TU Berlin

Embedded Systems ArchitectureEmbedded Systems Architecture

AES Logo

Page Content

to Navigation

Welcome at AES


The Embedded Systems Architecture (Architektur eingebetteter Systeme, AES) group investigates and teaches the field of computer architecture, ranging from low-power embedded systems to massively parallel high-performance systems. We focus on the design, implementation and optimization of high performance embedded systems; taking into account the interactions between applications, tools, and architectures. In addition to high performance we also aim at improving energy efficiency, programmability, predictability, error resilience, as well as other features of emerging computer systems.


AES paper accepted at ARCS 2022


[aes/dm,fbk] The paper "Effects of Approximate Computing on Workload Characteristics" has been accepted for publication at the ARCS 2022.

The paper studies how Approximate Computing fundamentally affects the core of workload characteristics and proposes a holistic approach of both traditional software optimizations and approximate computing techniques.

The ARCS conference has over 30 years of tradition reporting leading edge research in computer architecture and operating systems. This years' edition is taking place in Heilbronn, Germany on September 13-15.

AES paper accepted at Euro-Par 2021

Euro-Par Logo

[aes/dm,fbk] The paper "ALONA: Automatic Loop Nest Approximation with Reconstruction and Space Pruning" has been accepted as full paper at the International European Conference on Parallel and Distributed Computing.

This work is authored by Daniel Maier, Biagio Cosenza (University of Salerno) and Ben Juurlink and presents a novel approach for automatic loop nest approximation based on a polyhedral compilation.

Euro-Par is the prime European conference covering all aspects of parallel and distributed processing. The 27th edition of Euro-Par will take place from 30 August – 3 September 2021 as hybrid event in Lisbon, Portugal.

13.11.2020: Paper accepted at DATE'21


The paper "QSLC: Quantization-Based, Low-Error Selective Approximation for GPUs" by Sohan Lal, Jan Lucas, and Ben Juurlink has been accepted for publication at DATE 2021. The paper proposes a simple quantization-based selective approximation technique that has 5x lower error and 7.6x lower area than the state-of-the-art.

DATE is the top scientific event in Design, Automation, and Test of microelectronics and embedded systems for the academic and industrial research communities worldwide. The 2021 edition of the conference will take place from Februrary 01-05, 2021, in Grenoble, France.

More information can be found at www.date-conference.com

More news can be found here.


Quick Access

Schnellnavigation zur Seite über Nummerneingabe