Presentation
FDCA: Fine-grained Digital-CIM based CNN Accelerator with Hybrid Quantization and Weight-Stationary Dataflow
DescriptionDigital-Compute-In-Memory (DCIM) has demonstrated significant energy and area efficiency in convolutional neural network (CNN) accelerators, particularly for high precision applications. However, to mitigate parasitic effects on word and bit lines, most DCIMs employ fine-grained multiply-accumulate operations, which causes new challenges and opportunities but have not been widely explored. This paper proposes FDCA: a Fine-grained Digital-CIM based CNN Accelerator with hybrid quantization and weight-stationary dataflow, in which the key contributions are :1) a hybrid quantization approach for CNNs leveraging hessian trace and approximation is utilized. This method incorporates the ratio of computation time and storage time into quantization, achieving high efficiency while maintaining accuracy; 2) a Cartesian Genetic Programming based approximate shift and accumulate unit with error compensation is proposed, where an approximate adder tree is generated to compensate for errors introduced by DCIM; 3) a weight-stationary dataflow optimized for fine-grained DCIM is used to improve the utilization of CIM macro and eliminate dataflow stalls. The experimental results demonstrate that under 28-nm process, when running VGG16 and ResNet50 on CIFAR100, the proposed FDCA achieves 17.1TOPS/W and 18.79TOPS/W with accuracy loss by 0.71% and 0.98%, respectively. Compared to previous works, this work achieves 1.76× and 1.29× improvements in energy efficiency with less accuracy loss.
Event Type
Research Manuscript
TimeWednesday, June 2610:45am - 11:00am PDT
Location3002, 3rd Floor
Design
In-memory and Near-memory Computing Architectures, Applications and Systems