Collaborative Research: SHF: Small: Architecture Innovations for Enabling Simultaneous Translation at the Edge
合作研究:SHF:小型:支持边缘同步翻译的架构创新
基本信息
- 批准号:2223484
- 负责人:
- 金额:$ 15万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2022
- 资助国家:美国
- 起止时间:2022-10-01 至 2025-09-30
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
Simultaneous translation, which begins translating after just a few words are spoken, has significant real-world value that may disrupt and benefit a wide range of domains, such as military personnel deployed in foreign countries, businesspeople participating in multilingual meetings, medical service providers, law enforcement, customer support services, diplomats and political representatives, and countless international tourists. Currently, accurate real-time simultaneous translation is only possible by expensive, specially trained human interpreters or by running machine learning-based algorithms on server-grade graphics processing units (GPUs); both options are impractical for extensive and ubiquitous deployment of simultaneous translation in edge devices. Innovative domain-specific architecture needs to be designed that can reduce computation requirements by orders of magnitude while maintaining translation accuracy, thus enabling simultaneous translation at the edge.This research investigates the challenges and opportunities in designing hardware accelerators for transformer-based simultaneous translation. The objective is to utilize the unique characteristics of transformer models and the distinctive behaviors of simultaneous translation to develop cross-cutting solutions that meet the accuracy, latency, power, and resource efficiency goals. Among some of the specific lines of research that are explored include input-centric dataflow and data reuse that take advantage of extensive input data sharing, compute-proportional architecture that aims to achieve linearly scalable attention calculation, utility-driven linear transformation architecture that efficiently reduce dimensionality based on their actual utility, and customized routerless on-chip interconnects that provide scalable, flexible and ultra-low cost interconnects for simultaneous translation accelerators. Beyond specific technical contributions that advance the fields of computer architecture and natural language processing, this project also impacts more broadly on research, education, and outreach. Findings from this research are incorporated into graduate curricula, courses, and undergraduate research experiences. Various outreach activities have been planned to broaden inclusion and participation of diverse populations in the educational and societal impacts of this project.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.
同声传译只需说几句话就能开始翻译,它具有重大的现实价值,可能会扰乱广泛的领域,并使其受益,例如部署在外国的军事人员、参加多语言会议的商人、医疗服务提供商、执法部门、客户支持服务、外交官和政治代表,以及无数的国际游客。目前,准确的实时同声翻译只能由昂贵的、经过专门培训的人工口译员或通过在服务器级图形处理单元(GPU)上运行基于机器学习的算法来实现;对于在边缘设备中广泛和普遍地部署同声翻译来说,这两种选择都是不切实际的。需要设计创新的特定领域的体系结构,在保持翻译精度的同时,将计算量减少几个数量级,从而在边缘实现同声翻译。其目的是利用变压器模型的独特特性和同声传译的独特行为来开发满足准确性、延迟、功耗和资源效率目标的横切解决方案。在所探索的一些特定研究领域中,包括利用广泛的输入数据共享的以输入为中心的数据流和数据重用、旨在实现线性可扩展注意力计算的计算比例体系结构、基于其实际效用有效降维的效用驱动的线性变换体系结构、以及为同声翻译加速器提供可扩展、灵活和超低成本的可扩展、灵活和超低成本的定制的无路由片上互连。除了推动计算机体系结构和自然语言处理领域的具体技术贡献外,该项目还对研究、教育和推广产生了更广泛的影响。这项研究的结果被纳入研究生课程、课程和本科生研究经验。已经计划了各种外展活动,以扩大不同人群对该项目的教育和社会影响的包容和参与。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 }}
Timothy Pinkston其他文献
Timothy Pinkston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 }}
{{ truncateString('Timothy Pinkston', 18)}}的其他基金
SHF: Small: Collaborative Research: Design of Many-core NoCs for the Dark Silicon Era
SHF:小型:协作研究:暗硅时代的多核 NoC 设计
- 批准号:
1619472 - 财政年份:2016
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
SHF: Small: Enhancing Power, Performance, and Resource Efficiency of Many-core NoCs
SHF:小型:增强多核 NoC 的功耗、性能和资源效率
- 批准号:
1321131 - 财政年份:2013
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
EAGER: Network-Driven Shared Resource Design and Management in Multicores
EAGER:多核中网络驱动的共享资源设计和管理
- 批准号:
0946388 - 财政年份:2009
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
Investigation of Reliability-Constrained On-Chip Networks
可靠性受限片上网络的研究
- 批准号:
0541417 - 财政年份:2006
- 资助金额:
$ 15万 - 项目类别:
Continuing Grant
Efficient Adaptive Techniques for Irregular Switch-based Networks
基于不规则交换机的网络的高效自适应技术
- 批准号:
9812137 - 财政年份:1998
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
CAREER: Optically-Interconnected Fully-Adaptive Network Router
职业:光互连全自适应网络路由器
- 批准号:
9624251 - 财政年份:1996
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
System-level Integration of Optics into Multiprocessor Interconnect Architecture
将光学器件系统级集成到多处理器互连架构中
- 批准号:
9411587 - 财政年份:1994
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
相似国自然基金
Research on Quantum Field Theory without a Lagrangian Description
- 批准号:24ZR1403900
- 批准年份:2024
- 资助金额:0.0 万元
- 项目类别:省市级项目
Cell Research
- 批准号:31224802
- 批准年份:2012
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Cell Research
- 批准号:31024804
- 批准年份:2010
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Cell Research (细胞研究)
- 批准号:30824808
- 批准年份:2008
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Research on the Rapid Growth Mechanism of KDP Crystal
- 批准号:10774081
- 批准年份:2007
- 资助金额:45.0 万元
- 项目类别:面上项目
相似海外基金
Collaborative Research: SHF: Small: LEGAS: Learning Evolving Graphs At Scale
协作研究:SHF:小型:LEGAS:大规模学习演化图
- 批准号:
2331302 - 财政年份:2024
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Small: LEGAS: Learning Evolving Graphs At Scale
协作研究:SHF:小型:LEGAS:大规模学习演化图
- 批准号:
2331301 - 财政年份:2024
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Differentiable Hardware Synthesis
合作研究:SHF:媒介:可微分硬件合成
- 批准号:
2403134 - 财政年份:2024
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Small: Efficient and Scalable Privacy-Preserving Neural Network Inference based on Ciphertext-Ciphertext Fully Homomorphic Encryption
合作研究:SHF:小型:基于密文-密文全同态加密的高效、可扩展的隐私保护神经网络推理
- 批准号:
2412357 - 财政年份:2024
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Enabling Graphics Processing Unit Performance Simulation for Large-Scale Workloads with Lightweight Simulation Methods
合作研究:SHF:中:通过轻量级仿真方法实现大规模工作负载的图形处理单元性能仿真
- 批准号:
2402804 - 财政年份:2024
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Tiny Chiplets for Big AI: A Reconfigurable-On-Package System
合作研究:SHF:中:用于大人工智能的微型芯片:可重新配置的封装系统
- 批准号:
2403408 - 财政年份:2024
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Toward Understandability and Interpretability for Neural Language Models of Source Code
合作研究:SHF:媒介:实现源代码神经语言模型的可理解性和可解释性
- 批准号:
2423813 - 财政年份:2024
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Enabling GPU Performance Simulation for Large-Scale Workloads with Lightweight Simulation Methods
合作研究:SHF:中:通过轻量级仿真方法实现大规模工作负载的 GPU 性能仿真
- 批准号:
2402806 - 财政年份:2024
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Differentiable Hardware Synthesis
合作研究:SHF:媒介:可微分硬件合成
- 批准号:
2403135 - 财政年份:2024
- 资助金额:
$ 15万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Tiny Chiplets for Big AI: A Reconfigurable-On-Package System
合作研究:SHF:中:用于大人工智能的微型芯片:可重新配置的封装系统
- 批准号:
2403409 - 财政年份:2024
- 资助金额:
$ 15万 - 项目类别:
Standard Grant