Architecting Optically Controlled Phase Change Memory

被引:12
作者
Narayan, Aditya [1 ]
Thonnart, Yvain [2 ]
Vivet, Pascal [2 ]
Coskun, Ayse [1 ]
Joshi, Ajay [1 ]
机构
[1] Boston Univ, 8 St Marys St, Boston, MA 02215 USA
[2] Univ Grenoble Alpes, List, CEA, Grenoble, France
关键词
Phase Change Memory; silicon-photonics; 2.5D computing system; non-volatile memory; RANDOM-ACCESS MEMORY; SILICON PHOTONICS; RING-RESONATOR; ENERGY; DESIGN; MODEL; POWER; INTERCONNECTS; PERFORMANCE; STRATEGIES;
D O I
10.1145/3533252
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Phase Change Memory (PCM) is an attractive candidate for main memory, as it offers non-volatility and zero leakage power while providing higher cell densities, longer data retention time, and higher capacity scaling compared to DRAM. In PCM, data is stored in the crystalline or amorphous state of the phase change material. The typical electrically controlled PCM (EPCM), however, suffers from longer write latency and higher write energy compared to DRAM and limited multi-level cell (MLC) capacities. These challenges limit the performance of data-intensive applications running on computing systems with EPCMs. Recently, researchers demonstrated optically controlled PCM (OPCM) cells with support for 5 bits/cell in contrast to 2 bits/cell in EPCM. These OPCM cells can be accessed directly with optical signals that are multiplexed in high-bandwidth-density silicon-photonic links. The higher MLC capacity in OPCM and the direct cell access using optical signals enable an increased read/write throughput and lower energy per access than EPCM. However, due to the direct cell access using optical signals, OPCM systems cannot be designed using conventional memory architecture. We need a complete redesign of the memory architecture that is tailored to the properties of OPCM technology. This article presents the design of a unified network and main memory system called COSMOS that combines OPCM and silicon-photonic links to achieve high memory throughput. COSMOS is composed of a hierarchical multi-banked OPCM array with novel read and write access protocols. COSMOS uses an Electrical-Optical-Electrical (E-O-E) control unit to map standard DRAM read/write commands (sent in electrical domain) from the memory controller on to optical signals that access the OPCM cells. Our evaluation of a 2.5D-integrated system containing a processor and COSMOS demonstrates 2.14x average speedup across graph and HPC workloads compared to an EPCM system. COSMOS consumes 3.8x lower read energy-per-bit and 5.97x lower write energy-per-bit compared to EPCM. COSMOS is the first non-volatile memory that provides comparable performance and energy consumption as DDR5 in addition to increased bit density, higher area efficiency, and improved scalability.
引用
收藏
页数:26
相关论文
共 102 条
  • [1] Adaptive Tuning of Photonic Devices in a Photonic NoC Through Dynamic Workload Allocation
    Abellan, Jose L.
    Coskun, Ayse K.
    Gu, Anjun
    Jin, Warren
    Joshi, Ajay
    Kahng, Andrew B.
    Klamkin, Jonathan
    Morales, Cristian
    Recchio, John
    Srinivas, Vaishnav
    Zhang, Tiansheng
    [J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2017, 36 (05) : 801 - 814
  • [2] A Survey on Homomorphic Encryption Schemes: Theory and Implementation
    Acar, Abbas
    Aksu, Hidayet
    Uluagac, A. Selcuk
    Conti, Mauro
    [J]. ACM COMPUTING SURVEYS, 2018, 51 (04)
  • [3] Alduino Andrew, 2010, P INTEGRATED PHOTONI
  • [4] [Anonymous], 2014, The Memory Forum.
  • [5] [Anonymous], 2014, P 2014 51 ACMEDACIEE, DOI DOI 10.1109/DAC.2014.6881363
  • [6] [Anonymous], DDR4 AREA
  • [7] Boosting Access Parallelism to PCM-based Main Memory
    Arjomand, Mohammad
    Kandemir, Mahmut T.
    Sivasubramaniam, Anand
    Das, Chita R.
    [J]. 2016 ACM/IEEE 43RD ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA), 2016, : 695 - 706
  • [8] Brown TB, 2020, Arxiv, DOI arXiv:2005.14165
  • [9] Bahadori M, 2016, OPT INTERCONNECT C, P2, DOI 10.1109/OIC.2016.7483019
  • [10] THE NAS PARALLEL BENCHMARKS
    BAILEY, DH
    BARSZCZ, E
    BARTON, JT
    BROWNING, DS
    CARTER, RL
    DAGUM, L
    FATOOHI, RA
    FREDERICKSON, PO
    LASINSKI, TA
    SCHREIBER, RS
    SIMON, HD
    VENKATAKRISHNAN, V
    WEERATUNGA, SK
    [J]. INTERNATIONAL JOURNAL OF SUPERCOMPUTER APPLICATIONS AND HIGH PERFORMANCE COMPUTING, 1991, 5 (03): : 63 - 73