Spiking neural network (SNN) is the most commonly used computational model for neuroscience and neuromorphic computing communities. It provides more biological reality and possesses the potential to achieve high computational power and energy efficiency. Because existing SNN simulation frameworks on general-purpose graphics processing units (GPGPUs) do not fully consider the biological oriented properties of SNNs, like spike-driven, activity sparsity, etc., they suffer from insufficient parallelism exploration, irregular memory access, and load imbalance. In this article, we propose specific optimization methods to speed up the SNN simulation on GPGPU. First, we propose a fine-grained network representation as a flexible and compact intermediate representation (IR) for SNNs. Second, we propose the cross-population/-projection parallelism exploration to make full use of GPGPU resources. Third, sparsity aware load balance is proposed to deal with the activity sparsity. Finally, we further provide dedicated optimization to support multiple GPGPUs. Accordingly, BSim, a code generation framework for high-performance simulation of SNN on GPGPUs is also proposed. Tests show that, compared to a state-of-the-art GPU-based SNN simulator GeNN, BSim achieves $1.41\times \sim 9.33\times$1.41×∼9.33× speedup for SNNs with different configurations; it outperforms other simulators much more.

中文翻译：

---

GPGPU 上尖峰神经网络的高性能仿真

尖峰神经网络 (SNN) 是神经科学和神经形态计算社区最常用的计算模型。它提供了更多的生物现实，并具有实现高计算能力和能源效率的潜力。由于现有的通用图形处理单元 (GPGPU) 上的 SNN 仿真框架没有充分考虑 SNN 的生物学特性，如尖峰驱动、活动稀疏性等，它们存在并行探索不足、不规则内存访问和负载不平衡。在本文中，我们提出了特定的优化方法来加速 GPGPU 上的 SNN 模拟。首先，我们提出了一种细粒度的网络表示，作为 SNN 的灵活紧凑的中间表示 (IR)。第二，我们提出了cross-population/-projection 并行探索，以充分利用GPGPU 资源。第三，提出了稀疏感知负载均衡来处理活动稀疏性。最后，我们进一步提供了专门的优化来支持多个 GPGPU。因此，还提出了 BSim，一种用于在 GPGPU 上高性能模拟 SNN 的代码生成框架。测试表明，与最先进的基于 GPU 的 SNN 模拟器 GeNN 相比，BSim 实现了$1.41\times\sim 9.33\times$1.41×～9.33×不同配置的 SNN 加速；它比其他模拟器要好得多。