Machine learning: paradigms and methods
Machine learning: paradigms and methods
System Design with SystemC
Control Flow Modeling in Statistical Simulation for Accurate and Efficient Processor Design Studies
Proceedings of the 31st annual international symposium on Computer architecture
IBM Journal of Research and Development
IODINE: a tool to automatically infer dynamic invariants for hardware designs
Proceedings of the 42nd annual Design Automation Conference
Interactive presentation: PowerQuest: trace driven data mining for power optimization
Proceedings of the conference on Design, automation and test in Europe
Verification methodologies in a TLM-to-RTL design flow
Proceedings of the 44th annual Design Automation Conference
Markov Chains and Stochastic Stability
Markov Chains and Stochastic Stability
MAGENTA: transaction-based statistical micro-architectural root-cause analysis
Proceedings of the 46th Annual Design Automation Conference
Automated, retargetable back-annotation for host compiled performance and power modeling
Proceedings of the Ninth IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis
| Hi-index | 0.00 |
In general, we lack in EDA industry tools and automated solutions in μArchitectural domain. In this paper, we elaborate on our attempt to advance performance simulation based statistical analysis techniques. On one hand, we utilize the content knowledge of μArchitectural specification (e.g., explicit specification of the major transactions), and on the other hand, the statistical compact representation of the simulation trace. We name the compact statistical modeling of transaction level performance simulation traces, Magenta (Modeling Agent for Transactional Analysis). As demonstrated by industrial case studies, Magenta can effectively capture all the sample flows that are represented in the simulation trace that exhibit the transaction of interest in terms of μArchitectural events in a statistical event dependency graph. Our industrial experience shows that Magenta is an effective statistical model for μArchitectural performance verification and power/performance trade-off.