Multi-objective optimisations for a superscalar architecture with selective value prediction

This work extends an earlier manual design space ex ploration of our developed Selective Load Value Pre diction based superscalar architecture to the L2 unified cache. A fter that we perform an automatic design space expl oration using a special developed software tool by varying several architectural parameters. Our goal is to find optim al configurations in terms of CPI (Cycles per Instruction) and energy consumption. By varying 19 architectural parameter s, as we proposed, the design space is over 2.5 millions of billions configurations which obviously means that only heuristic search can be considered. Therefore, we propose dif ferent methods of automatic design space exploratio n based on our developed FADSE tool which allow us to evaluate only 2500 configurations of the above mentioned huge design space! The experimental results show that our automatic de sign space exploration (DSE) provides significantly better configurations than our previous manual DSE approach, considering the proposed multi-objective approac h.

[1]  Arpad Gellert,et al.  Exploiting selective instruction reuse and value prediction in a superscalar architecture , 2009, J. Syst. Archit..

[2]  Arpad Gellert,et al.  Focalising dynamic value prediction to CPU's context , 2005 .

[3]  Sascha Uhrig,et al.  Reconfigurable Grid Alu Processor: Optimization and Design Space Exploration , 2010, 2010 13th Euromicro Conference on Digital System Design: Architectures, Methods and Tools.

[4]  Marco Laumanns,et al.  SPEA2: Improving the strength pareto evolutionary algorithm , 2001 .

[5]  Chantal Ykman-Couvreur,et al.  MULTICUBE: Multi-objective Design Space Exploration of Multi-core Architectures , 2010, 2010 IEEE Computer Society Annual Symposium on VLSI.

[6]  Mikko H. Lipasti,et al.  Value locality and load value prediction , 1996, ASPLOS VII.

[7]  Enrique Alba,et al.  SMPSO: A new PSO-based metaheuristic for multi-objective optimization , 2009, 2009 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making(MCDM).

[8]  Vittorio Zaccaria,et al.  Meta-model Assisted Optimization for Design Space Exploration of Multi-Processor Systems-on-Chip , 2009, 2009 12th Euromicro Conference on Digital System Design, Architectures, Methods and Tools.

[9]  Onur Mutlu,et al.  Address-Value Delta (AVD) Prediction: A Hardware Technique for Efficiently Parallelizing Dependent Cache Misses , 2006, IEEE Transactions on Computers.

[10]  Chantal Ykman-Couvreur,et al.  MULTICUBE: Multi-objective Design Space Exploration of Multi-core Architectures , 2010, ISVLSI.

[11]  Francisco Luna,et al.  jMetal: a Java Framework for Developing Multi-Objective Optimization Metaheuristics , 2006 .

[12]  Wei Liu,et al.  ReSlice: selective re-execution of long-retired misspeculated instructions using forward slicing , 2005, 38th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO'05).

[13]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[14]  Theo Ungerer,et al.  Automatic multi-objective optimization of parameters for hardware and code optimizations , 2011, 2011 International Conference on High Performance Computing & Simulation.

[15]  Kevin Skadron,et al.  Predictive design space exploration using genetically programmed response surfaces , 2008, 2008 45th ACM/IEEE Design Automation Conference.

[16]  Carlos A. Coello Coello,et al.  Improving PSO-Based Multi-objective Optimization Using Crowding, Mutation and epsilon-Dominance , 2005, EMO.

[17]  Rakesh Kumar,et al.  Magellan: A Search and Machine Learning-based Framework for Fast Multi-core Design Space Exploration and Optimization , 2008, 2008 Design, Automation and Test in Europe.

[18]  Jianwei Chen,et al.  Integrating complete-system and user-level performance/power simulators: the SimWattch approach , 2003, 2003 IEEE International Symposium on Performance Analysis of Systems and Software. ISPASS 2003..

[19]  C. Coello,et al.  Improving PSO-based Multi-Objective Optimization using Crowding , Mutation and �-Dominance , 2005 .

[20]  Theo Ungerer,et al.  Boosting Design Space Explorations with Existing or Automatically Learned Knowledge , 2012, MMB/DFT.

[21]  Andrew D. Hilton.  Energy Efficient Load Latency Tolerance: Single-Thread Performance for the Multi-Core Era , 2010 .

[22]  Olivier Temam,et al.  ArchExplorer.org: joint compiler/hardware exploration for fair comparison of architectures , 2009 .

[23]  Lucian Vintan,et al.  An automatic design space exploration framework for multicore architecture optimizations , 2010, 9th RoEduNet IEEE International Conference.

[24]  E. H. Mamdani,et al.  An Experiment in Linguistic Synthesis with a Fuzzy Logic Controller , 1999, Int. J. Man Mach. Stud..

[25]  Vittorio Zaccaria,et al.  Energy-performance design space exploration in SMT architectures exploiting selective load value predictions , 2010, 2010 Design, Automation & Test in Europe Conference & Exhibition (DATE 2010).

[26]  Duc Truong Pham,et al.  Action aggregation and defuzzification in Mamdani-type fuzzy systems , 2002 .

[28]  Chung-Ping Chung,et al.  Early load: Hiding load latency in deep pipeline processor , 2008, 2008 13th Asia-Pacific Computer Systems Architecture Conference.

[29]  Margo McCall,et al.  IEEE Computer Society , 2019, Encyclopedia of Software Engineering.

[30]  Theo Ungerer,et al.  Optimizing a Superscalar System using Multi-objective Design Space Exploration , 2011 .

[31]  Vittorio Zaccaria,et al.  Multi-processor system-on-chip Design Space Exploration based on multi-level modeling techniques , 2009, 2009 International Symposium on Systems, Architectures, Modeling, and Simulation.

[32]  Margaret Martonosi,et al.  Wattch: a framework for architectural-level power analysis and optimizations , 2000, Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat. No.RS00201).

[33]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[34]  Andy D. Pimentel,et al.  NASA: A generic infrastructure for system-level MP-SoC design space exploration , 2010, 2010 8th IEEE Workshop on Embedded Systems for Real-Time Multimedia.