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 2205.04586cs.LGcs.AIcs.NE
收藏

利用神经网络推断硬件性能的最优VPU制造成本建模

Towards Optimal VPU Compiler Cost Modeling by using Neural Networks to Infer Hardware Performances

Intel Corporation(英特尔公司)

Ian Frederick Vigogne Goodbody Hunter, Alessandro Palla, Sebastian Eusebiu Nagy, Richard Richmond, Kyle McAdoo

摘要:

在神经网络编译器中计算最有效的工作时间表是一项困难的任务。有许多参数需要考虑,这些参数可以根据其配置积极或不利地影响该调度-如何在分布式目标之间共享工作,张量的细分以适应内存,切换优化的启用等传统上,神经网络编译器通过构建选择图并选择具有最小“成本”的路径来确定如何设置这些值。这些选择及其相应的成本通常由对目标平台有深入了解的工程师制定的算法确定。然而,当编译器可用的选项数量很大时,很难确保这些模型始终为所有场景生成最佳调度,同时仍然在可接受的时间范围内完成编译。本文介绍了“VPUNN”--一种基于神经网络的成本模型,该模型在低级任务分析上进行了训练,其性能始终优于英特尔VPU处理器系列中最先进的成本模型。

英文摘要:

Calculating the most efficient schedule of work in a neural network compiler is a difficult task. There are many parameters to be accounted for that can positively or adversely affect that schedule depending on their configuration - How work is shared between distributed targets, the subdivision of tensors to fit in memory, toggling the enablement of optimizations, etc. Traditionally, neural network compilers determine how to set these values by building a graph of choices and choosing the path with minimal 'cost'. These choices and their corresponding costs are usually determined by an algorithm crafted by engineers with a deep knowledge of the target platform. However, when the amount of options available to a compiler is large, it is very difficult to ensure that these models consistently produce an optimal schedule for all scenarios, whilst still completing compilation in an acceptable timeframe. This paper presents 'VPUNN' - a neural network-based cost model trained on low-level task profiling that consistently outperforms the state-of-the-art cost modeling in Intel's line of VPU processors.

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。

↑