1. Introduction
The Poplar Advanced Run Time (PopART) is part of the Poplar SDK for implementing and running algorithms on networks of Graphcore IPUs. It enables you to import models using the Open Neural Network Exchange (ONNX) and run them using the Poplar tools. ONNX is a serialisation format for neural network systems that can be created and read by several frameworks including Caffe2, PyTorch and MXNet.
This document describes the features of PopART. It assumes that you are familiar with machine learning and the ONNX framework.
An overview of the IPU architecture and programming model can be found in the IPU Programmer’s Guide. For more information on the Poplar graph programming framework, refer to the Poplar and PopLibs User Guide.
PopART has three main features:
It can import ONNX graphs into a runtime environment (Section 3, Importing graphs).
It provides a simple interface for constructing ONNX graphs without need for a third party framework (described in Section 4, Building graphs in PopART).
It runs imported graphs in inference, evaluation or training modes, by building a Poplar Engine, connecting data feeds and scheduling the execution of the Engine (Section 5, Executing graphs).
IPU-specific annotations on ONNX operations allow the provider of the graph to control IPU-specific features, such as mapping an algorithm across multiple IPUs.
PopART has both a C++ API and a Python API. Most of the examples in this document use the Python API.