Deploying deep learning models on various devices has become an important
topic. The wave of hardware specialization brings a diverse set of acceleration
primitives for multi-dimensional tensor computations. These new acceleration
primitives, along with the emerging machine learning models, bring tremendous
engineering challenges. In this paper, we present TensorIR, a compiler
abstraction for optimizing programs with these tensor computation primitives.
TensorIR generalizes the loop nest representation used in existing machine
learning compilers to bring tensor computation as the first-class citizen.
Finally, we build an end-to-end framework on top of our abstraction to
automatically optimize deep learning models for given tensor computation
primitives. Experimental results show that TensorIR compilation automatically
uses the tensor computation primitives for given hardware backends and delivers
performance that is competitive to state-of-art hand-optimized systems across
platforms.

该论文介绍了 TensorIR 编译器抽象，用于优化具有张量计算原语的程序，通过 TensorIR 编译可以自动化优化深度学习模型，实验结果表明 TensorIR 编译使用特定的硬件后端的张量计算原语，并在各平台上提供了与手动优化系统相当的性能竞争力。

TensorIR：自动张量程序优化的抽象

TensorIR: An Abstraction for Automatic Tensorized Program Optimization

Advancing research in the emerging field of deep graph learning requires new
tools to support tensor computation over graphs. In this paper, we present the
design principles and implementation of Deep Graph Library (DGL). DGL distills
the computational patterns of GNNs into a few generalized sparse tensor
operations suitable for extensive parallelization. By advocating graph as the
central programming abstraction, DGL can perform optimizations transparently.
By cautiously adopting a framework-neutral design, DGL allows users to easily
port and leverage the existing components across multiple deep learning
frameworks. Our evaluation shows that DGL significantly outperforms other
popular GNN-oriented frameworks in both speed and memory consumption over a
variety of benchmarks and has little overhead for small scale workloads.

本文介绍了 Deep Graph Library（DGL）的设计原则和实现方法，DGL 将 GNNs 的计算模式提炼成几个泛化的稀疏张量操作，适合大规模并行化。DGL 以图形为中心编程抽象，能够透明地进行优化。同时 DGL 采用了框架中立的设计，允许用户在多个深度学习框架中轻松移植和利用现有的组件。我们的评估表明，在各种基准测试中，DGL 在速度和内存消耗方面都显著优于其他流行的面向 GNNs 的框架，并且对于小规模工作负载的开销很小。