Non-volatile Memory Page Allocation Mechanism

With the current demand for large-capacity, easy-to-expand, and low-power high-performance memory systems, the current memory systems continue to have problems such as high static power consumption, small DRAM capacity, and low scalability, New nonvolatile The emergence of the non-volatile memory provides the possibility to solve these restrictions. Although the new non-volatile memory has the characteristics of low static power consumption, non-volatile, and high scalability, but the memory cell has a limited number of writes, poor tolerance, and large access delay. The access performance is also inferior to DRAM. Therefore, NVM cannot completely replace DRAM as the main memory. Generally, unified addressing is used to form hybrid memory by taking advantage of their own advantages, In recent years, a lot of research has been done on a hybrid memory system composed of DRAM and non-volatile memory has achieved research results. This article mainly introduces the page classification of hybrid memory based on NVM and how to select the free page that is most similar to the requested page as the allocation page. and experiments have verified that the mechanism can effectively reduce bit flipping and writing Number, thereby reducing the write energy consumption of the hybrid memory system, the experimental results show that the average energy consumption of the hybrid memory energy consumption optimization and management scheme based on the system architecture is reduced by about 27.3%.

[1]  Naehyuck Chang,et al.  PTL: PCM Translation Layer , 2012, 2012 IEEE Computer Society Annual Symposium on VLSI.

[2]  Jun Yang,et al.  Improving write operations in MLC phase change memory , 2012, IEEE International Symposium on High-Performance Comp Architecture.

[3]  Sivan Toledo,et al.  Phase-change memory: An architectural perspective , 2013, CSUR.

[4]  Hyunjin Lee,et al.  Flip-N-Write: A simple deterministic technique to improve PRAM write performance, energy and endurance , 2009, 2009 42nd Annual IEEE/ACM International Symposium on Microarchitecture (MICRO).

[5]  Yiran Chen,et al.  Exploration of GPGPU register file architecture using domain-wall-shift-write based racetrack memory , 2014, 2014 51st ACM/EDAC/IEEE Design Automation Conference (DAC).

[6]  Jun Yang,et al.  A durable and energy efficient main memory using phase change memory technology , 2009, ISCA '09.

[7]  Onur Mutlu,et al.  Memory scaling: A systems architecture perspective , 2013, 2013 5th IEEE International Memory Workshop.

[8]  Wei Xu,et al.  Data manipulation techniques to reduce phase change memory write energy , 2009, ISLPED.

[9]  Paolo Cappelletti,et al.  Non volatile memory evolution and revolution , 2015, 2015 IEEE International Electron Devices Meeting (IEDM).

[10]  Yiran Chen,et al.  Emerging non-volatile memories: Opportunities and challenges , 2011, 2011 Proceedings of the Ninth IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS).

[11]  Dmitri B. Strukov,et al.  Memristors for neural branch prediction: a case study in strict latency and write endurance challenges , 2013, CF '13.