Frank Feinbube

Frank Feinbube
Hasso Plattner Institute · Research Group Operating Systems and Middleware

M.Sc.

About

37
Publications
5,778
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
126
Citations
Additional affiliations
October 2014 - April 2015
Hasso Plattner Institute
Position
  • Lecturer
Description
  • Non-Uniform Memory Access (NUMA) Seminar
April 2014 - September 2014
Beuth Hochschule für Technik Berlin
Position
  • Lecturer
Description
  • Lecture and Exercise: Operating Systems with 39 participants. Moodle
January 2014 - April 2014
Hasso Plattner Institute
Position
  • Lecturer
Description
  • Open Online Course "Parallel Programming Concepts" with 9000+ participants
Education
October 2007 - April 2009
Hasso Plattner Institute
Field of study
  • IT Systems Engineering
October 2004 - September 2007
Hasso Plattner Institute
Field of study
  • IT Systems Engineering

Publications

Publications (37)
Chapter
Full-text available
Many scientific problems rely on the efficient execution of stencil computations, which are usually memory-bound. In this paper, stencils on two-dimensional data are executed on NUMA architectures. Each node of a NUMA system processes a distinct partition of the input data independent from other nodes. However, processors may need access to the mem...
Conference Paper
Full-text available
For the implementation of data-intensive C++ applications for cache coherent Non-Uniform Memory Access (NUMA) systems, both massive parallelism and data locality have to be considered. While massive parallelism has been largely understood, the shared memory paradigm is still deeply entrenched in the mindset of many C++ software developers. Hence, d...
Article
Full-text available
GPU compute devices have become very popular for general purpose computations. However, the SIMD-like hardware of graphics processors is currently not well suited for irregular workloads, like searching unbalanced trees. In order to mitigate this drawback, NVIDIA introduced an extension to GPU programming models called Dynamic Parallelism. This ext...
Conference Paper
Traditional encryption schemes can effectively ensure the confidentiality of sensitive data stored on cloud infrastructures. Unfortunately, they also prevent most operations on the data such as search by design. As a solution, searchable encryption schemes have been proposed that provide keyword-search capability on encrypted content. In this paper...
Conference Paper
Full-text available
GPU compute devices have become very popular for general purpose computations. However, the SIMD-like hardware of graphics processors is currently not well suited for irregular workloads, like searching unbalanced trees. In order to mitigate this drawback, NVIDIA introduced an extension to GPU programming models called dynamic parallelism. This ext...
Technical Report
Full-text available
In the Gartner hype cycle, cloud computing is a paradigm that has crossed the peak of inflated expectations but also has overcome the worst part of the trough of disillusionment. While the advantages of cloud computing are the best qualification for traversing the slope enlightenment, security concerns are still a major hindrance that prevent full...
Conference Paper
Due to the increasing heterogeneity of parallel and distributed systems, coordination of data (placement) and tasks (scheduling) becomes increasingly complex. Many traditional solutions do not take into account the details of modern system topologies and consequently experience unacceptable performance penalties with modern hierarchical interconnec...
Conference Paper
Full-text available
In recent years the multi-core era started to affect embedded systems, changing some of the rules: While on a single processor, Earliest Deadline First has been proven to be the best algorithm to guarantee the correct execution of priorized tasks, Dhall et al. have shown that this approach is not feasible for multi-processor systems anymore. A vari...
Conference Paper
Blind Signal Separation is an algorithmic problem class that deals with the restoration of original signal data from a signal mixture. Implementations, such as FastICA, are optimized for parallelization on CPU or first-generation GPU hardware. With the advent of modern, compute centered GPU hardware with powerful features such as dynamic parallelis...
Conference Paper
The advent of hybrid CPU-GPU architectures has significantly increased the number of raw FLOP/s. However, it is not obvious how these can be put to use when processing Big Data. In this paper, we present an approach for designing Big Data simulations for hybrid architectures, which is based on a hierarchal application of design patterns in parallel...
Conference Paper
Scale-invariant feature transform (SIFT) is an algorithm to identify and track objects in a series of digital images. The algorithm can handle objects that change their location, scale, rotation or illumination in subsequent images. This makes SIFT an ideal candidate for object tracking – typically denoted as feature detection – problems in compute...
Conference Paper
Scale-invariant feature transform (SIFT) is an algorithm to identify and track objects in a series of digital images. The algorithm can handle objects that change their location, scale, rotation or illumination in subsequent images. This makes SIFT a promising choice for feature detection and tracking in computer vision applications. The only probl...
Conference Paper
The pipeline pattern for parallel programs is utilized in a wide array of scientific applications designed for execution on hybrid CPU-GPU architectures. However, there is a dearth of tools and libraries to support implementation of software pipelines for hybrid architectures. We present the Hybrid Pipeline Framework (HPF) that is intended to fill...
Article
Massive open online courses enjoy a surge of popularity: Numerous platforms such as Coursera, Udacity, edX and many more offer a variety of high-quality courses to learners worldwide. Hasso Plattner Institute is operating its own platform openHPI where selected courses are available. These platforms are well-suited for the presentation of video and...
Conference Paper
InstantLab is our online experimentation platform that is used for hosting exercises and experiments for operating systems and software engineering courses at HPI. In this paper, we discuss challenges and solutions for scaling InstantLab to provide experiment infrastructure for thousands of users in MOOC scenarios. We present InstantLabs XCloud arc...
Conference Paper
Modern server and desktop systems combine multiple computational cores and accelerator devices into a hybrid architecture. GPUs as one class of such devices provide dedicated processing power and memory capacities for data parallel computation of 2D and 3D graphics. Although these cards have demonstrated their applicability in a variety of areas, t...
Data
In this chapter we consider several examples. Each example is given in such a way that it progresses along the theory introduced in the book and that it is possible to study the examples in parallel to the main text. We indicate in the section titles up to which chapter definitions and results are used in that particular section.
Conference Paper
Full-text available
State-of-the-art computer systems are a combination of general purpose processors and special function accelerators. The most common type of accelerators are GPU compute devices, which are used for some years to compute a variety of data parallel tasks fast and energy efficient. Since the release of Intel’s Sandy Bridge architecture and AMD’s APU t...
Article
Full-text available
The advent of homogeneous many-core processors has been widely noticed as a major shift in the architecture of commodity computer systems. It has influenced the design of operating systems and programming models and gives a boost to high-level parallelization libraries. Future commodity systems will combine homogeneous many-core processors with gra...
Conference Paper
Full-text available
Computer architecture is shifting. The upper levels of the software stack are thus to be adapted in order to benefit from the current and future hardware capabilities. In this paper, we present the Hybrid.Parallel library. It is our approach to bridge the gap between state-of-the-art computer architecture and application developers (in contrast to...
Article
Desktop software developers' interest in graphics hardware is increasing as a result of modern graphics cards' capabilities to act as compute devices that augment the main processor. This capability means parallel computing is no longer a dedicated task for the CPU. A trend toward heterogeneous computing combines the main processor and graphics pro...
Conference Paper
Full-text available
Todays commercial off-the-shelf computer systems are multicore computing systems as a combination of CPU, graphic processor (GPU) and custom devices. In comparison with CPU cores, graphic cards are capable to execute hundreds up to thousands compute units in parallel. To benefit from these GPU computing resources, applications have to be paralleliz...
Conference Paper
Full-text available
Conference Paper
Full-text available
Since services are hosted by application servers, shifts in the underlying systems have a great influence on their efficiency and functionality. Therefore it is necessary to get a deep understanding of trends in operating systems and middleware as well as hardware environments. This paper discusses some of these shifts. It will take a short look on...
Thesis
Full-text available
Enterprise applications are becoming increasingly complex. To meet the high demands that are put on them you need sophisticated technologies that support the development of enterprise software and provide a platform to deploy programs in a scalable, flexible and secure environment. Such an environment is provided by the application server for the J...
Article
Full-text available
With the ongoing internationalization of virtuallaboratories, the integration aspect becomes moreimportant. The meanwhile commonly accepted ’glue’ forsuch legacy systems are service oriented architectures, basedon standardized and accepted Web service standards.We present our concept of the ’experiment as a service’,where the idea of service-based...
Conference Paper
Full-text available
Remote and virtual laboratories are commonly used in elec- tronic engineering and computer science to provide hands-on experience for students. Web services have lately emerged as a standardized interfaces to remote laboratory experiments and simulators. One drawback of direct Web service inter- faces to experiments is that the connected hardware c...
Thesis
Full-text available
Within the bachelor project ”DNA“ the Distributed Control Lab (DCL), that facilitates the usage of real-time control experiments, and the ASG-C5 component of the Adaptive Services Grid (ASG) for dynamic placement of services, were combined. Thereby, the ASG-C5 component was reimplemented. Besides, a scheduling mechanism and a component that augment...

Network

Cited By

Projects

Project (1)
Project
OpenSubmit is a small web application for managing student assignment solutions in a university environment. The unique capability of OpenSubmit is the support for coding assignments, were students upload their programming exercise solution as source code archive. OpenSubmit offers an executor daemon that runs on another machine and downloads submitted solutions from the web server. These archives are unpacked and compiled, so that non-compiling assignment solutions are rejected by the system before the deadline. You can also run an assignment-specific validation script that figures out if the student code behaves nicely, before accepting it as solution. This makes the life of the corrector less miserable, because after the deadline, all gradable solutions are ‘valid’. Students also seem to like the idea of having a validated solution, so that they do not fail due to technical difficulties at the correctors side.