Ray C. C. Cheung

High-Throughput GPU Design and Implementation of MAYO with Matrix Computation Reordering

This work presents the first high-throughput GPU implementation and evaluation of MAYO, covering Keygen, Signing, and Verification, and introduces a data reuse-aware computation model for matrix-dominated and memory-access-bound workloads, and proposes Reuse Matrix Multiplication Evaluation (RMME) to reduce redundant g...