[论文解读] Dissecting the NVidia Turing T4 GPU via Microbenchmarking

Zhe Jia, Marco Maggioni+2 more|arXiv (Cornell University)|Mar 18, 2019

Ferroelectric and Negative Capacitance Devices被引用 73

一句话总结

本技术报告通过微基准测试来分析和剖析 NVIDIA Turing T4 GPU，提供其架构行为的实证分析。

ABSTRACT

In 2019, the rapid rate at which GPU manufacturers refresh their designs, coupled with their reluctance to disclose microarchitectural details, is still a hurdle for those software designers who want to extract the highest possible performance. Last year, these very reasons motivated us to dissect the Volta GPU architecture using microbenchmarks. The introduction in August 2018 of Turing, NVidia's latest architecture, pressed us to update our study. In this report, we examine Turing and compare it quantitatively against previous NVidia GPU generations. Specifically, we study the T4 GPU: a low-power board aiming at inference applications. We describe its improvements against its inference-oriented predecessor: the P4 GPU based on the Pascal architecture. Both T4 and P4 GPUs achieve significantly higher frequency-per-Watt figures than their full-size counterparts. We study the performance of the T4's TensorCores, finding a much higher throughput on low-precision operands than on the P4 GPU. We reveal that Turing introduces new instructions that express matrix math more succinctly. We map Turing's instruction space, finding the same encoding as Volta, and additional instructions. We reveal that the Turing TU104 chip has the same memory hierarchy depth as the Volta GV100; cache levels sizes on the TU104 are frequently twice as large as those found on the Pascal GP104. We benchmark each constituent of the T4 memory hierarchy and find substantial overall performance improvements over its P4 predecessor. We studied how clock throttling affects compute-intensive workloads that hit power or thermal limits. Many of our findings are novel, published here for the first time. All of them can guide high-performance software developers get closer to the GPU's peak performance.

研究动机与目标

• 通过有针对性的微基准测试促进对 Turing T4 架构的理解。
• 利用受控实验表征 T4 的性能与行为特征。
• 提供可重复的实验方法和分析，独立于厂商确认。

提出的方法

• 应用微基准测试技术来探测 Turing T4 GPU。
• 描述实验设置和测量程序以确保可重复性。
• 分析观察到的行为以推断架构和性能特征。
• 基于作者的实验观察呈现分析和发现。

实验结果

研究问题

• RQ1 在摘要中未提供明确的研究问题。

主要发现

• 本报告呈现基于对 Turing T4 GPU 的微基准测试得到的分析与发现。
• 这些发现反映了作者测量和解释的实证观察。