Dataflow Models of computation for programming heterogeneous multicores
The hardware complexity of modern integrated circuits keeps increasing at a steady pace.
Heterogeneous Multi-Processor Systems-on-Chips (MPSoCs) integrate general-purpose …
Heterogeneous Multi-Processor Systems-on-Chips (MPSoCs) integrate general-purpose …
Notifying Memories for Dataflow Applications on Shared-Memory Parallel Computer
A Ghasemi - 2022 - theses.hal.science
Symmetric Shared-memory multiprocessor~(SMP) is the most widely used implementation
of high-performance multi-core processors. It offers a uniform shared memory view that …
of high-performance multi-core processors. It offers a uniform shared memory view that …
Scratchy: A Class of Adaptable Architectures with Software-Managed Communication for Edge Streaming Applications
Stream processing applications are becoming increasingly complex, requiring parallel and
adaptable architectures under real-time constraints. Currently, selecting appropriate …
adaptable architectures under real-time constraints. Currently, selecting appropriate …
Open Hardware Custom Architectures for Near-Sensor Signal Processing and Machine Learning
JFN PELCAT, K MARTIN, S Shuvra - 2022 - open-src-soc.org
In order to improve the energy efficiency of distributed systems, signal processing and
machine learning (SPML) workloads tend to be processed closer to the network edge …
machine learning (SPML) workloads tend to be processed closer to the network edge …