SAMOS Conference - Beachnote (2011)

SAMOS XXI Trailer

A Fine-Granularity Image Pyramid Accelerator for Embedded Processor

A fast heuristic to pipeline SDF graphs

A Quantitative Study of Locality in GPU Caches

System Simulation of Memristor Based Computation In Memory Platforms

Energy-aware Partial-Duplication Task Mapping under Real-Time and Reliability Constraints

Transpiling Python to Rust for Optimized Performance

Combining task- and data-level parallelism for high-throughput CNN inference on embedded MPSoCs

Rec2Poly: Converting Recursions to Polyhedral Optimized Loops using an Inspector-Executor Strategy

AMAIX: A Generic Analytical Model for Deep Learning Accelerators

DRAMSys4.0: A Fast and Cycle-Accurate SystemC/TLM-Based DRAM Simulator

'Economics Be Damned!' by Yale Patt

'Embracing Rather Than Fighting Memory Latency' by Walid Najjar

'Progress towards self-optimising and self-verifying design' by Wayne Luk

‘Machine Learning Processors — Deja Vu?' by Trevor Mudge

‘When to Process in Storage?‘ by Uri Weiser

‘On Neural Computing and Architectures‘ by Nikitas Dimopoulos

‘Cluster Communication Latency' by Manolis Katevenis

‘Efficient Computing in the Post-Moore Era‘ by Per Stenstom

'From Classical to Runtime Aware Architectures' by Mateo Valero

Introduction to the symposium by Yale Patt

SAMOS Conference - Beachnote (2012)

SAMOS Conference - Beachnote (2011)

SAMOS Conference - Beachnote (2010)