• DocumentCode
    572221
  • Title

    SRAM-DRAM hybrid memory with applications to efficient register files in fine-grained multi-threading

  • Author

    Yu, Wing-kei S. ; Huang, Ruirui ; Xu, Sarah Q. ; Wang, Sung-En ; Kan, Edwin ; Suh, G. Edward

  • Author_Institution
    Cornell Univ., Ithaca, NY, USA
  • fYear
    2011
  • fDate
    4-8 June 2011
  • Firstpage
    247
  • Lastpage
    258
  • Abstract
    Large register files are common in highly multi-threaded architectures such as GPUs. This paper presents a hybrid memory design that tightly integrates embedded DRAM into SRAM cells with a main application to reducing area and power consumption of multi-threaded register files. In the hybrid memory, each SRAM cell is augmented with multiple DRAM cells so that multiple bits can be stored in each cell. This configuration results in significant area and energy savings compared to the SRAM array with the same capacity due to compact DRAM cells. On other hand, the hybrid memory requires explicit data movements in order to access DRAM contexts. In order to minimize context switching impact, we introduce write-back buffers, background context switching, and context-aware thread scheduling, to the processor pipeline and the scheduler. Circuit and architecture simulations of GPU benchmarks suites show significant savings in register file area (38%) and energy (68%) over the traditional SRAM implementation, with minimal (1.4%) performance loss.
  • Keywords
    DRAM chips; SRAM chips; buffer storage; circuit simulation; graphics processing units; integrated circuit design; multi-threading; pipeline processing; scheduling; GPU benchmarks; SRAM-DRAM hybrid memory design; architecture simulations; area reduction; background context switching; circuit simulations; context switching impact minimization; context-aware thread scheduling; explicit data movements; fine-grained multithreading; multithreaded register files; power consumption reduction; processor pipeline; scheduler; write-back buffers; Arrays; Context; Graphics processing unit; Pipelines; Random access memory; Registers; Switches; DRAM; Fine-grain multithreading; GPGPU; GPU; Hybrid memory; Memory; Register file; SRAM;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Architecture (ISCA), 2011 38th Annual International Symposium on
  • Conference_Location
    San Jose, CA
  • ISSN
    1063-6897
  • Print_ISBN
    978-1-4503-0472-6
  • Type

    conf

  • Filename
    6307179