Research group
The Parallel Computing Systems (PCS) group at the University of Amsterdam performs research on the design, programming and run-time management of parallel and distributed computer systems. The modeling, analysis and optimization of the extra-functional aspects of these systems, such as performance, power/energy consumption, thermals, reliability or verifiability but also the degree of productivity to design and program these systems, play a pivotal role in this work.
DNN model inference on resource-constrained Edge devices
Thermal modeling, simulation and optimization of chips
Monitor the Energy Costs of Digital Services
Approximate Computing for Power and Energy Optimisation
Towards Adaptively Morphing Embedded Systems
Towards Optimal Design of Complex, Distributed Cyber Physical Systems
Interactive DSL for Composable EFB Adaptation using Bi-simulation and Extrinsic Coordination [Finalized]
Time, Energy and security Analysis for Multi/Many-core heterogenous PLAtforms [Finalized]
Software framework for runtime-Adaptive and secure deep Learning On Heterogeneous Architectures [Finalized]
Automated Distributed CNN Inference at the Edge
for heterogeneous real-time systems
Transient-Temperature Based Safe Power Budgeting in Multi-/Many-Core Processors
Core-memory thermal simulations for 2D, 2.5D, and 3D processors
Interval thermal simulation of 2D multi-/many-cores
High-throughput CPU-GPU CNN inference pipeline
High-level modeling and simulation of MPSoCs for early DSE
for modeling software interfaces