A programmable memory controller for the DDRx interfacing standards

作者: Mahdi Nazm Bojnordi , Engin Ipek

DOI: 10.1145/2534845

关键词:

摘要: Modern memory controllers employ sophisticated address mapping, command scheduling, and power management optimizations to alleviate the adverse effects of DRAM timing resource constraints on system performance. A promising way improving versatility efficiency these is make them programmable—a proven technique that has seen wide use in other control tasks, ranging from DMA scheduling NAND Flash directory control. Unfortunately, stringent latency throughput requirements modern DDRx devices have rendered such programmability largely impractical, confining fixed-function hardware.This article presents instruction set architecture (ISA) hardware implementation PARDIS, a programmable controller can meet performance high-speed interface. The proposed evaluated by mapping previously refresh algorithms onto PARDIS. Simulation results show average PARDIS comes within 8p for each techniques; moreover, enabling application-specific optimizations, improves 6 17p reduces energy 9 22p over four existing controllers.

参考文章(32)
David H. Bailey, NAS Parallel Benchmarks. parallel computing. pp. 1254- 1259 ,(2011)
Yoongu Kim, Dongsu Han, Onur Mutlu, Mor Harchol-Balter, ATLAS: A scalable and high-performance scheduling algorithm for multiple memory controllers high-performance computer architecture. pp. 1- 12 ,(2010) , 10.1109/HPCA.2010.5416658
Amin Firoozshahian, Alex Solomatnikov, Ofer Shacham, Zain Asgar, Stephen Richardson, Christos Kozyrakis, Mark Horowitz, A memory system design framework Proceedings of the 36th annual international symposium on Computer architecture - ISCA '09. ,vol. 37, pp. 406- 417 ,(2009) , 10.1145/1555754.1555805
Bruno Diniz, Dorgival Guedes, Wagner Meira, Ricardo Bianchini, Limiting the power consumption of main memory Proceedings of the 34th annual international symposium on Computer architecture - ISCA '07. ,vol. 35, pp. 290- 301 ,(2007) , 10.1145/1250662.1250699
L. Dagum, R. Menon, OpenMP: an industry standard API for shared-memory programming computational science and engineering. ,vol. 5, pp. 46- 55 ,(1998) , 10.1109/99.660313
Janani Mukundan, Jose F. Martinez, MORSE: Multi-objective reconfigurable self-optimizing memory scheduler high performance computer architecture. pp. 1- 12 ,(2012) , 10.1109/HPCA.2012.6168945
J. Carter, W. Hsieh, L. Stoller, M. Swanson, Lixin Zhang, E. Brunvand, A. Davis, Chen-Chi Kuo, R. Kuramkote, M. Parker, L. Schaelicke, T. Tateyama, Impulse: building a smarter memory controller high-performance computer architecture. pp. 70- 79 ,(1999) , 10.1109/HPCA.1999.744334
Song Liu, Karthik Pattabiraman, Thomas Moscibroda, Benjamin G. Zorn, Flikker Proceedings of the sixteenth international conference on Architectural support for programming languages and operating systems - ASPLOS '11. ,vol. 47, pp. 213- 224 ,(2011) , 10.1145/1950365.1950391
Richard M. Yoo, Anthony Romano, Christos Kozyrakis, Phoenix rebirth: Scalable MapReduce on a large-scale shared-memory system ieee international symposium on workload characterization. pp. 198- 207 ,(2009) , 10.1109/IISWC.2009.5306783
Niket K. Choudhary, Salil V. Wadhavkar, Tanmay A. Shah, Hiran Mayukh, Jayneel Gandhi, Brandon H. Dwiel, Sandeep Navada, Hashem H. Najaf-abadi, Eric Rotenberg, FabScalar Proceeding of the 38th annual international symposium on Computer architecture - ISCA '11. ,vol. 39, pp. 11- 22 ,(2011) , 10.1145/2000064.2000067