Galaxy: A High-Performance Energy-Efficient Multi-Chip Architecture Using Photonic Interconnects

被引:39
|
作者
Demir, Yigit [1 ]
Pan, Yan [2 ]
Song, Seukwoo [3 ]
Hardavellas, Nikos [1 ]
Kim, John [3 ]
Memik, Gokhan [1 ]
机构
[1] Northwestern Univ, Dept Elect Engn & Comp Sci, Evanston, IL 60208 USA
[2] Globalfoundries Inc, Malta, NY USA
[3] Korea Adv Inst Sci & Technol, Dept Comp Sci, Daejeon, South Korea
关键词
Interconnection Networks; Nanophotonics; Energy Efficiency; SILICON;
D O I
10.1145/2597652.2597664
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
The scalability trends of modern semiconductor technology lead to increasingly dense multicore chips. Unfortunately, physical limitations in area, power, off-chip bandwidth, and yield constrain single-chip designs to a relatively small number of cores, beyond which scaling becomes impractical. Multi-chip designs overcome these constraints, and can reach scales impossible to realize with conventional single-chip architectures. However, to deliver commensurate performance, multi-chip architectures require a cross chip interconnect with bandwidth, latency, and energy consumption well beyond the reach of electrical signaling. We propose Galaxy, an architecture that enables the construction of a many-core "virtual chip" by connecting multiple smaller chiplets through optical fibers. The low optical loss of fibers allows the flexible placement of chiplets, and offers simpler packaging, power; and heat requirements. At the same time, the low latency and high bandwidth density of optical signaling maintain the tight coupling of cores, allowing the virtual chip to match the performance of a single chip that is not subject to area, power; and bandwidth limitations. Our results indicate that Galaxy attains speedup of 2.2x over the best single-chip alternatives with electrical or photonic interconnects (3.4x maximum), and 2.6x smaller energy-delay product (6.8x maximum). We show that Galaxy scales to 4K cores and attains 2.5x speedup at 6x lower laser power compared to a Macrochip with silicon waveguides.
引用
收藏
页码:303 / 312
页数:10
相关论文
共 50 条
  • [1] A High-Performance and Energy-Efficient Photonic Architecture for Multi-DNN Acceleration
    Li, Yuan
    Louri, Ahmed
    Karanth, Avinash
    [J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2024, 35 (01) : 46 - 58
  • [2] Tools and Methodologies for Designing Energy-Efficient Photonic Networks-on-Chip for High-Performance Chip Multiprocessors
    Chan, Johnnie
    Hendry, Gilbert
    Biberman, Aleksandr
    Bergman, Keren
    [J]. 2010 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, 2010, : 3605 - 3608
  • [3] The effect of corrosion on the performance of high speed multi-chip module interconnects
    Guan, L
    Christou, A
    Barbe, DF
    [J]. QUALITY AND RELIABILITY ENGINEERING INTERNATIONAL, 2000, 16 (04) : 255 - 260
  • [4] Towards Energy-Efficient Photonic Interconnects
    Demir, Yigit
    Hardavellas, Nikos
    [J]. OPTICAL INTERCONNECTS XV, 2015, 9368
  • [5] SPRINT: A High-Performance, Energy-Efficient, and Scalable Chiplet-Based Accelerator With Photonic Interconnects for CNN Inference
    Li, Yuan
    Louri, Ahmed
    Karanth, Avinash
    [J]. IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2022, 33 (10) : 2332 - 2345
  • [6] EcoLaser: An Adaptive Laser Control for Energy-Efficient On-Chip Photonic Interconnects
    Demir, Yigit
    Hardavellas, Nikos
    [J]. PROCEEDINGS OF THE 2014 IEEE/ACM INTERNATIONAL SYMPOSIUM ON LOW POWER ELECTRONICS AND DESIGN (ISLPED), 2014, : 3 - 8
  • [7] A High-Performance, Energy-Efficient Modular DMA Engine Architecture
    Benz, Thomas
    Rogenmoser, Michael
    Scheffler, Paul
    Riedel, Samuel
    Ottaviano, Alessandro
    Kurth, Andreas
    Hoefler, Torsten
    Benini, Luca
    [J]. IEEE TRANSACTIONS ON COMPUTERS, 2024, 73 (01) : 263 - 277
  • [8] A Micro-architectural Analysis of Switched Photonic Multi-chip Interconnects
    Koka, Pranay
    McCracken, Michael O.
    Schwetman, Herb
    Chen, Chia-Hsin Owen
    Zheng, Xuezhe
    Ho, Ron
    Raj, Kannan
    Krishnamoorthy, Ashok V.
    [J]. 2012 39TH ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA), 2012, : 153 - 164
  • [9] Silicon Photonic Multi-Chip Module Interconnects for Disaggregated Data Centers
    Abrams, Nathan C.
    Glick, Madeleine
    Bergman, Keren
    [J]. 2020 INTERNATIONAL CONFERENCE ON OPTICAL NETWORK DESIGN AND MODELING (ONDM), 2020,
  • [10] Energy-Efficient and High-Performance Software Architecture for Storage Class Memory
    Baek, Seungjae
    Choi, Jongmoo
    Lee, Donghee
    Noh, Sam H.
    [J]. ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS, 2013, 12 (03)