arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.14486cs.LGcs.AI
收藏

基于价值函数的深度学习工作负载性能优化

Value Function Based Performance Optimization of Deep Learning Workloads

Facebook AI Research(Facebook人工智能研究院);Facebook(脸书)

Benoit Steiner, Chris Cummins, Horace He, Hugh Leather

摘要:

随着机器学习技术变得无处不在,神经网络实现的效率相应地变得至关重要。Halide和TVM等框架将网络的算法表示与确定其实现的时间表分开。然而,找到一个好的时间表仍然是非常具有挑战性的。我们将此调度问题建模为一系列优化选择,并提出了一种新的技术来准确地预测部分时间表的预期性能。通过利用这些预测,我们可以做出这些优化决策,并迅速确定一个有效的时间表。这使我们能够找到将深度神经网络的吞吐量提高到Halide的2.6倍和TVM的1.5倍的调度。此外,我们的技术比这些工具快两到三个数量级,并且在几秒钟而不是几小时内完成。

英文摘要:

As machine learning techniques become ubiquitous, the efficiency of neural network implementations is becoming correspondingly paramount. Frameworks, such as Halide and TVM, separate out the algorithmic representation of the network from the schedule that determines its implementation. Finding good schedules, however, remains extremely challenging. We model this scheduling problem as a sequence of optimization choices, and present a new technique to accurately predict the expected performance of a partial schedule. By leveraging these predictions we can make these optimization decisions greedily and rapidly identify an efficient schedule. This enables us to find schedules that improve the throughput of deep neural networks by 2.6x over Halide and 1.5x over TVM. Moreover, our technique is two to three orders of magnitude faster than that of these tools, and completes in seconds instead of hours.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑