arXiv subjects

Sabri Pllana

Publications and source records attributed to Sabri Pllana.

At least 19 recordsLinked to original sources

arXiv2023

DECICE: Device-Edge-Cloud Intelligent Collaboration Framework

DECICE is a Horizon Europe project that is developing an AI-enabled open and portable management framework for automatic and adaptive optimization and deployment of applications in computing continuum encompassing from IoT sensors on the Edge to large-scale Cloud / HPC computing infrastructures. In this paper, we describe the DECICE framework and architecture. Furthermore, we highlight use-cases for framework evaluation: intelligent traffic intersection, magnetic resonance imaging, and emergency response.

cs.DC↗

arXiv2022

Data-driven Real-time Short-term Prediction of Air Quality: Comparison of ES, ARIMA, and LSTM

Air pollution is a worldwide issue that affects the lives of many people in urban areas. It is considered that the air pollution may lead to heart and lung diseases. A careful and timely forecast of the air quality could help to reduce the exposure risk for affected people. In this paper, we use a data-driven approach to predict air quality based on historical data. We compare three popular methods for time series prediction: Exponential Smoothing (ES), Auto-Regressive Integrated Moving Average (ARIMA) and Long short-term memory (LSTM). Considering prediction accuracy and time complexity, our experiments reveal that for short-term air pollution prediction ES performs better than ARIMA and LSTM.

cs.LG↗

arXiv2021

Optimization of Heterogeneous Systems with AI Planning Heuristics and Machine Learning: A Performance and Energy Aware Approach

Heterogeneous computing systems provide high performance and energy efficiency. However, to optimally utilize such systems, solutions that distribute the work across host CPUs and accelerating devices are needed. In this paper, we present a performance and energy aware approach that combines AI planning heuristics for parameter space exploration with a machine learning model for performance and energy evaluation to determine a near-optimal system configuration. For data-parallel applications our approach determines a near-optimal host-device distribution of work, number of processing units required and the corresponding scheduling strategy. We evaluate our approach for various heterogeneous systems accelerated with GPU or the Intel Xeon Phi. The experimental results demonstrate that our approach finds a near-optimal system configuration by evaluating only about 7% of reasonable configurations. Furthermore, the performance per Joule estimation of system configurations using our machine learning model is more than 1000x faster compared to the system evaluation by program execution.

cs.SE↗

arXiv2019

Performance Modelling of Deep Learning on Intel Many Integrated Core Architectures

Many complex problems, such as natural language processing or visual object detection, are solved using deep learning. However, efficient training of complex deep convolutional neural networks for large data sets is computationally demanding and requires parallel computing resources. In this paper, we present two parameterized performance models for estimation of execution time of training convolutional neural networks on the Intel many integrated core architecture. While for the first performance model we minimally use measurement techniques for parameter value estimation, in the second model we estimate more parameters based on measurements. We evaluate the prediction accuracy of performance models in the context of training three different convolutional neural network architectures on the Intel Xeon Phi. The achieved average performance prediction accuracy is about 15% for the first model and 11% for second model.

cs.DC↗

arXiv2019

Customizing Pareto Simulated Annealing for Multi-objective Optimization of Control Cabinet Layout

Determining the optimal location of control cabinet components requires the exploration of a large configuration space. For real-world control cabinets it is impractical to evaluate all possible cabinet configurations. Therefore, we need to apply methods for intelligent exploration of cabinet configuration space that enable to find a near-optimal configuration without evaluation of all possible configurations. In this paper, we describe an approach for multi-objective optimization of control cabinet layout that is based on Pareto Simulated Annealing. Optimization aims at minimizing the total wire length used for interconnection of components and the heat convection within the cabinet. We simulate heat convection to study the warm air flow within the control cabinet and determine the optimal position of components that generate heat during the operation. We evaluate and demonstrate the effectiveness of our approach empirically for various control cabinet sizes and usage scenarios.

cs.OH↗

arXiv2018

HSTREAM: A directive-based language extension for heterogeneous stream computing

Big data streaming applications require utilization of heterogeneous parallel computing systems, which may comprise multiple multi-core CPUs and many-core accelerating devices such as NVIDIA GPUs and Intel Xeon Phis. Programming such systems require advanced knowledge of several hardware architectures and device-specific programming models, including OpenMP and CUDA. In this paper, we present HSTREAM, a compiler directive-based language extension to support programming stream computing applications for heterogeneous parallel computing systems. HSTREAM source-to-source compiler aims to increase the programming productivity by enabling programmers to annotate the parallel regions for heterogeneous execution and generate target specific code. The HSTREAM runtime automatically distributes the workload across CPUs and accelerating devices. We demonstrate the usefulness of HSTREAM language extension with various applications from the STREAM benchmark. Experimental evaluation results show that HSTREAM can keep the same programming simplicity as OpenMP, and the generated code can deliver performance beyond what CPUs-only and GPUs-only executions can deliver.

cs.PL↗

arXiv2018

A Machine Learning Driven IoT Solution for Noise Classification in Smart Cities

We present a machine learning based method for noise classification using a low-power and inexpensive IoT unit. We use Mel-frequency cepstral coefficients for audio feature extraction and supervised classification algorithms (that is, support vector machine and k-nearest neighbors) for noise classification. We evaluate our approach experimentally with a dataset of about 3000 sound samples grouped in eight sound classes (such as, car horn, jackhammer, or street music). We explore the parameter space of support vector machine and k-nearest neighbors algorithms to estimate the optimal parameter values for classification of sound samples in the dataset under study. We achieve a noise classification accuracy in the range 85% -- 100%. Training and testing of our k-nearest neighbors (k = 1) implementation on Raspberry Pi Zero W is less than a second for a dataset with features of more than 3000 sound samples.

cs.SD↗

arXiv2018

Using Meta-heuristics and Machine Learning for Software Optimization of Parallel Computing Systems: A Systematic Literature Review

While modern parallel computing systems offer high performance, utilizing these powerful computing resources to the highest possible extent demands advanced knowledge of various hardware architectures and parallel programming models. Furthermore, optimized software execution on parallel computing systems demands consideration of many parameters at compile-time and run-time. Determining the optimal set of parameters in a given execution context is a complex task, and therefore to address this issue researchers have proposed different approaches that use heuristic search or machine learning. In this paper, we undertake a systematic literature review to aggregate, analyze and classify the existing software optimization methods for parallel computing systems. We review approaches that use machine learning or meta-heuristics for software optimization at compile-time and run-time. Additionally, we discuss challenges and future research directions. The results of this study may help to better understand the state-of-the-art techniques that use machine learning and meta-heuristics to deal with the complexity of software optimization for parallel computing systems. Furthermore, it may aid in understanding the limitations of existing approaches and identification of areas for improvement.

cs.DC↗

arXiv2017

The Internet of Things for Aging and Independent Living: A Modeling and Simulation Study

Population aging is affecting many countries, Sweden being one of them, and it may lead to a shortage of caregivers for elderly people in near future. Smart interconnected devices known as the Internet of Things may help elderly to live independently at home and avoid unnecessary hospital stay. For instance, a carephone device enables the elderly to establish a communication link with caregivers and ask for help when it is needed. In this paper, we describe a simulation study of the care giving system in the Växjö municipality in Sweden. The simulation model can be used to address various issues, such as, determining the lack or excess of resources or long waiting times, and study the system behavior when the number of alarms is increased.

cs.CY↗

arXiv2017

Benchmarking OpenCL, OpenACC, OpenMP, and CUDA: programming productivity, performance, and energy consumption

Many modern parallel computing systems are heterogeneous at their node level. Such nodes may comprise general purpose CPUs and accelerators (such as, GPU, or Intel Xeon Phi) that provide high performance with suitable energy-consumption characteristics. However, exploiting the available performance of heterogeneous architectures may be challenging. There are various parallel programming frameworks (such as, OpenMP, OpenCL, OpenACC, CUDA) and selecting the one that is suitable for a target context is not straightforward. In this paper, we study empirically the characteristics of OpenMP, OpenACC, OpenCL, and CUDA with respect to programming productivity, performance, and energy. To evaluate the programming productivity we use our homegrown tool CodeStat, which enables us to determine the percentage of code lines that was required to parallelize the code using a specific framework. We use our tool x-MeterPU to evaluate the energy consumption and the performance. Experiments are conducted using the industry-standard SPEC benchmark suite and the Rodinia benchmark suite for accelerated computing on heterogeneous systems that combine Intel Xeon E5 Processors with a GPU accelerator or an Intel Xeon Phi co-processor.

cs.DC↗

arXiv2017

Using Cognitive Computing for Learning Parallel Programming: An IBM Watson Solution

While modern parallel computing systems provide high performance resources, utilizing them to the highest extent requires advanced programming expertise. Programming for parallel computing systems is much more difficult than programming for sequential systems. OpenMP is an extension of C++ programming language that enables to express parallelism using compiler directives. While OpenMP alleviates parallel programming by reducing the lines of code that the programmer needs to write, deciding how and when to use these compiler directives is up to the programmer. Novice programmers may make mistakes that may lead to performance degradation or unexpected program behavior. Cognitive computing has shown impressive results in various domains, such as health or marketing. In this paper, we describe the use of IBM Watson cognitive system for education of novice parallel programmers. Using the dialogue service of the IBM Watson we have developed a solution that assists the programmer in avoiding common OpenMP mistakes. To evaluate our approach we have conducted a survey with a number of novice parallel programmers at the Linnaeus University, and obtained encouraging results with respect to usefulness of our approach.

cs.PL↗

arXiv2017

CHAOS: A Parallelization Scheme for Training Convolutional Neural Networks on Intel Xeon Phi

Deep learning is an important component of big-data analytic tools and intelligent applications, such as, self-driving cars, computer vision, speech recognition, or precision medicine. However, the training process is computationally intensive, and often requires a large amount of time if performed sequentially. Modern parallel computing systems provide the capability to reduce the required training time of deep neural networks. In this paper, we present our parallelization scheme for training convolutional neural networks (CNN) named Controlled Hogwild with Arbitrary Order of Synchronization (CHAOS). Major features of CHAOS include the support for thread and vector parallelism, non-instant updates of weight parameters during back-propagation without a significant delay, and implicit synchronization in arbitrary order. CHAOS is tailored for parallel computing systems that are accelerated with the Intel Xeon Phi. We evaluate our parallelization approach empirically using measurement techniques and performance modeling for various numbers of threads and CNN architectures. Experimental results for the MNIST dataset of handwritten digits using the total number of threads on the Xeon Phi show speedups of up to 103x compared to the execution on one thread of the Xeon Phi, 14x compared to the sequential execution on Intel Xeon E5, and 58x compared to the sequential execution on Intel Core i5.

cs.DC↗

arXiv2017

Pushing STEM-education through a social-media-based contest format - experiences and lessons-learned from the H2020-project SciChallenge

Science education is a crucial issue with long-term impacts for Europe as the low enrolment rates in the STEM-fields, including (natural) science, technology, engineering and mathematics, will lead to a workforce problem in research and development. In order to address this challenge, the EU-funded research project SciChallenge (project.scichallenge.eu) aims to find a new way for getting young people more interested in STEM. For this purpose, the project developed and implemented a social-media-based STEM-contest for young people, which aims at increasing the attractiveness of science education and careers among young people. In the first two parts, the paper reflects on the problem, introduces the project and highlights the main steps of the preparation of the contest. The third section of the paper presents the idea, design and implementation of the digital contest platform (www.scichallenge.eu), which serves as the core of the challenge. The fourth part of the paper will provide a status update on the contest pilot. It will provide a summary of the experiences that the consortium made with this novel approach as well as the main obstacles that the consortium was facing. The paper will conclude with a preliminary reflection on the question if such an approach can help to increase the interest of young people in STEM-education and careers.

cs.CY↗

arXiv2016

Combinatorial Optimization of Work Distribution on Heterogeneous Systems

We describe an approach that uses combinatorial optimization and machine learning to share the work between the host and device of heterogeneous computing systems such that the overall application execution time is minimized. We propose to use combinatorial optimization to search for the optimal system configuration in the given parameter space (such as, the number of threads, thread affinity, work distribution for the host and device). For each system configuration that is suggested by combinatorial optimization, we use machine learning for evaluation of the system performance. We evaluate our approach experimentally using a heterogeneous platform that comprises two 12-core Intel Xeon E5 CPUs and an Intel Xeon Phi 7120P co-processor with 61 cores. Using our approach we are able to find a near-optimal system configuration by performing only about 5% of all possible experiments.

cs.DC↗

arXiv2016

SciChallenge: Using Student-Generated Content and Contests to Enhance the Interest for Science Education and Careers

Science education will play a vital role in shaping the present and future of modern societies. Thus, Europe needs all its talents to increase creativity and competitiveness. Young boys and girls especially have to be engaged to pursue careers in Science, Technology, Engineering and Mathematics (STEM). However, statistics still show that enrolment rates in STEM-based degree programs are decreasing. This will lead to a workforce problem in the industrial sector as well as in research and development, especially in many of the new member countries. This paper highlights a recently funded EU-research project SciChallenge (www.scichallenge.eu), which focuses on the development of novel concepts to get young people excited about science education. It uses a contest-based approach towards self-produced digital education materials from young people for young people. In cooperation with partner schools, teachers, and other youth-oriented institutions, the contest participants (individuals or groups) between the ages of 10 and 20 years generate creative digital materials (videos, slides, or infographics). The participants upload their content in social media channels and the submissions are aggregated on the SciChallenge Web Platform. The winners receive prizes funded by science-oriented industry and other stakeholders. Intelligent cross-sectoral positioning of various awareness modules on the SciChallenge Open Information Hub is expected to increase awareness on science careers. Through a strong involvement of related organizations and industries, we expect to open new opportunities for young people in regards to internships or taster days in STEM disciplines. Additionally, aggregated information on science events (such as, slams, nights, festivals) is shared. With this multi-level approach, SciChallenge may boost the attractiveness of science education and careers among young people.

cs.CY↗

arXiv2016

A Survey of the State of the Art in Data Mining and Integration Query Languages

The major aim of this survey is to identify the strengths and weaknesses of a representative set of Data-Mining and Integration (DMI) query languages. We describe a set of properties of DMI-related languages that we use for a systematic evaluation of these languages. In addition, we introduce a scoring system that we use to quantify our opinion on how well a DMI-related language supports a property. The languages surveyed in this paper include: DMQL, MineSQL, MSQL, M2MQL, dmFSQL, OLEDB for DM, MINE RULE, and Oracle Data Mining. This survey may help researchers to propose a DMI language that is beyond the state-of-the-art, or it may help practitioners to select an existing language that fits well a purpose.

cs.DB↗

arXiv2015

Analyzing large-scale DNA Sequences on Multi-core Architectures

Rapid analysis of DNA sequences is important in preventing the evolution of different viruses and bacteria during an early phase, early diagnosis of genetic predispositions to certain diseases (cancer, cardiovascular diseases), and in DNA forensics. However, real-world DNA sequences may comprise several Gigabytes and the process of DNA analysis demands adequate computational resources to be completed within a reasonable time. In this paper we present a scalable approach for parallel DNA analysis that is based on Finite Automata, and which is suitable for analyzing very large DNA segments. We evaluate our approach for real-world DNA segments of mouse (2.7GB), cat (2.4GB), dog (2.4GB), chicken (1GB), human (3.2GB) and turkey (0.2GB). Experimental results on a dual-socket shared-memory system with 24 physical cores show speed-ups of up to 17.6x. Our approach is up to 3x faster than a pattern-based parallel approach that uses the RE2 library.

cs.DC↗

arXiv2015

The Potential of the Intel Xeon Phi for Supervised Deep Learning

Supervised learning of Convolutional Neural Networks (CNNs), also known as supervised Deep Learning, is a computationally demanding process. To find the most suitable parameters of a network for a given application, numerous training sessions are required. Therefore, reducing the training time per session is essential to fully utilize CNNs in practice. While numerous research groups have addressed the training of CNNs using GPUs, so far not much attention has been paid to the Intel Xeon Phi coprocessor. In this paper we investigate empirically and theoretically the potential of the Intel Xeon Phi for supervised learning of CNNs. We design and implement a parallelization scheme named CHAOS that exploits both the thread- and SIMD-parallelism of the coprocessor. Our approach is evaluated on the Intel Xeon Phi 7120P using the MNIST dataset of handwritten digits for various thread counts and CNN architectures. Results show a 103.5x speed up when training our large network for 15 epochs using 244 threads, compared to one thread on the coprocessor. Moreover, we develop a performance model and use it to assess our implementation and answer what-if questions.

cs.DC↗