Harnessing Machine Learning to Improve the Success Rate of Stimuli Generation

The initial state of a design under verification has a major impact on the ability of stimuli generators to successfully generate the requested stimuli. For complexity reasons, most stimuli generators use sequential solutions without planning ahead. Therefore, in many cases, they fail to produce a consistent stimuli due to an inadequate selection of the initial state. We propose a new method, based on machine learning techniques, to improve generation success by learning the relationship between the initial state vector and generation success. We applied the proposed method in two different settings, with the objective of improving generation success and coverage in processor and system level generation. In both settings, the proposed method significantly reduced generation failures and enabled faster coverage

[1]  Dana Angluin,et al.  Queries and concept learning , 1988, Machine Learning.

[2]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[3]  A. Hasman,et al.  Probabilistic reasoning in intelligent systems: Networks of plausible inference , 1991 .

[4]  W. Näther.  Optimum experimental designs , 1994 .

[5]  大西 仁,et al.  Pearl, J. (1988, second printing 1991). Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan-Kaufmann. , 1994 .

[6]  Yishay Mansour,et al.  Learning Boolean Functions via the Fourier Transform , 1994 .

[7]  Cathy May,et al.  The PowerPC Architecture: A Specification for a New Family of RISC Processors , 1994 .

[8]  Aharon Aharon,et al.  Test Program Generation for Functional Verification of PowePC Processors in IBM , 1995, 32nd Design Automation Conference.

[9]  David Heckerman,et al.  Causal independence for probability assessment and inference using Bayesian networks , 1996, IEEE Trans. Syst. Man Cybern. Part A.

[10]  Avi Ziv,et al.  User defined coverage—a tool supported methodology for design verification , 1998, DAC.

[11]  Laurent Fournier,et al.  Functional verification methodology for microprocessors using the Genesys test-program generator. Application to the x86 microprocessors family , 1999, Design, Automation and Test in Europe Conference and Exhibition, 1999. Proceedings (Cat. No. PR00078).

[12]  Laurent Fournier,et al.  Functional verification methodology for microprocessors using the Genesys test-program generator , 1999, DATE '99.

[13]  Edmund M. Clarke,et al.  Model Checking , 1999, Handbook of Automated Reasoning.

[14]  Tom Shanley,et al.  Infiniband Network Architecture , 2002 .

[15]  Allon Adir,et al.  Adaptive test program generation: planning for the unplanned , 2002, Seventh IEEE International High-Level Design Validation and Test Workshop, 2002..

[16]  Yehuda Naveh,et al.  X-Gen: a random test-case generator for systems and SoCs , 2002, Seventh IEEE International High-Level Design Validation and Test Workshop, 2002..

[17]  Avi Ziv,et al.  Using a constraint satisfaction formulation and solution techniques for random test program generation , 2002, IBM Syst. J..

[18]  Avi Ziv,et al.  Hole analysis for functional coverage data , 2002, DAC '02.

[19]  Avi Ziv,et al.  Coverage directed test generation for functional verification using Bayesian networks , 2003, Proceedings 2003. Design Automation Conference (IEEE Cat. No.03CH37451).

[20]  Allon Adir,et al.  Genesys-Pro: innovations in test program generation for functional processor verification , 2004, IEEE Design & Test of Computers.

[21]  Andrew Piziali,et al.  Functional verification coverage measurement and analysis , 2004 .

[22]  Wolfgang Roesner,et al.  Comprehensive Functional Verification: The Complete Industry Cycle (Systems on Silicon) , 2005 .

[23]  Wolfgang Roesner,et al.  Comprehensive Functional Verification: The Complete Industry Cycle , 2005 .

[24]  David Heckerman,et al.  A Tutorial on Learning with Bayesian Networks , 1999, Innovations in Bayesian Networks.