High Performance Computing (HPC) benefits from different improvements during last decades, specially in terms of hardware platforms to provide more processing power while maintaining the power consumption at a reasonable level. The Intelligence Processing Unit (IPU) is a new type of massively parallel processor, designed to speedup parallel computations with huge number of processing cores and on-chip memory components connected with high-speed fabrics. IPUs mainly target machine learning applications, however, due to the architectural differences between GPUs and IPUs, especially significantly less memory capacity on an IPU, methods for reducing model size by sparsification have to be considered. Butterfly factorizations are well-known replacements for fully-connected and convolutional layers. In this paper, we examine how butterfly structures can be implemented on an IPU and study their behavior and performance compared to a GPU. Experimental results indicate that these methods can provide 98.5% compression ratio to decrease the immense need for memory, the IPU implementation can benefit from 1.3x and 1.6x performance improvement for butterfly and pixelated butterfly, respectively. We also reach to 1.62x training time speedup on a real-word dataset such as CIFAR10.

翻译：高性能计算（HPC）在过去几十年中得益于多项改进，特别是在硬件平台方面，以在保持合理功耗水平的同时提供更强的处理能力。智能处理单元（IPU）是一种新型大规模并行处理器，旨在通过大量处理核心和与高速互联结构相连的片上内存组件来加速并行计算。IPU主要面向机器学习应用，但由于GPU与IPU在架构上的差异，尤其是IPU内存容量显著较小，必须考虑通过稀疏化方法缩减模型大小。蝴蝶分解是替代全连接层和卷积层的经典方法。本文探讨了如何在IPU上实现蝴蝶结构，并研究了其行为特性及与GPU的性能对比。实验结果表明，这些方法可实现98.5%的压缩比以大幅降低内存需求；IPU实现中，蝴蝶分解和像素化蝴蝶分解分别能获得1.3倍和1.6倍的性能提升。此外，在CIFAR10等真实数据集上，训练速度可提升至1.62倍。