Efficient system design space exploration using machine learning techniques
Proceedings of the 45th annual Design Automation Conference
Exploring and predicting the architecture/optimising compiler co-design space
CASES '08 Proceedings of the 2008 international conference on Compilers, architectures and synthesis for embedded systems
CPR: Composable performance regression for scalable multiprocessor models
Proceedings of the 41st annual IEEE/ACM International Symposium on Microarchitecture
Proceedings of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture
Rapid early-stage microarchitecture design using predictive models
ICCD'09 Proceedings of the 2009 IEEE international conference on Computer design
Designing heterogeneous embedded network-on-chip platforms with users in mind
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Effective feature set construction for SVM-based hot method prediction and optimisation
International Journal of Computational Science and Engineering
ACM Transactions on Embedded Computing Systems (TECS)
Microarchitectural design space exploration made fast
Microprocessors & Microsystems
Inferred Models for Dynamic and Sparse Hardware-Software Spaces
MICRO-45 Proceedings of the 2012 45th Annual IEEE/ACM International Symposium on Microarchitecture
ACM Transactions on Intelligent Systems and Technology (TIST) - Special Section on Intelligent Mobile Knowledge Discovery and Management Systems and Special Issue on Social Web Mining
Hi-index | 0.00 |
The vast number of transistors available through modern fabrication technology gives architects an unprecedented amount of freedom in chip-multiprocessor (CMP) designs. However, such freedom translates into a design space that is impossible to fully, or even partially to any significant frac- tion, explore through detailed simulation. In this paper we propose to address this problem using predictive modeling, a well-known machine learning technique. More specifi- cally we build models that, given only a minute fraction of the design space, are able to accurately predict the behav- ior of the remaining designs orders of magnitude faster than simulating them. In contrast to previous work, our models can predict per- formance metrics not only for unseen CMP configurations for a given application, but also for unseen configurations of a new application that was not in the set of applications used to build the model, given only a very small number of results for this new application. We perform extensive experiments to show the efficacy of the technique for exploring the design space of CMP's running parallel applications. The technique is used to pre- dict both energy-delay and execution time. Choosing both explicitly parallel applications and applications that are parallelized using the thread-level speculation (TLS) ap- proach, we evaluate performance on a CMP design space with about 95 million points using 18 benchmarks with up to 1000 training points each. For predicting the energy- delay metric, prediction errors for unseen configurations of the same application range from 2.4% to 4.6% and for con- figurations of new applications from 3.1% to 4.9%.