A Photonic-Electronic non-von Neumann Processor Core for Highly Efficient Computing (APT-NuCOM)

用于高效计算的光子电子非冯诺依曼处理器核心（APT-NuCOM）

• 批准号: EP/W022931/1
• 负责人: C Wright
• 金额: $ 146.33万
• 依托单位: UNIVERSITY OF EXETER
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2023
• 资助国家: 英国
• 起止时间: 2023 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FW022931%2F1
• 关键词: Photonic; Electronic; non; von; Neumann

Modern society depends massively on the generation, processing and transmission of vast amounts of data. It is predicted that by 2025, 175 zettabytes (175 trillion gigabytes) of data will be generated around the globe, with so-called 'edge computing' devices creating more than 90 zettabytes alone. Processing such huge amounts of data demands ever increasing computational power, memory and communication bandwidth - demands that cannot be sustainably met by conventional digital electronic technologies. The growing gap between the needs and the capabilities of today's information technology is exemplified if we consider the historical trend in total number of computations (in units of #days of calculating at a rate of 1 PetaFLOP/s) needed to train various artificial intelligence (AI) systems. The trend followed Moore's Law (doubling approximately every two years) until 2012, after which the doubling time reduced to a mere 3.4 months! This trend is compounded by the breakdown in Koomey's Law, which states that the number of computations per Joule of energy doubles around every 1.5 years. This law was also followed until quite recently, but we are now approaching a widely accepted computing efficiency-wall at around 10 GMAC/Joule (a MAC is a multiply-accumulate operation) for CMOS electronics and the von-Neumann architecture. As a result, the energy consumption used in training modern AI systems is truly staggering, with consequent adverse effects for sustainability. This has led to a move away from standard CPU designs in AI towards the use of co-processors - GPUs, ASICs, FPGAs - with superior parallelism.However, even here the limitations of electrical signalling lead to massive levels of energy consumption. It was recently estimated, for example, that the training of a large GPU-based natural language processing system used for accurate machine translation resulted in carbon dioxide emissions equivalent to lifetime use of 5 cars! Clearly, a new approach is needed. Thus, in the APT-NuCOM project we will develop a highly efficient novel non-von Neumann co-processor that exploits clear advantages offered by photonic computation, but at the same time links seamlessly with the electronic domain to enable integration with existing electronic computing infrastructure. The APT-NuCOM co-processor will exploit novel phase-change photonic in-memory computing concepts to deliver massively parallel computation at PetaMAC/s speeds and, ultimately, an energy budget approaching that of the human brain.

现代社会在很大程度上依赖于海量数据的产生、处理和传输。据预测，到2025年，全球将产生175 ZB(175万亿GB)的数据，仅所谓的边缘计算设备就产生了超过90 ZB的数据。处理如此海量的数据需要不断增加的计算能力、内存和通信带宽--这是传统数字电子技术无法持续满足的要求。如果我们考虑一下训练各种人工智能(AI)系统所需的总计算量(以#天为单位，以1Petaflop/S的速度计算)的历史趋势，就可以看出当今信息技术的需求和能力之间的日益扩大的差距。这一趋势遵循摩尔定律(大约每两年翻一番)，直到2012年，翻一番的时间减少到仅3.4个月！库米定律的崩溃加剧了这一趋势，该定律指出，每焦耳能量的计算次数大约每1.5年翻一番。这一定律直到最近才得到遵守，但我们现在正在接近被广泛接受的计算效率墙，大约为10GMAC/Joule(MAC是乘法累加运算)，适用于CMOS电子学和冯-诺伊曼体系结构。因此，用于训练现代人工智能系统的能源消耗确实令人震惊，从而对可持续性产生不利影响。这导致了人工智能从标准的CPU设计转向使用具有卓越并行性的协处理器--GPU、ASIC、FPGA。然而，即使在这里，电子信号的限制也导致了巨大的能量消耗水平。例如，最近估计，用于准确机器翻译的基于GPU的大型自然语言处理系统的培训导致的二氧化碳排放量相当于5辆汽车的终生使用量！显然，需要一种新的方法。因此，在APT-NuCOM项目中，我们将开发一种高效的新型非冯·诺伊曼协处理器，它利用光子计算提供的明显优势，同时与电子领域无缝连接，实现与现有电子计算基础设施的集成。APT-NUCOM协处理器将利用新颖的相变光子内存计算概念，以PetaMAC/S的速度提供大规模并行计算，最终实现接近人脑的能量预算。

项目成果

Reduced rank photonic computing accelerator

降阶光子计算加速器

• DOI: 10.1364/optica.485883
• 发表时间: 2023
• 期刊: Optica
• 影响因子: 10.4
• 作者: Aggarwal S

Silicon Ring Resonator with Phase-Change Material as a Plastic Dynamical Node for Scalable All-Optical Neural Networks with Synaptic Plasticity

采用相变材料作为塑性动态节点的硅环谐振器，用于具有突触可塑性的可扩展全光神经网络

• DOI: 10.1109/icton59386.2023.10207385
• 发表时间: 2023
• 作者: Lugnan A

Hybrid Electro-Optic Crossbar Array for Matrix-Vector Multiplications

• DOI: 10.1364/cleo_si.2023.sf3e.8
• 发表时间: 2023-05
• 期刊: 2023 Conference on Lasers and Electro-Optics (CLEO)
• 作者: Frank Brückerhoff-Plückelmann;I. Bente;Daniel Wendland;J. Feldmann;C. D. Wright;H. Bhaskaran;W. Pernice

High-Quality Amorphous Silicon Carbide for Hybrid Photonic Integration Deposited at a Low Temperature.

• DOI: 10.1021/acsphotonics.3c00968
• 发表时间: 2023-10-18
• 期刊: ACS PHOTONICS
• 影响因子: 7
• 作者: Lopez-Rodriguez, Bruno;van der Kolk, Roald;Aggarwal, Samarth;Sharma, Naresh;Li, Zizheng;van der Plaats, Daniel;Scholte, Thomas;Chang, Jin;Gro''blacher, Simon;Pereira, Silvania F.;Bhaskaran, Harish;Zadeh, Iman Esmaeil
• 通讯作者: Zadeh, Iman Esmaeil

Optical switching dynamics of sub-micrometer Sb2Se3 thin films for active photonics

用于主动光子学的亚微米 Sb2Se3 薄膜的光学开关动力学

• DOI: 10.1117/12.2682125
• 发表时间: 2023
• 作者: Lawson D