Affiliation:
1. University of Rochester, Rochester, NY
Abstract
Modern memory controllers employ sophisticated address mapping, command scheduling, and power management optimizations to alleviate the adverse effects of DRAM timing and resource constraints on system performance. A promising way of improving the versatility and efficiency of these controllers is to make them programmable---a proven technique that has seen wide use in other control tasks ranging from DMA scheduling to NAND Flash and directory control. Unfortunately, the stringent latency and throughput requirements of modern DDRx devices have rendered such programmability largely impractical, confining DDRx controllers to fixed-function hardware.
This paper presents the instruction set architecture (ISA) and hardware implementation of PARDIS, a programmable memory controller that can meet the performance requirements of a high-speed DDRx interface. The proposed controller is evaluated by mapping previously proposed DRAM scheduling, address mapping, refresh scheduling, and power management algorithms onto PARDIS. Simulation results show that the average performance of PARDIS comes within 8% of fixed-function hardware for each of these techniques; moreover, by enabling application-specific optimizations, PARDIS improves system performance by 6--17% and reduces DRAM energy by 9--22% over four existing memory controllers.
Publisher
Association for Computing Machinery (ACM)
Reference40 articles.
1. A fully-programmable memory management system optimizing queue handling at multi gigabit rates
2. Micron Technology Inc. TN-29-14: Increasing NAND Flash Performance Functionality 2009. http://www.micron.com/get-document/?documentId=140. Micron Technology Inc. TN-29-14: Increasing NAND Flash Performance Functionality 2009. http://www.micron.com/get-document/?documentId=140.
Cited by
12 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. CLAY: CXL-based Scalable NDP Architecture Accelerating Embedding Layers;Proceedings of the 38th ACM International Conference on Supercomputing;2024-05-30
2. DRAM Bender: An Extensible and Versatile FPGA-Based Infrastructure to Easily Test State-of-the-Art DRAM Chips;IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems;2023-12
3. NDIE: A Near DRAM Inference Engine Exploiting DIMM's Parallelism;2023 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS);2023-11-19
4. An In-Module Disturbance Barrier for Mitigating Write Disturbance in Phase-Change Memory;IEEE Transactions on Computers;2023-04-01
5. ReTagger;Proceedings of the 56th Annual Design Automation Conference 2019;2019-06-02