Gervin Thomas
ABSTRACT
Predictors are used in many fields of computer architectures to enhance performance. With good estimations of future system behaviour, policies can be developed to improve system performance or reduce power consumption. These policies become more effective if the predictors are implemented in hardware and can provide quantified forecasts and not only binary ones. In this paper, we present and evaluate a generic predictor implemented in VHDL running on an FPGA which produces quantified forecasts. Moreover, a complete scalability analysis is presented which shows that our implementation has a maximum device utilization of less than 5%. Furthermore, we analyse the power consumption of the predictor running on an FPGA. Additionally, we show that this implementation can be clocked by over 210 MHz. Finally, we evaluate a power-saving policy based on our hardware predictor. Based on predicted idle periods, this power-saving policy uses power-saving modes and is able to reduce memory power consumption by 14.3%.
- M. Awasthi, D. W. Nellans, R. Balasubramonian, and A. Davis. Prediction Based DRAM Row-Buffer Management in the Many-Core Era. In 20th International Conference on Parallel Architecture and Compilation Techniques (PACT), Galveston Island, Texas, October 2011. Google Scholar
Digital Library
- K. Chandrasekar, B. Akesson, and K. Goossens. Improved Power Modeling of DDR SDRAMs. In 14th Euromicro Conference on Digital System Design (DSD), 2011. Google ScholarDigital Library
- K. Chandrasekar et al. DRAMPower: Open Source DRAM Power & Energy Estimation Tool. www.es.ele.tue.nl/drampower, 2012.Google Scholar
- B.-S. Chen, Y.-S. Yang, B.-K. Lee, and T.-H. Lee. Fuzzy Adaptive Predictive Flow Control of ATM Network traffic. IEEE Transactions on Fuzzy Systems, 2003. Google ScholarDigital Library
- K. Deliparaschos, F. Nenedakis, and S. Tzafestas. Design and implementation of a fast digital fuzzy logic controller using fpga technology. Journal of Intelligent and Robotic Systems, 2006. Google ScholarDigital Library
- Y. Huang, K.-K. Chou, C.-T. King, and S.-Y. Tseng. NTPT: On the End-to-End Traffic Prediction in the On-Chip Networks. In 47th Design Automation Conference (DAC), 2010. Google ScholarDigital Library
- A. Mellit, H. Mekki, A. Messai, and S. Kalogirou. Fpga-based implementation of intelligent predictor for global solar irradiation, part i: Theory and simulation. Expert Systems with Applications, 2011. Google ScholarDigital Library
- Mentor Graphics. ModelSim, 11 2013.Google Scholar
- Micron Technology Inc. DDR3 SDRAM 1Gb Data Sheet, 2006.Google Scholar
- L. Miller. Division in VHDL, February 2009.Google Scholar
- U. Y. Ogras and R. Marculescu. Prediction-based Flow Control for Network-on-Chip Traffic. In 43th Design Automation Conference (DAC), New York, NY, USA, 2006. ACM. Google ScholarDigital Library
- B. Akesson, A. Molnos, A. Hansson, J. Ambrose Angelo, and K. Goossens. Composability and Predictability for Independent Application Development, Verification, and Execution. In Multiprocessor System-on-Chip | Hardware Design and Tool Integration, chapter 2. Springer, 2010.Google Scholar
- V. Stankovic and N. Milenkovic. DRAM Controller with a Complete Predictor: Preliminary Results. In 7th International Conference on Telecommunications in Modern Satellite, Cable and Broadcasting Services, volume 2, sept. 2005.Google ScholarCross Ref
- G. Thomas, K. Chandrasekar, B. Akesson, B. Juurlink, and K. Goossens. A Predictor-Based Power-Saving Policy for DRAM Memories. In 15th Euromicro Conference on Digital System Design (DSD), 2012. Google ScholarDigital Library
- G. Thomas, B. Juurlink, and D. Tutsch. Traffic Prediction for NoCs using Fuzzy Logic. In 2nd International Workshop on New Frontiers in High-performane and Hardware-aware Computing, San Antonio, USA, February 2011. KIT Scientific Publishing.Google Scholar
- Xilinx. Xilinx Power Estimator 14.3, October 2012.Google Scholar
- Xilinx. XST User Guide for Virtex-6, Spartan-6, and 7 Series Devices, 14.3 edition, October 2012.Google Scholar
- Xilinx. ISE Design Suite 14.6, 11 2013.Google Scholar
- Xilinx. Spartan-6 FPGA Family, 11 2013.Google Scholar
- Y. Xu, A. S. Agarwal, and B. T. Davis. Prediction in Dynamic SDRAM Controller Policies. In Proc. 9th International Workshop on Embedded Computer Systems: Architectures, Modeling, and Simulation, 2009. Google ScholarDigital Library
Index Terms
- A generic implementation of a quantified predictor on FPGAs
Recommendations
Optimized RTL Code Generation from Coarse-Grain Dataflow Specification for Fast HW/SW Cosynthesis
This paper presents a new methodology of automatic RTL code generation from coarse-grain dataflow specification for fast HW/SW cosynthesis. A node in a coarse-grain dataflow specification represents a functional block such as FIR and DCT and an arc may ...
A Predictor-Based Power-Saving Policy for DRAM Memories
DSD '12: Proceedings of the 2012 15th Euromicro Conference on Digital System DesignReducing power/energy consumption is an important goal for all computer systems, from servers to battery-driven hand-held devices. To achieve this goal, the energy consumption of all system components needs to be reduced. One of the most power-hungry ...
Power Consumption Management on FPGAs
CONIELECOMP '05: Proceedings of the 15th International Conference on Electronics, Communications and ComputersDuring the last years, the number of hardware implementations based on Field Programmable Gate Arrays (FPGAs) is increasing because it satisfies the high speed of system and hardware cost constraints. FPGAs implementation allows the building of rapid ...
Comments