Rationale for a 3D Heterogeneous Multi-core Processor

被引:0
|
作者
Rotenberg, Eric [1 ]
Dwiel, Brandon H. [1 ]
Forbes, Elliott [1 ]
Zhang, Zhenqian [1 ]
Widialaksono, Randy [1 ]
Chowdhury, Rangeen Basu Roy [1 ]
Tshibangu, Nyunyi [1 ]
Lipa, Steve [1 ]
Davis, W. Rhett [1 ]
Franzon, Paul D. [1 ]
机构
[1] N Carolina State Univ, Dept Elect & Comp Engn, Raleigh, NC 27695 USA
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Single-ISA heterogeneous multi-core processors are comprised of multiple core types that are functionally equivalent but microarchitecturally diverse. This paradigm has gained a lot of attention as a way to optimize performance and energy. As the instruction-level behavior of the currently executing program varies, it is migrated to the most efficient core type for that behavior. This paper makes a case for implementing a heterogeneous multi-core processor via 3D die stacking. The case is framed from three angles: product strategy, architecture, and physical design. Product strategy: Die stacking enables plug-andplay composition of heterogeneous processors from homogeneous designs, a more efficient product customization strategy than fabricating dedicated 2D heterogeneous processors. Architecture: Frequent thread migrations substantially increase the benefits of microarchitectural diversity, but only if migration can be done with very low overhead. Thus, fast transfer of architectural state and uninterrupted access to accumulated microarchitectural state are essential. Physical design: Exchanging/referencing state between cores with low latency requires many new wires that must also be as short as possible, introducing intense physical design pressures and tradeoffs in a 2D layout that are diminished in a 3D layout. We are currently researching applications and fabricating prototypes of "H3", a 3D heterogeneous multi-core processor. H3's salient features include: two core types for optimizing latency and energy; a power management unit (PMU) that schedules migrations; fast thread migration (FTM) and cachecore decoupling (CCD) via face-to-face, microbump based buses; face-to-back, through-silicon-via (TSV) based buses connecting the core stacks to stacked L2 DRAM cache. The H3 project spans applications, processor architecture, circuits, logic and physical design/verification, design automation, fabrication and post-silicon validation. There are close interactions among all elements, both in terms of executing the project and in empirically justifying 3D-enabled heterogeneity. Thus, H3 is illustrative of the multi-disciplinary mission of this conference proceedings, the International Conference on Computer Design.
引用
收藏
页码:154 / 168
页数:15
相关论文
共 50 条
  • [21] Study on Static Task Scheduling Based on Heterogeneous Multi-Core Processor
    Shen Yang
    Qi Deyu
    [J]. 2017 INTERNATIONAL CONFERENCE ON COMPUTER NETWORK, ELECTRONIC AND AUTOMATION (ICCNEA), 2017, : 180 - 182
  • [22] Interconnection of Godson-3 multi-core processor
    Wang, Huandong
    Gao, Xiang
    Chen, Yunji
    Hu, Weiwu
    [J]. Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2008, 45 (12): : 2001 - 2010
  • [23] Multi-core virtualization on loongson-3 processor
    Ruan, Li
    Xu, Peng
    Wang, Hui-Xiang
    Zhu, Ming-Fa
    Xiao, Li-Min
    Tang, Hao-Fu
    [J]. Ruan Jian Xue Bao/Journal of Software, 2013, 24 (SUPPL.2): : 127 - 139
  • [24] Thermal-aware 3D multi-core processor design using core and level-2 cache placement
    Son, Dong Oh
    Choi, Hong Jun
    Jeon, Hyung Gyu
    Kim, Cheol Hong
    [J]. International Journal of Control and Automation, 2013, 6 (01): : 25 - 32
  • [25] Thermal-Aware On-Line Task Allocation for 3D Multi-Core Processor Throughput Optimization
    Lung, Chiao-Ling
    Ho, Yi-Lun
    Kwai, Ding-Ming
    Chang, Shih-Chieh
    [J]. 2011 DESIGN, AUTOMATION & TEST IN EUROPE (DATE), 2011, : 8 - 13
  • [26] The Impact of Liquid Cooling on 3D Multi-Core Processors
    Jang, Hyung Beom
    Yoon, Ikroh
    Kim, Cheol Hong
    Shin, Seungwon
    Chung, Sung Woo
    [J]. 2009 IEEE INTERNATIONAL CONFERENCE ON COMPUTER DESIGN, 2009, : 472 - +
  • [27] Data driven multi-core processor
    [J]. Bi, Z. (zhuo.bi@shu.edu.cn), 1600, Shanghai Jiaotong University (47):
  • [28] Modal parallel algorithm based on Shenwei heterogeneous multi-core processor architecture
    Yu, Gaoyuan
    Ma, Zhiqiang
    Li, Junjie
    Jin, Xianlong
    [J]. Zhendong yu Chongji/Journal of Vibration and Shock, 2022, 41 (03): : 224 - 230
  • [29] Evaluation of partitioning methods for stream applications on a heterogeneous multi-core processor simulator
    Zheng, Kai
    Zhu, Yongxin
    Xu, Jun
    [J]. EUC 2008: PROCEEDINGS OF THE 5TH INTERNATIONAL CONFERENCE ON EMBEDDED AND UBIQUITOUS COMPUTING, VOL 2, WORKSHOPS, 2008, : 486 - 491
  • [30] The Design of Microkernel Memory Management Mechanism Based on Heterogeneous Multi-core Processor
    Yun, Deng
    Yan, Zhu
    Cheng Xiaohui
    [J]. ICIIP'18: PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON INTELLIGENT INFORMATION PROCESSING, 2018, : 120 - 126