Kim Grüttner

Kim Grüttner

orcid

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 April 2021 in Software and Systems Modeling
Verified
Journal Article
Closed access
PDF file
MFMaher Fakih
Maher Fakih
OKOliver Klemp
Oliver Klemp
SPStefan Puch
Stefan Puch
KGKim Grüttner
Kim Grüttner

20 July 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
RSRalf Stemmer
Ralf Stemmer
HVHai Dang VU
Hai Dang VU
SNSebastien Le Nours
Sebastien Le Nours
KGKim Grüttner
Kim Grüttner
SPSebastien Pillement
Sebastien Pillement
WNWolfgang Nebel
Wolfgang Nebel
Fast yet accurate performance and timing prediction of complex parallel data flow applications on multi-processor systems remains a very difficult discipline. The reason for it comes from the complexity of the data flow applications w.r.t. data dependent execution paths and the hardware platform with shared resources, like buses and memories. This combination may lead to complex timing interferences that are difficult to express in pure analytical or classical simulation-based approaches. In this work, we propose the combination of timing measurement and statistical simulation models for probabilistic timing and performance prediction of Synchronous Data Flow (SDF) applications on MPSoCs with shared memories. We exploit the separation of computation and communication in our SDF model of computation to set-up simulation-based performance prediction models following different abstraction approaches. We especially propose a message-level communication model driven by a data-dependent probabilistic execution phase timing model. We compare our work against measurement on two case-studies from the computer vision domain: a Sobel filter and a JPEG decoder. We show that the accuracy and execution time of our modeling and evaluation framework outperforms existing approaches and is suitable for a fast yet accurate design space exploration.


17 January 2023
Verified
Conference Paper
Open access
QDQuentin Dariol
Quentin Dariol
SNSebastien Le Nours
Sebastien Le Nours
DHDomenik Helms
Domenik Helms
RSRalf Stemmer
Ralf Stemmer
SPSebastien Pillement
Sebastien Pillement
KGKim Grüttner
Kim Grüttner
When deploying Artificial Neural Networks (ANNs) onto multi-core embedded platforms, an intensive evaluation flow is necessary to find implementations that optimize resource usage, timing and power. ANNs require indeed significant amounts of computational and memory resources to execute, while embedded execution platforms offer limited resources with strict power budget. Concurrent accesses from processors to shared resources on multi-core platforms can lead to bottlenecks with impact on performance and power. Existing approaches show limitations to deliver fast yet accurate evaluation ahead of ANN deployment on the targeted hardware. In this paper, we present a modeling flow for timing and power prediction in early design stage of fully-connected ANNs on multi-core platforms. Our flow offers fast yet accurate predictions with consideration of shared communication resources and scalability in regards of the number of cores used. The flow is evaluated on real measurements for 42 mappings of 3 fully-connected ANNs executed on a clock-gated multi-core platform featuring two different communication modes: polling or interrupt-based. Our modeling flow predicts timing with accuracy and power with accuracy on the tested mappings for an average simulation time of 0.23 s for 100 iterations. We then illustrate the application of our approach for efficient design space exploration of ANN implementations.

9 January 2023 in SN Computer Science
Verified
Journal Article
Open access
PDF file
FHFrederik Haxel
Frederik Haxel
AVAlexander Viehl
Alexander Viehl
MBMichael Benkel
Michael Benkel
BBBjoern Beyreuther
Bjoern Beyreuther
KBKlaus Birken
Klaus Birken
DMDaniel Mueller-Gritschneder
Daniel Mueller-Gritschneder
Designing software that meets the stringent requirements of functional safety standards imposes a significant development effort compared to conventional software. A key aspect is the integration of safety mechanisms into the functional design to ensure a safe state during operation even in the event of hardware errors. These safety mechanisms can be applied at different levels of abstraction during the development process and are usually implemented and integrated manually into the design. This does not only cause significant effort but does also reduce the overall maintainability of the software. To mitigate this, we present the Universal Safety Format (USF), which enables the generation of safety mechanisms based on the separation of concerns principle in a model-driven approach. Safety mechanisms are described as generic patterns using a transformation language independent from the functional design or any particular programming language. The USF was designed to be easily integrated into existing tools and workflows that can support different programming languages. Tools supporting the USF can utilize the patterns in a functional design to generate and integrate specific safety mechanisms for different languages using the transformation rules contained within the patterns. This enables not only the reuse of safety patterns in different designs, but also across different programming languages. The approach is demonstrated with an automotive use-case as well as different tools supporting the USF.