Artificial Intelligence

We present a building block architecture for systolic array 3D-IC implementations of convolutional neural network (CNN) inference. The building block can be part of a library offered by a chip design service provider to support efficient CNN implementations. We describe how the building block can form systolic arrays for implementing low-latency, energy-efficient CNN inference for models of any size, while incorporating advanced packaging features such as “logic-on-logic” 3D-IC (micro-bump/TSV, monolithic 3D or other 3D technology). We present delay and power analysis for 2D and 3D implementations, and argue that as systolic arrays scale in size, 3D implementations based on, e.g., micro-bump/TSV, lead to significant performance improvements over 2D implementations.

A memory-logic hybrid gate with complementary resistive switching pairs on vias in BEOL FinFET technologies with an area-efficient, 3D-stackable structures is proposed. Stable output logic stages enabled by the complementary states on the RRAM pair have been demonstrated. Through stacked-vias architectures, logic operations based on multiple non-volatile states are achieved.

For deep-neural-network (DNN) processors [1-4], the product-sum (PS) operation predominates the computational workload for both convolution (CNVL) and fully-connect (FCNL) neural-network (NN) layers. This hinders the adoption of DNN processors to on the edge artificial-intelligence (AI) devices, which require low-power, low-cost and fast inference. Binary DNNs [5-6] are used to reduce computation and hardware costs for AI edge devices; however, a memory bottleneck still remains. In Fig. 31.5.1 conventional PE arrays exploit parallelized computation, but suffer from inefficient single-row SRAM access to weights and intermediate data. Computing-in-memory (CIM) improves efficiency by enabling parallel computing, reducing memory accesses, and suppressing intermediate data. Nonetheless, three critical challenges remain (Fig. 31.5.2), particularly for FCNL. We overcome these problems by co-optimizing the circuits and the system. Recently, researches have been focusing on XNOR based binary-DNN structures [6]. Although they achieve a slightly higher accuracy, than other binary structures, they require a significant hardware cost (i.e. 8T-12T SRAM) to implement a CIM system. To further reduce the hardware cost, by using 6T SRAM to implement a CIM system, we employ binary DNN with 0/1-neuron and ±1-weight that was proposed in [7]. We implemented a 65nm 4Kb algorithm-dependent CIM-SRAM unit-macro and in-house binary DNN structure (focusing on FCNL with a simplified PE array), for cost-aware DNN AI edge processors. This resulted in the first binary-based CIM-SRAM macro with the fastest (2.3ns) PS operation, and the highest energy-efficiency (55.8TOPS/W) among reported CIM macros [3-4].