The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.02 - July-Dec. (2012 vol.11)
pp: 33-36
Nagesh B. Lakshminarayana , Georgia Institute of Technology, Atlanta
Jaekyu Lee , Georgia Institute of Technology, Atlanta
Hyesoon Kim , Georgia Institute of Technology, Atlanta
Jinwoo Shin , Georgia Institute of Technology, Atlanta
ABSTRACT
GPGPU architectures (applications) have several different characteristics compared to traditional CPU architectures (applications): highly multithreaded architectures and SIMD-execution behavior are the two important characteristics of GPGPU computing. In this paper, we propose a potential function that models the DRAM behavior in GPGPU architectures and a DRAM scheduling policy α-SJF policy to minimize the potential function. The scheduling policy essentially chooses between SJF and FR-FCFS at run-time based on the number of requests from each thread and whether the thread has a row buffer hit.
INDEX TERMS
Random access memory, Processor scheduling, Computer architecture, Benchmark testing, Mathematical model, Equations, Instruction sets, DRAM scheduling, Random access memory, Processor scheduling, Computer architecture, Benchmark testing, Mathematical model, Equations, Instruction sets, Potential function, GPGPU
CITATION
Nagesh B. Lakshminarayana, Jaekyu Lee, Hyesoon Kim, Jinwoo Shin, "DRAM Scheduling Policy for GPGPU Architectures Based on a Potential Function", IEEE Computer Architecture Letters, vol.11, no. 2, pp. 33-36, July-Dec. 2012, doi:10.1109/L-CA.2011.32
REFERENCES
1. “HYNIX GDDR5 SGRAM,” http://www.hynix.co.kr/inc/pdfDownload.jsp?path=/ datasheet/pdf/graphicsH5GQ1H24AFR(Rev1.0).pdf.
2. “MacSim,” http://code.google.com/p/macsim.
3. NVIDIA, “Fermi: Nvidia's next generation cuda compute architecture,” http://www.nvidia.comfermi.
4. CUDA Programming Guide, V4.0, NVIDIA Corporation.
5. S. Rixner,“Memory controller optimizations Ror web servers,” in MICRO-37. Los Alamitos, CA, USA: IEEE Computer Society, 2004, pp. 355-366.
6. S. Rixner,W. J. Dally,U. J. Kapasi,P. Mattson,, and J. D. Owens,“Memory access scheduling,” in ISCA-27. Washington, DC, USA: IEEE Computer Society, 2000.
7. D. Shah and D. Wischik,“Switched networks with maximum weight policies: Fluid approximation and multiplicative state space collapse,” CoRR, volume abs/1004.1995, 2010.
8. W. K. Zuravleff and T. Robinson,“Controller for a synchronous dram that maximizes throughput by allowing memory requests and commands to be issued out of order,” U.S. Patent Number 5,630,096, May 1997.
42 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool