Close

Presentation

CoDR: Computation and Data Reuse Aware CNN Accelerator
TimeWednesday, December 8th6:00pm - 7:00pm PST
Event Type
Networking Reception
Work-in-Progress Poster
Virtual Programs
Presented In-Person
DescriptionComputation and Data Reuse is critical for the resource-limited Convolutional Neural Network (CNN) accelerators. This paper presents Universal Computation Reuse to exploit weight sparsity, repetition, and similarity simultaneously in a convolutional layer. Moreover, CoDR decreases the cost of weight memory access by proposing a customized Run-Length Encoding scheme and the number of memory accesses to the intermediate results by introducing an input and output stationary dataflow. Compared to two recent compressed CNN accelerators [6][2] with the same area of 2.85 mm2, CoDR decreases SRAM access by 5.08X and 7.99X, and consumes 3.76X and 6.84X less energy.