RRAM-based multi-core systems improve the energy efficiency and performance of CNNs. Thereby, the distributed parallel execution of convolutional layers causes critical data dependencies that limit the potential speedup. This paper presents synchronization techniques for parallel inference of convolutional layers on RRAM-based CIM architectures. We propose an architecture optimization that enables efficient data exchange and discuss the impact of different architecture setups on the performance. The corresponding compiler algorithms are optimized for high speedup and low memory consumption during CNN inference. We achieve more than 99% of the theoretical acceleration limit with a marginal data transmission overhead of less than 4% for state-of-the-art CNN benchmarks.

翻译：基于多核RRAM的CIM架构可提升CNN的能效与性能。然而，卷积层的分布式并行执行会引起关键数据依赖问题，从而限制潜在加速比。本文提出面向RRAM-CIM架构中卷积层并行推理的同步技术。我们提出一种支持高效数据交换的架构优化方案，并探讨不同架构配置对性能的影响。针对CNN推理过程，相应编译器算法被优化以实现高加速比与低内存占用。在主流CNN基准测试上，本方案达到理论加速极限的99%以上，数据传输开销低于4%。