrix multiplication operations can be implemented on tensor cores of a parallel processing unit. The efficiency of these operations can be enhanced when one of the input operands or the output operand is a square matrix with a triangular data pattern. By dropping computations and masking out elements of the square matrix input operand on one side of the main diagonal, the number of computations performed can be significantly reduced. This innovative approach also applies to cases where the output operand exhibits a triangular data pattern.

Career Highlights

Qing Yang is currently employed at Nvidia Corporation, a leading company in the field of graphics processing and computing technology. Her work at Nvidia focuses on advancing computational techniques that leverage the capabilities of modern processing units.

Collaborations

Some of her notable coworkers include Aniket Shivam and Andrew Kerr, who collaborate with her on various projects related to matrix computations and data processing.

Conclusion

Qing Yang's contributions to matrix computations and her innovative patent demonstrate her significant role in advancing technology in this field. Her work continues to influence the efficiency of computational operations in modern processing units.