Loading...

Improving Write Efficiency in MLC PCM Memory

Rashidi, Saeed | 2017

1594 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 49959 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Sarbazi-Azad, Hamid
  7. Abstract:
  8. With increasing number of cores and developing sophisticated applications in today’s computer systems, larger main memory capacity is increasingly demanded. Unfortunately, DRAM cannot satisfy the increasing demand for larger main memory capacity due to its power and scalability limits that makes further scaling of DRAM infeasible. Phase Change Memory (PCM) is one of the most promising candidates to be used at main memory level of the memory hierarchy because it is more scalable, denser, and consumes less standby power compared to DRAM. PCM is a new resistive memory which is capable of storing data based on resistance values. The wide resistance range of PCM allows for storing multiple bits per cell (MLC) rather than a single bit per cell (SLC). Unfortunately, higher density of MLC PCM comes at the expense of longer read/write latency, higher energy consumption and earlier wearout compared to the SLC PCM.In order to deal with the limited lifetime of PCM, some extra storage per memory line is required to correct permanent hard errors (stuck-at faults). Since the extra storage is used only when permanent faults occur, it has a low utilization for a long time before hard errors start to occur. In this paper, we utilize the extra storage to improve the read/write latency in a 2-bit MLC PCM using a relaxation scheme for writing the cells for intermediate resistance levels. Evaluation results show that the proposed scheme improves read latency by 17:4%, write latency by 37:7%, and overall system performance (IPC) by 13:1% over the baseline. It is noteworthy that combining the proposed scheme and FPC compression method improves read latency by 32:7%, write latency by 52:3%, and overall system performance (IPC) by 26:7%
  9. Keywords:
  10. Energy Consumption ; Energy Delay Product ; Phase Change Memory ; Multi-Level Cell Phase Change Memory (MLC-PCM) ; Write Speed ; Approximate Storing

 Digital Object List

 Bookmark

...see more