On Performance Analysis of Graphcore IPUs: Analyzing Squared and Skewed Matrix Multiplication

TL;DR

This paper analyzes the performance of Graphcore IPUs in executing matrix multiplication, especially skewed matrices, comparing them to GPUs and highlighting their advantages in certain computational scenarios.

Contribution

It provides an extensive analysis of IPU performance on matrix multiplication, including efficiency, memory usage, and comparison with GPUs, emphasizing their strengths with skewed matrices.

Findings

IPUs outperform GPUs in skewed matrix multiplication.

IPUs show consistent robustness across various matrix aspect ratios.

Analysis includes execution efficiency and memory considerations.

Abstract

In recent decades, High Performance Computing (HPC) has undergone significant enhancements, particularly in the realm of hardware platforms, aimed at delivering increased processing power while keeping power consumption within reasonable limits. The Intelligence Processing Unit (IPU) represents an entirely novel category of massively parallel processors, meticulously designed to expedite parallel computations through a multitude of processing cores and on-chip memory components interconnected via high-speed fabrics. While IPUs are primarily tailored for machine learning applications and come equipped with several libraries for the seamless implementation of neural networks, they also retain the capability to execute traditional parallel programs like matrix multiplication. However, it is essential to acknowledge that there are certain considerations and limitations when utilizing IPUs for such tasks. This paper embarks on an extensive analytical examination of matrix multiplications (MM) executed on an IPU, focusing on aspects such as execution efficiency and memory usage. Additionally, a comparative analysis is conducted, pitting the IPU against a GPU. Our findings indicate that IPUs can outperform modern GPUs, especially in handling the consistently challenging skewed matrix multiplication operations. For a more comprehensive understanding, we scrutinize various aspect ratios of matrices for these operations on an IPU and a Turing-class GPU (RTX 2080TI), revealing that the IPU consistently delivers more robust performance when dealing with skewed matrices compared to a GPU.