University of Manchester

Pavlos Petoumenos

Lecturer (Assistant Professor) (Information and computing sciences)

Manchester, UK


  • Where replacement algorithms fail: A thorough analysis
  • Measuring QoE of interactive workloads and characterising frequency governors on mobile devices
  • Modeling cache sharing on chip multiprocessor architectures
  • Synthesizing benchmarks for predictive modeling
  • Preventing denial-of-service attacks in shared CMP caches
  • Instruction-based reuse-distance prediction for effective cache management
  • Fast automatic heuristic construction using active learning
  • Efficient microarchitecture policies for accurately adapting to power constraints
  • Using value locality to reduce memory encryption overhead in embedded processors
  • Minimizing the cost of iterative compilation with active learning
  • MLP-aware instruction queue resizing: The key to power-efficient performance
  • Power capping: What works, what does not
  • Cache replacement based on reuse-distance prediction
  • ALEA: A fine-grained energy profiling tool
  • Active learning accelerated automatic heuristic construction for parallel program mapping
  • Effective Function Merging in the SSA Form
  • Collaborative Heterogeneity-Aware OS Scheduler for Asymmetric Multicore Processors
  • Developer and user-transparent compiler optimization for interactive applications
  • HyFM: function merging for free
  • POSTER: A collaborative multi-factor scheduler for asymmetric multicore processors
  • Function Merging by Sequence Alignment
  • Compiler fuzzing through deep learning
  • End-to-End Deep Learning of Optimization Heuristics

Usage metrics

Co-workers & collaborators

Rodrigo Rocha

Rodrigo Rocha

Pavlos Petoumenos's public data