当前位置: X-MOL 学术IEEE Comput. Archit. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
FlexScore: Quantifying Flexibility
IEEE Computer Architecture Letters ( IF 2.3 ) Pub Date : 2021-04-28 , DOI: 10.1109/lca.2021.3076413
Tian Tan , Eriko Nurvitadhi , Aravind Dasu , Martin Langhammer , Derek Chiou

Domain-specific accelerators achieve high performance and efficiency at the cost of reduced adaptivity to functionality changes, i.e., flexibility. Balancing efficiency and flexibility is important for accelerator designing. There is not, however, a commonly accepted metric for flexibility. We propose FlexScore as a flexibility metric based on the relationship between flexibility and goodness metrics, such as performance. FlexScore does not incorporate domain-specific or hardware-specific knowledge and, thus, is applicable to general accelerator design. We present FlexScores of three well-known DNN accelerators and observe that there is 45 percent FlexScore difference among them and show how architectural changes could improve FlexScore by up to 21 percent, demonstrating the usefulness of FlexScore in evaluating, comparing, and trading-off different architectures.

中文翻译:

FlexScore:量化灵活性

特定领域的加速器以降低对功能变化的适应性(即灵活性)为代价来实现高性能和高效率。平衡效率和灵活性对于加速器设计很重要。然而,没有一个普遍接受的灵活性指标。我们建议FlexScore作为基于灵活性和良好度量(例如性能)之间关系的灵活性度量。FlexScore 不包含特定领域或特定硬件的知识,因此适用于通用加速器设计。我们展示了三个著名 DNN 加速器的 FlexScore,观察到它们之间存在 45% 的 FlexScore 差异,并展示了架构更改如何将 FlexScore 提高多达 21%,证明了 FlexScore 在评估、比较和权衡不同架构。
更新日期:2021-06-04
down
wechat
bug