High Performance Processor Architecture for Automotive Large Scaled Integrated Systems within the European Processor Initiative Research Project

Reinhardt, Dominik; Dannebaum, Udo; Scheffer, Michael; Traub, Matthias

doi:10.4271/2019-01-0118

Cited by 12 publications

(8 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On board ML computing can be done only if the computational algorithm complexity is not too high, and a performing HW is adopted. Hence, on-board computing units for ML should be optimized in terms of the ratio between processing throughput performance and resources (memory, bandwidth, power consumption, ...) [7][8][9]. This is the trend that also big industrial players are following like Google, Nvidia or Intel, that are trying to enter in the autonomous driving market, or the recently announced Full Self Driving (FSD) chip from Tesla.…”

Section: Introductionmentioning

confidence: 99%

“…This is the trend that also big industrial players are following like Google, Nvidia or Intel, that are trying to enter in the autonomous driving market, or the recently announced Full Self Driving (FSD) chip from Tesla. This topic is also the core of the automotive stream in the H2020 European Processor Initiative (embedded HPC for autonomous driving with BMW as main technology end-user [9,10]) funding this work. To address the above issues new computing arithmetic styles are appearing in research [11][12][13][14][15][16][17][18][19][20] overcoming the classic fixed-point (INT) vs. IEEE-754 floating-point duality in case of embedded DNN (Deep Neural Networks) signal processing.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Novel Arithmetics to Accelerate Machine Learning Classifiers in Autonomous Driving Applications

Cococcioni

Rossi

Ruffaldi³

et al. 2019

2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS)

View full text Add to dashboard Cite

Autonomous driving techniques frequently need the clustering and the classification of data coming from several input sensors, like cameras, radar and lidars. These sub-tasks need to be implemented0020in real-time in embedded on-board computing units. The trend for data classification and clustering in the signal processing community is moving towards machine learning (ML) algorithms. One of them, which plays a central role, is the k-nearest neighbors (k-NN) algorithm. To meet stringent requirements in terms of real-time computing capability and circuit/memory complexity, ML accelerators are needed. Innovation is required in terms of computing arithmetic since classic integer numbers lead to low classification accuracy with respect to the needs of safety critical applications like autonomous driving. Instead, floating numbers require too much circuit and memory. To overcome these issues the paper shows that the use of a new format, called Posit, implemented in a new cppPosit software library, can lead to a k-NN implementation having the same accuracy of floats, but with halved bit-size. This means that a Posit Processing Unit (PPU) reduces by a factor higher than 2 the data transfer and storage complexity of ML accelerators. We also prove that a LUTbased complete tabulated implementation of a PPU for a 8-bit requires just 64 kB storage size, compliant with memoryconstrained devices.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Novel Arithmetics to Accelerate Machine Learning Classifiers in Autonomous Driving Applications

Cococcioni

Rossi

Ruffaldi³

et al. 2019

2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS)

View full text Add to dashboard Cite

show abstract

“…Hence, on-board computing units for DNN should be optimized in terms of the ratio between signal processing throughput performance and resources (memory, bandwidth, power consumption, etc.) [15]- [17]. This is the trend that also big players are following like Google, NVIDIA or Intel, that are trying to enter in the autonomous driving market, or the recently announced Full Self Driving (FSD) chip from Tesla.…”

Section: Introductionmentioning

confidence: 99%

“…This is the trend that also big players are following like Google, NVIDIA or Intel, that are trying to enter in the autonomous driving market, or the recently announced Full Self Driving (FSD) chip from Tesla. This concept is also the core of the automotive stream in the H2020 European Processor Initiative (embedded HPC for autonomous driving with the BMW group as main technology end user [17], where the article's authors are involved. To address the above issues new computing arithmetic styles are appearing in state of art [18]- [26] to overcome the classic fixedpoint (INT) vs. IEEE-754 floating point duality in case of embedded DNN signal processing.…”

Section: Introductionmentioning

confidence: 99%

Novel Arithmetics in Deep Neural Networks Signal Processing for Autonomous Driving: Challenges and Opportunities

Cococcioni

Rossi

Ruffaldi

et al. 2021

IEEE Signal Process. Mag.

View full text Add to dashboard Cite

This paper focuses on trends, opportunities and challenges of novel arithmetics for DNN signal processing, with particular reference to assisted and autonomous driving applications. Due to strict constrains in terms of latency, dependability and security of autonomous driving, machine perception (i.e. detection or decisions tasks) based on DNN can not be implemented relying on a remote cloud access. These tasks must be performed in real-time on embedded systems on-board the vehicle, particularly for the inference phase (considering the use of DNNs pre-trained during an off-line step). When developing a DNN computing platform, the choice of the computing arithmetics matters. Moreover, functional safe applications like autonomous driving pose severe constraints on the effect that signal processing accuracy has on final rate of wrong detection/decisions. Hence, after reviewing the different choices and trade-off concerning arithmetics, both in academia and industry, we highlight the issues in implementing DNN accelerators to achieve accurate and low-complex processing of automotive sensor signals (the latter coming from diverse sources like cameras, radars, lidars, ultrasonics). The focus is on both on general-purpose operations massively used in DNN like multiply, accumulation, compare, or on specific functions like for example sigmoid or hyperbolic tangent, used for neuron activation.

show abstract

“…Future autonomous driving sub-tasks are very likely to be realizes as a service-oriented computing architecture. Accordingly, the authors in [1] define different levels of serviceoriented architectures. The lowest level is referred to as a Software-as-a-service (SaaS), which is defined by functionality and information on-demand.…”

Section: Introductionmentioning

confidence: 99%

Embedded Image Processing the European Way: A new platform for the future automotive market

Hotfilter¹,

Kempf²,

Becker³

et al. 2020

2020 IEEE 6th World Forum on Internet of Things (WF-IoT)

Self Cite

View full text Add to dashboard Cite

Within the European Processor Initiative (EPI) an objective is build an embedded High-Performance processing platform for future automotive applications such as autonomous driving. An embedded Field-Programmable-Gate-Array (eF-PGA) enables the platform to be extended for future needs and requirements by various stakeholders. In this paper we give an overview about the project and our contributions to define the architecture of the eFPGA, which is suitable for the automotive market. Therefore, we describe our concept to explore the eFPGA architecture. It is motivated by a sound use case that deals with face recognition based on current neural networks. During the scope of the work we describe how the application is carefully mapped on the different domains of the EPI platform to make it more safe and secure as well as performant. As a result, we will find an apt eFPGA configuration, which can host common but also future neural network applications and a mapping of common image processing tasks.

show abstract

High Performance Processor Architecture for Automotive Large Scaled Integrated Systems within the European Processor Initiative Research Project

Cited by 12 publications

References 4 publications

Novel Arithmetics to Accelerate Machine Learning Classifiers in Autonomous Driving Applications

Novel Arithmetics to Accelerate Machine Learning Classifiers in Autonomous Driving Applications

Novel Arithmetics in Deep Neural Networks Signal Processing for Autonomous Driving: Challenges and Opportunities

Embedded Image Processing the European Way: A new platform for the future automotive market

Contact Info

Product

Resources

About