当前位置: X-MOL 学术arXiv.cs.AR › 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.)
Mind Mappings: Enabling Efficient Algorithm-Accelerator Mapping Space Search
arXiv - CS - Hardware Architecture Pub Date : 2021-03-02 , DOI: arxiv-2103.01489
Kartik Hegde, Po-An Tsai, Sitao Huang, Vikas Chandra, Angshuman Parashar, Christopher W. Fletcher

Modern day computing increasingly relies on specialization to satiate growing performance and efficiency requirements. A core challenge in designing such specialized hardware architectures is how to perform mapping space search, i.e., search for an optimal mapping from algorithm to hardware. Prior work shows that choosing an inefficient mapping can lead to multiplicative-factor efficiency overheads. Additionally, the search space is not only large but also non-convex and non-smooth, precluding advanced search techniques. As a result, previous works are forced to implement mapping space search using expert choices or sub-optimal search heuristics. This work proposes Mind Mappings, a novel gradient-based search method for algorithm-accelerator mapping space search. The key idea is to derive a smooth, differentiable approximation to the otherwise non-smooth, non-convex search space. With a smooth, differentiable approximation, we can leverage efficient gradient-based search algorithms to find high-quality mappings. We extensively compare Mind Mappings to black-box optimization schemes used in prior work. When tasked to find mappings for two important workloads (CNN and MTTKRP), the proposed search finds mappings that achieve an average $1.40\times$, $1.76\times$, and $1.29\times$ (when run for a fixed number of steps) and $3.16\times$, $4.19\times$, and $2.90\times$ (when run for a fixed amount of time) better energy-delay product (EDP) relative to Simulated Annealing, Genetic Algorithms and Reinforcement Learning, respectively. Meanwhile, Mind Mappings returns mappings with only $5.32\times$ higher EDP than a possibly unachievable theoretical lower-bound, indicating proximity to the global optima.

中文翻译:

思维映射:启用高效的算法-加速器映射空间搜索

现代计算越来越依赖于专业化来满足不断增长的性能和效率要求。设计这样的专用硬件体系结构的核心挑战是如何执行映射空间搜索,即搜索从算法到硬件的最佳映射。先前的工作表明,选择低效的映射可能会导致乘数效率开销。另外,搜索空间不仅很大,而且不凸且不平滑,从而排除了高级搜索技术。结果,以前的工作被迫使用专家的选择或次优搜索启发式方法来实现映射空间搜索。这项工作提出了思维映射,一种用于算法-加速器映射空间搜索的新颖的基于梯度的搜索方法。关键思想是获得平稳,对否则为非平滑,非凸的搜索空间的可微近似。通过平滑,可微的近似,我们可以利用基于梯度的高效搜索算法来找到高质量的映射。我们将思维导图与先前工作中使用的黑盒优化方案进行了广泛的比较。当任务是查找两个重要工作负载(CNN和MTTKRP)的映射时,建议的搜索将查找达到平均$ 1.40 \ times $,$ 1.76 \ times $和$ 1.29 \ times $的映射(运行固定数量的步骤时),并且相对于模拟退火,遗传算法和强化学习,$ 3.16 \ times $,$ 4.19 \ times $和$ 2.90 \ times $(运行固定时间)的能量延迟产品(EDP)更好。同时,Mind Mappings仅返回$ 5的映射。
更新日期:2021-03-03
down
wechat
bug