As neural network model sizes have dramatically increased, so has the
interest in various techniques to reduce their parameter counts and accelerate
their execution. An active area of research in this field is sparsity -
encouraging zero values in parameters that can then be discarded from storage
or computations. While most research focuses on high levels of sparsity, there
are challenges in universally maintaining model accuracy as well as achieving
significant speedups over modern matrix-math hardware. To make sparsity
adoption practical, the NVIDIA Ampere GPU architecture introduces sparsity
support in its matrix-math units, Tensor Cores. We present the design and
behavior of Sparse Tensor Cores, which exploit a 2:4 (50%) sparsity pattern
that leads to twice the math throughput of dense matrix units. We also describe
a simple workflow for training networks that both satisfy 2:4 sparsity pattern
requirements and maintain accuracy, verifying it on a wide range of common
tasks and model architectures. This workflow makes it easy to prepare accurate
models for efficient deployment on Sparse Tensor Cores.

介绍了 NVIDIA Ampere GPU 架构中的稀疏张量核心 (Sparse Tensor Cores)，它们利用了 2:4 的稀疏模式，通过两倍的数学吞吐量加速了稠密矩阵单元，并提出了一种简单的工作流程以训练满足 2:4 稀疏模式和保持准确性的网络，从而在稀疏张量核心上实现精确模型的高效部署。