89 citations · 180 across the 30 of their papers we have counts for
6 papers · 1 filter
Optimizing GEMM for Energy and Performance on Versal ACAP Architectures
Ilias Papalamprou, Dimosthenis Masouros, Ioannis Loudaros +2
General Matrix Multiplication (GEMM) is a fundamental operation in many scientific workloads, signal processing, and particularly deep learning. It is often a bottleneck for perfor…
A Soft SIMD Based Energy Efficient Computing Microarchitecture
Pengbo Yu, Alexandre Levisse, Mohit Gupta +4
The ever-increasing size and computational complexity of today's machine-learning algorithms pose an increasing strain on the underlying hardware. In this light, novel and dedicate…
VWR2A: A Very-Wide-Register Reconfigurable-Array Architecture for Low-Power Embedded Devices
Benoît Walter Denkinger, Miguel Peón-Quirós, Mario Konijnenburg +2
Edge-computing requires high-performance energy-efficient embedded systems. Fixed-function or custom accelerators, such as FFT or FIR filter engines, are very efficient at implemen…
MemPool-3D: Boosting Performance and Efficiency of Shared-L1 Memory Many-Core Clusters with 3D Integration
Matheus Cavalcante, Anthony Agnesina, Samuel Riedel +6
Three-dimensional integrated circuits promise power, performance, and footprint gains compared to their 2D counterparts, thanks to drastic reductions in the interconnects' length t…
A Hybrid Prefetch Scheduling Heuristic to Minimize at Run-Time the Reconfiguration Overhead of Dynamically Reconfigurable Hardware
Javier Resano, Daniel Mozos, Francky Catthoor
Due to the emergence of highly dynamic multimedia applications there is a need for flexible platforms and run-time scheduling support for embedded systems. Dynamic Reconfigurable H…
A Memory Hierarchical Layer Assigning and Prefetching Technique to Overcome the Memory Performance/Energy Bottleneck
Minas Dasygenis, Erik Brockmeyer, Bart Durinck +3
The memory subsystem has always been a bottleneck in performance as well as significant power contributor in memory intensive applications. Many researchers have presented multi-la…