CC* Compute: Integrating Georgia Tech into the Open Science Grid for Multi-Messenger Astrophysics
CC* 计算:将佐治亚理工学院集成到多信使天体物理学的开放科学网格中
基本信息
- 批准号:1925541
- 负责人:
- 金额:$ 39.99万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2019
- 资助国家:美国
- 起止时间:2019-07-01 至 2021-06-30
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Studying the Universe with all possible sources of information is the objective of multi-messenger astrophysics. Groundbreaking gravitational wave observations with LIGO, high-energy neutrino observations with IceCube, and very high-energy gamma-ray observations with VERITAS enable multi-messenger astrophysics. These and future instruments like CTA enable a complete view of the most violent and energetic phenomena in the Universe, such as the merger of black holes and neutron stars or the processes near the supermassive black holes at the center of large galaxies. All these efforts are computationally intensive, both in data analysis and in simulations. The Open Science Grid (OSG) infrastructure and services are an ideal platform to meet the computational requirements of Multi-messenger Astrophysics. This project acquires cyber infrastructure resources to connect Georgia Tech to the OSG and integrate these resources into computational efforts of the previously-mentioned NSF funded facilities. The High Throughput Computing Cluster acquired under this award includes 12 compute nodes with 40-core Intel Skylakes with 192 GB memory to support LIGO project requirements and others. IceCube and LIGO are supported with 4 GPU nodes, each equipped with 16-core Intel Skylakes and 4 NVIDIA TeslaV100 GPUs with 96GB memory. A special OSG StashCache has 432TB of storage in direct support of projects such as CTA. The system is 10Gbps connected in the Georgia Tech data center which in turn has 100Gbps+ to Southern Crossroads R&E exchange point. This project's resources serve as a catalyst for Georgia Tech's long-term integration into the OSG, as a standard service offered to all researchers on campus. An important component of this proposal is a significant number of Graphical Processing Units, used to accelerate simulations. This project makes Atlanta the first StashCache provider in the Southeast, as a service that enables fast access to distributed OSG datasets by regional institutions that participate in this national grid.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
利用所有可能的信息来源研究宇宙是多信使天体物理学的目标。LIGO上的开创性引力波观测、IceCube上的高能中微子观测以及Veritas上的超高能伽马射线观测使多信使天体物理学成为可能。这些和未来的仪器,如CTA,使我们能够完整地看到宇宙中最猛烈和最有能量的现象,例如黑洞和中子星的合并,或者大星系中心超大质量黑洞附近的过程。所有这些努力都是计算密集型的,无论是在数据分析还是在模拟中。开放科学网格(OSG)的基础设施和服务是满足多信使天体物理计算需求的理想平台。该项目获得网络基础设施资源,将佐治亚理工学院与OSG连接起来,并将这些资源整合到前面提到的NSF资助的设施的计算工作中。根据该奖项获得的高吞吐量计算集群包括12个计算节点,配备40核Intel Skylake和192 GB内存,以支持LIGO项目要求和其他要求。IceCube和LIGO支持4个GPU节点,每个节点配备16核Intel Skylake和4个96 GB内存的NVIDIA TeslaV100 GPU。一个特殊的OSG StashCache拥有432 TB的存储容量,可直接支持CTA等项目。该系统以10Gbps连接在佐治亚理工学院数据中心,该数据中心又有100Gbps+到南十字路口R&A;E交换点。该项目的资源是佐治亚理工学院长期融入OSG的催化剂,作为向校园内所有研究人员提供的标准服务。这一提议的一个重要组成部分是大量的图形处理单元,用于加速模拟。该项目使亚特兰大成为东南部第一个StashCach提供商,作为一项服务,使参与国家网格的地区机构能够快速访问分布式OSG数据集。该奖项反映了NSF的法定使命,并通过使用基金会的智力优势和更广泛的影响审查标准进行评估,被认为值得支持。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Mehmet Belgin其他文献
An operation stacking framework for large ensemble computations
用于大型集成计算的操作堆栈框架
- DOI:
10.1145/1274971.1274986 - 发表时间:
2007 - 期刊:
- 影响因子:4.7
- 作者:
Mehmet Belgin;C. Ribbens;Godmar Back - 通讯作者:
Godmar Back
A data‐driven support strategy for a sustainable research software repository
可持续研究软件存储库的数据驱动支持策略
- DOI:
10.1002/cpe.5338 - 发表时间:
2019 - 期刊:
- 影响因子:0
- 作者:
Mehmet Belgin;Tyler A. Perini;F. Liu;Nuyun Zhang;Semir Sarajlic;A. McNeill;Paul D. Manno;Neil Bright - 通讯作者:
Neil Bright
Operation Stacking for Ensemble Computations With Variable Convergence
具有可变收敛性的集成计算的操作堆栈
- DOI:
10.1177/1094342009347892 - 发表时间:
2010 - 期刊:
- 影响因子:0
- 作者:
Mehmet Belgin;Godmar Back;C. Ribbens - 通讯作者:
C. Ribbens
Structure-based Optimizations for Sparse Matrix-Vector Multiply
基于结构的稀疏矩阵向量乘法优化
- DOI:
- 发表时间:
2010 - 期刊:
- 影响因子:0
- 作者:
Mehmet Belgin - 通讯作者:
Mehmet Belgin
Phoenix: The Revival of Research Computing and the Launch of the New Cost Model at Georgia Tech
凤凰城:佐治亚理工学院研究计算的复兴和新成本模型的推出
- DOI:
- 发表时间:
2022 - 期刊:
- 影响因子:0
- 作者:
A. Jezghani;Semir Sarajlic;Michael Brandon;Neil Bright;Mehmet Belgin;Gregory L. Beyer;Christopher Blanton;Pamela J. Buffington;J. Coulter;Rubén Lara;L. Lefton;David Leonard;F. Liu;Kevin Manalo;Paul D. Manno;Craig A. Moseley;Trever C. Nightingale;N. B. Bonner;Ronald Rahaman;Christopher P. Stone;Kenneth J. Suda;Peter Wan;Michael D. Weiner;Deirdre Womack;Nuyun Zhang;Dan Zhou - 通讯作者:
Dan Zhou
Mehmet Belgin的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
相似海外基金
CC* Campus Compute: UTEP Cyberinfrastructure for Scientific and Machine Learning Applications
CC* 校园计算:用于科学和机器学习应用的 UTEP 网络基础设施
- 批准号:
2346717 - 财政年份:2024
- 资助金额:
$ 39.99万 - 项目类别:
Standard Grant
SHF: Small: Redesigning the Memory System in the Era of Compute Express Link
SHF:小型:重新设计 Compute Express Link 时代的内存系统
- 批准号:
2333049 - 财政年份:2024
- 资助金额:
$ 39.99万 - 项目类别:
Standard Grant
MYRTUS: Multi-layer 360° dYnamic orchestrion and interopeRable design environmenT for compute-continUum Systems
MYRTUS:用于连续计算系统的多层 360° 动态编排和可互操作设计环境
- 批准号:
10087666 - 财政年份:2024
- 资助金额:
$ 39.99万 - 项目类别:
EU-Funded
CC* Campus Compute: Interdisciplinary GPU-Enabled Compute
CC* 校园计算:支持 GPU 的跨学科计算
- 批准号:
2346343 - 财政年份:2024
- 资助金额:
$ 39.99万 - 项目类别:
Standard Grant
CC* Campus Compute: Building a Computational Cluster for Scientific Discovery
CC* 校园计算:构建科学发现计算集群
- 批准号:
2346673 - 财政年份:2024
- 资助金额:
$ 39.99万 - 项目类别:
Standard Grant
CAREER: Reinventing Computer Vision through Bio-inspired Retinomorphic Vision Sensors, Corticomorphic Compute-In-Memory Processors and Event-based Algorithms
职业:通过仿生视网膜形态视觉传感器、皮质形态内存计算处理器和基于事件的算法重塑计算机视觉
- 批准号:
2338171 - 财政年份:2024
- 资助金额:
$ 39.99万 - 项目类别:
Continuing Grant
Equipment: CC* Campus Compute: A High-Performance Computing System for Research and Education in Arkansas
设备:CC* 校园计算:用于阿肯色州研究和教育的高性能计算系统
- 批准号:
2346752 - 财政年份:2024
- 资助金额:
$ 39.99万 - 项目类别:
Standard Grant
Research Infrastructure: CC* Campus Compute: Lawrence 2.0: Advancing Multi-Disciplinary Research and Education in South Dakota
研究基础设施:CC* 校园计算:Lawrence 2.0:推进南达科他州的多学科研究和教育
- 批准号:
2346643 - 财政年份:2024
- 资助金额:
$ 39.99万 - 项目类别:
Standard Grant
DS Compute- Designing solutions for the future of computing
DS Compute - 为未来计算设计解决方案
- 批准号:
10050415 - 财政年份:2023
- 资助金额:
$ 39.99万 - 项目类别:
Collaborative R&D
A Reconfigurable Neuromorphic Compute System for Brain-Scale Simulations
用于大脑规模模拟的可重构神经形态计算系统
- 批准号:
LE230100034 - 财政年份:2023
- 资助金额:
$ 39.99万 - 项目类别:
Linkage Infrastructure, Equipment and Facilities