Problem
Research questions and friction points this paper is trying to address.
edge devices
coarse grain reconfigurable architecture (CGRA)
multiply-and-accumulate (MAC)
A 420 GOPS/W CGRA with a Configurable MAC and Dynamic Truncation
🤖 AI Summary
本文提出一种具有可配置MAC单元的CGRA，通过单周期执行加法、乘法或MAC操作及动态截断技术提高处理效率和灵活性，解决了边缘设备中实时工作负载处理效率低的问题。
📝 Abstract
Edge devices demand for highly efficient yet flexible processing capability to handle dynamic real-time workloads. Coarse grain reconfigurable architecture (CGRA) emerges as a suitable accelerator candidate in edge devices, because they are as flexible as general purpose processors and offer high efficiency close to that of domain specific accelerators. However, a typical CGRA requires two cycles for a multiply-and-accumulate (MAC) operation, and workloads such as neural network inference and signal processing involve many MAC operations, resulting in long CGRA processing time. This work proposes a CGRA that has configurable MAC units in the processing elements (PEs) that can perform an addition (ADD) or multiplication (MUL) or a MAC by using the same multiplier and adder, in a single cycle. The readout precision of MAC result can be adjusted by a truncation block. The proposed CGRA is implemented with 40nm CMOS technology. It attains an energy efficiency of 420.6GOPS/W operating at supply of 0.6V and frequency of 21MHz, which is 1.4 times higher than the state-of-the-art.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Configurable MAC
Dynamic Truncation
CGRA
Energy Efficiency
🔎 Similar Papers
No similar papers found.
