Automatic phase detection for stochastic on-chip traffic generation

(NoC) prototyping is used for adapting NoC parameters to the application running on the chip. This prototyping is currently done using traffic generators which emulate the SoC components (IPs) behavior: processors, hardware accelerators, etc. Traffic generated by processor-like IPs is highly non-regular, it must be decomposed into program phases. We propose an original feature for NoC prototyping, inspired by techniques used in processor architecture performance evaluation: the automatic detection of traffic phases. Integrated in our NoC prototyping environment, this feature permits to have a completely automatic toolchain for the generation of stochastic traffic generators. We show that our traffic generators emulate precisely the behavior of processors and that our environment is a versatile tool for networks-on-chip prototyping. Simulations are performed in a SystemC-based simulation environment with a mesh network-on-chip (DSPIN) and a processor running MP3 decoding applications.

[1]  Brad Calder,et al.  How to use SimPoint to pick simulation points , 2004, PERV.

[2]  Philippe Owezarski,et al.  Non-Gaussian and Long Memory Statistical Characterizations for Internet Traffic with Anomalies , 2007, IEEE Transactions on Dependable and Secure Computing.

[3]  Brad Calder,et al.  A co-phase matrix to guide simultaneous multithreading simulation , 2004, IEEE International Symposium on - ISPASS Performance Analysis of Systems and Software, 2004.

[4]  Dake Liu,et al.  Network on chip simulations for benchmarking , 2004, 4th IEEE International Workshop on System-on-Chip for Real-Time Applications.

[5]  Sujit Dey,et al.  Evaluation of the traffic-performance characteristics of system-on-chip communication architectures , 2001, VLSI Design 2001. Fourteenth International Conference on VLSI Design.

[6]  Luca Benini,et al.  Analyzing on-chip communication in a MPSoC environment , 2004, Proceedings Design, Automation and Test in Europe Conference and Exhibition.

[7]  Antoine Fraboulet,et al.  A Generic Multi-Phase On-Chip Traffic Generation Environment , 2006, IEEE 17th International Conference on Application-specific Systems, Architectures and Processors (ASAP'06).

[8]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[9]  Brad Calder,et al.  Discovering and Exploiting Program Phases , 2003, IEEE Micro.

[10]  Giovanni De Micheli,et al.  A complete network-on-chip emulation framework , 2005, Design, Automation and Test in Europe.

[11]  Andrew W. Moore,et al.  X-means: Extending K-means with Efficient Estimation of the Number of Clusters , 2000, ICML.

[12]  Axel Jantsch,et al.  Evaluating NoC communication backbones with simulation , 2003 .

[13]  Jan Madsen,et al.  Network traffic generator model for fast network-on-chip simulation , 2005, Design, Automation and Test in Europe.

[14]  Kees G. W. Goossens,et al.  Cost-performance trade-offs in networks on chip: a simulation-based approach , 2004, Proceedings Design, Automation and Test in Europe Conference and Exhibition.

[15]  Alain Greiner,et al.  A generic architecture for on-chip packet-switched interconnections , 2000, DATE '00.

[16]  Radu Marculescu,et al.  On-chip traffic modeling and synthesis for MPEG-2 video applications , 2004, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.