EAGER: Software-Hardware Co-Design Approaches for Multi-Level Memories

EAGER：多级存储器的软硬件协同设计方法

• 批准号: 1748652
• 负责人: Sanjay Ranka
• 金额: $ 30万
• 依托单位: University of Florida
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-10-01 至 2020-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1748652&HistoricalAwards=false
• 关键词: EAGER; Software; Hardware; Co; Design

The effective solution of big data problems requires computers that have very large memory capacity and that are able to perform very many operations per second. Since providing the required amount of main memory with sufficient bandwidth to achieve the desired throughput is cost prohibitive, vendors have resorted to multi-level memory (MLM) architectures in which main memory comprises two or more levels, with each level having memory with different bandwidth and cost characteristics. The Intel Knights Landing is an example; it has two levels of main memory - 16Gigabytes of high-cost, high-throughput memory, and up to 384Gigabytes of relatively low-cost, low-throughput memory. The Knights Landing also has 72 compute cores capable of performing up to 6 teraflops of single precision or 3 teraflops of double precision operations. This project seeks to demonstrate the effectiveness of multicore MLM architectures in solving big data problems.This project will develop efficient multicore MLM software for representative applications with different workflow characteristics: data parallel, hierarchical, and task parallel. The specific applications being considered are simulation of compressible multiphase turbulence, sparse matrix factorization, and image reconstruction from synthetic aperture radar data. The software will be evaluated on the Knights Landing as well as using MLM simulation software. Techniques for the development of such software and optimal MLM configurations based on workload characterization will be identified.

大数据问题的有效解决需要计算机具有非常大的内存容量并且每秒能够执行非常多的操作。由于提供所需量的主存储器和足够的带宽来实现所需的吞吐量的成本过高，因此供应商采用了多级存储器（MLM）架构，其中主存储器包括两个或多个级别，每个级别具有具有不同带宽和成本特性的存储器。英特尔骑士登陆就是一个例子；它有两级主内存——16GB的高成本、高吞吐量内存，以及高达384GB的相对低成本、低吞吐量内存。 Knights Landing 还拥有 72 个计算核心，能够执行高达 6 teraflops 的单精度运算或 3 teraflops 的双精度运算。该项目旨在展示多核 MLM 架构在解决大数据问题方面的有效性。该项目将为具有不同工作流程特征的代表性应用程序开发高效的多核 MLM 软件：数据并行、分层和任务并行。正在考虑的具体应用是可压缩多相湍流的模拟、稀疏矩阵分解以及合成孔径雷达数据的图像重建。该软件将在 Knights Landing 上以及使用 MLM 模拟软件进行评估。将确定开发此类软件的技术以及基于工作负载特征的最佳传销配置。

项目成果

Multilevel Approaches to Fine Tune Performance of Linear Algebra Libraries

微调线性代数库性能的多级方法

• DOI: 10.1109/isspit47144.2019.9001832
• 发表时间: 2019
• 期刊: Proceedings of ISSPIT
• 作者: Gheibi, Sanaz;Banerjee, Tania;Ranka, Sanjay;Sahni, Sartaj
• 通讯作者: Sahni, Sartaj

Fine Tuning the Performance of Parallel Codes

• DOI: 10.25046/aj050497
• 发表时间: 2020
• 期刊: Advances in Science, Technology and Engineering Systems Journal
• 作者: Sanaz Gheibi;Tania Banerjee;S. Ranka;S. Sahni

Cache efficient Value Iteration using clustering and annealing

使用聚类和退火来缓存高效的值迭代

• DOI: 10.1016/j.comcom.2020.04.058
• 发表时间: 2020
• 期刊: Computer Communications
• 影响因子: 6
• 作者: Jain, Anuj;Sahni, Sartaj
• 通讯作者: Sahni, Sartaj