Dalvan Griebler

@article{MENCAGLI:JPDC:24,

title = {General-purpose data stream processing on heterogeneous architectures with WindFlow},

author = {Gabriele Mencagli and Massimo Torquati and Dalvan Griebler and Alessandra Fais and Marco Danelutto},

url = {https://www.sciencedirect.com/science/article/pii/S0743731523001521},

doi = {https://doi.org/10.1016/j.jpdc.2023.104782},

year  = {2024},

date = {2024-02-01},

journal = {Journal of Parallel and Distributed Computing},

volume = {184},

pages = {104782},

publisher = {Elsevier},

abstract = {Many emerging applications analyze data streams by running graphs of communicating tasks called operators. To develop and deploy such applications, Stream Processing Systems (SPSs) like Apache Storm and Flink have been made available to researchers and practitioners. They exhibit imperative or declarative programming interfaces to develop operators running arbitrary algorithms working on structured or unstructured data streams. In this context, the interest in leveraging hardware acceleration with GPUs has become more pronounced in high-throughput use cases. Unfortunately, GPU acceleration has been studied for relational operators working on structured streams only, while non-relational operators have often been overlooked. This paper presents WindFlow, a library supporting the seamless GPU offloading of general partitioned-stateful operators, extending the range of operators that benefit from hardware acceleration. Its design provides high throughput still exposing a high-level API to users compared with the raw utilization of GPUs in Apache Flink.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{BIANCHESSI:WSCAD:23,

title = {Conversão do NAS Parallel Benchmarks para C++ Standard},

author = {Arthur S. Bianchessi and Leonardo Mallmann and Renato Barreto Hoffmann and Dalvan Griebler},

url = {https://doi.org/},

year  = {2023},

date = {2023-10-01},

booktitle = {Anais do XXIII Simpósio em Sistemas Computacionais de Alto Desempenho (WSCAD)},

pages = {1-12},

publisher = {SBC},

address = {Porto Alegre, Brasil},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ALF:WSCAD:23,

title = {Análise da Execução de Algoritmos de Aprendizado de Máquina em Dispositivos Embarcados},

author = {Lucas Alf and Renato Barreto Hoffmann and Caetano Müller and Dalvan Griebler},

url = {https://doi.org/},

year  = {2023},

date = {2023-10-01},

booktitle = {Anais do XXIII Simpósio em Sistemas Computacionais de Alto Desempenho (WSCAD)},

pages = {1-12},

publisher = {SBC},

address = {Porto Alegre, Brasil},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ANDRADE:WSCAD:23,

title = {Extending the Planning Poker Method to Estimate the Development Effort of Parallel Applications},

author = {Gabriella Andrade and Dalvan Griebler and Rodrigo Santos and Luiz Gustavo Fernandes},

url = {https://doi.org/},

year  = {2023},

date = {2023-10-01},

booktitle = {Anais do XXIII Simpósio em Sistemas Computacionais de Alto Desempenho (WSCAD)},

pages = {1-12},

publisher = {SBC},

address = {Porto Alegre, Brasil},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{larcc:MALISZEWSKI:SBAC-PADW:23,

title = {Evaluation Model and Performance Analysis of NIC Aggregations in Containerized Private Clouds},

author = {Anderson Matthias Maliszewski and Dalvan Griebler and Eduardo Roloff and Rodrigo Rosa Righi and Philippe O. A. Navaux},

url = {https://doi.org/10.1109/SBAC-PADW60351.2023.00025},

doi = {10.1109/SBAC-PADW60351.2023.00025},

year  = {2023},

date = {2023-10-01},

booktitle = {International Symposium on Computer Architecture and High Performance Computing Workshops (SBAC-PADW)},

pages = {101-107},

publisher = {IEEE},

address = {Porto Alegre, Brazil},

series = {SBAC-PADW'23},

abstract = {The availability of computational resources changed significantly due to cloud computing. In addition, we have witnessed efforts to execute High-Performance Computing (HPC) applications in the cloud attracted by the advantages of cost savings and scalable/elastic resource allocation. Allocating more powerful hardware and exclusivity allocating resources such as memory, storage, and CPU can improve performance in the cloud. For network interconnection, significant noise, and other inferences are generated by several simultaneous instances (multitenants) communicating using the same network. As increasing the network bandwidth may be an alternative, we designed an evaluation model, and performance analysis of NIC aggregation approaches in containerized private clouds. The experiments using NAS Parallel Benchmarks revealed that NIC aggregation approach outperforms the baseline up to ≈98% of the executions with applications characterized by intensive network use. Also, the Balance Round-Robin aggregation mode performed better than the 802.3ad aggregation mode in most assessments.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{HOFFMANN:SBAC-PADW:23,

title = {Analyzing C++ Stream Parallelism in Shared-Memory when Porting to Flink and Storm},

author = {Renato Barreto Hoffmann and Leonardo Faé and Isabel Manssour and Dalvan Griebler},

url = {https://doi.org/10.1109/SBAC-PADW60351.2023.00017},

doi = {10.1109/SBAC-PADW60351.2023.00017},

year  = {2023},

date = {2023-10-01},

booktitle = {International Symposium on Computer Architecture and High Performance Computing Workshops (SBAC-PADW)},

pages = {1-8},

publisher = {IEEE},

address = {Porto Alegre, Brazil},

series = {SBAC-PADW'23},

abstract = {Stream processing plays a crucial role in various information-oriented digital systems. Two popular frameworks for real-time data processing, Flink and Storm, provide solutions for effective parallel stream processing in Java. An option to leverage Java's mature ecosystem for distributed stream processing involves porting legacy C++ applications to Java. However, this raises considerations on the adequacy of the equivalent Java mechanisms and potential degradation in throughput. Therefore, our objective is to evaluate programmability and performance when converting stream processing applications from C++ to Java while also exploring the parallelization capabilities offered by Flink and Storm. Furthermore, we aim to assess the throughput of Flink and Storm on shared-memory manycore machines, a hardware architecture commonly found in cloud environments. To achieve this, we conduct experiments involving four different stream processing applications. We highlight challenges encountered when porting C++ to Java and working with Flink and Storm. Furthermore, we discuss throughput, latency, CPU, and memory usage results.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{FAE:SBLP:23,

title = {Source-to-Source Code Transformation on Rust for High-Level Stream Parallelism},

author = {Leonardo Faé and Renato Barreto Hoffmann and Dalvan Griebler},

url = {https://doi.org/10.1145/3624309.3624320},

doi = {10.1145/3624309.3624320},

year  = {2023},

date = {2023-09-01},

booktitle = {XXVII Brazilian Symposium on Programming Languages (SBLP)},

pages = {41-49},

publisher = {ACM},

address = {Campo Grande, Brazil},

series = {SBLP'23},

abstract = {Utilizing parallel systems to their full potential can be challenging for general-purpose developers. A solution to this problem is to create high-level abstractions using Domain-Specific Languages (DSL). We create a stream-processing DSL for Rust, a growing programming language focusing on performance and safety. To that end, we explore Rust’s macros as a high-level abstraction tool to support an existing DSL language named SPar and perform source-to-source code transformations in the abstract syntax tree. We aim to assess the Rust source-to-source code transformations toolset and its implications. We highlight that Rust macros are powerful tools for performing source-to-source code transformations for abstracting structured stream processing. In addition, execution time and programmability results are comparable to other solutions.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{LEONARCZYK:Euro-ParW:23,

title = {Evaluation of Adaptive Micro-batching Techniques for GPU-accelerated Stream Processing},

author = {Ricardo Leonarczyk and Dalvan Griebler and Gabriele Mencagli and Marco Danelutto},

url = {https://doi.org/},

year  = {2023},

date = {2023-08-01},

booktitle = {Euro-ParW 2023: Parallel Processing Workshops},

pages = {1-8},

publisher = {Springer},

address = {Limassol},

series = {Euro-ParW'23},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{ANDRADE:CSI:2023,

title = {A parallel programming assessment for stream processing applications on multi-core systems},

author = {Gabriella Andrade and Dalvan Griebler and Rodrigo Santos and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1016/j.csi.2022.103691},

doi = {10.1016/j.csi.2022.103691},

year  = {2023},

date = {2023-03-01},

journal = {Computer Standards & Interfaces},

volume = {84},

pages = {103691},

publisher = {Elsevier},

abstract = {Multi-core systems are any computing device nowadays and stream processing applications are becoming recurrent workloads, demanding parallelism to achieve the desired quality of service. As soon as data, tasks, or requests arrive, they must be computed, analyzed, or processed. Since building such applications is not a trivial task, the software industry must adopt parallel APIs (Application Programming Interfaces) that simplify the exploitation of parallelism in hardware for accelerating time-to-market. In the last years, research efforts in academia and industry provided a set of parallel APIs, increasing productivity to software developers. However, a few studies are seeking to prove the usability of these interfaces. In this work, we aim to present a parallel programming assessment regarding the usability of parallel API for expressing parallelism on the stream processing application domain and multi-core systems. To this end, we conducted an empirical study with beginners in parallel application development. The study covered three parallel APIs, reporting several quantitative and qualitative indicators involving developers. Our contribution also comprises a parallel programming assessment methodology, which can be replicated in future assessments. This study revealed important insights such as recurrent compile-time and programming logic errors performed by beginners in parallel programming, as well as the programming effort, challenges, and learning curve. Moreover, we collected the participants’ opinions about their experience in this study to understand deeply the results achieved.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{VOGEL:PDP:23,

title = {Revisiting self-adaptation for efficient decision-making at run-time in parallel executions},

author = {Adriano Vogel and Marco Danelutto and Dalvan Griebler and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/PDP59025.2023.00015},

doi = {10.1109/PDP59025.2023.00015},

year  = {2023},

date = {2023-03-01},

booktitle = {31st Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {43-50},

publisher = {IEEE},

address = {Naples, Italy},

series = {PDP'23},

abstract = {Self-adaptation is a potential alternative to provide a higher level of autonomic abstractions and run-time responsiveness in parallel executions. However, the recurrent problem is that self-adaptation is still limited in flexibility and efficiency. For instance, there is a lack of mechanisms to apply adaptation actions and efficient decision-making strategies to decide which configurations should be conveniently enforced at run-time. In this work, we are interested in providing and evaluating potential abstractions achievable with self-adaptation transparently managing parallel executions. Therefore, we provide a new mechanism to support self-adaptation in applications with multiple parallel stages executed in multi-cores. Moreover, we reproduce, reimplement, and evaluate an existing decision-making strategy in our scenario. The observations from the results show that the proposed mechanism for self-adaptation can provide new parallelism abstractions and autonomous responsiveness at run-time. On the other hand, there is a need for more accurate decision-making strategies to enable efficient executions of applications in resource-constrained scenarios like multi-cores.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GARCIA:PDP:23,

title = {A Latency, Throughput, and Programmability Perspective of GrPPI for Streaming on Multi-cores},

author = {Adriano Marques Garcia and Dalvan Griebler and Claudio Schepke and José Daniel García and Javier Fernández Muñoz and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/PDP59025.2023.00033},

doi = {10.1109/PDP59025.2023.00033},

year  = {2023},

date = {2023-03-01},

booktitle = {31st Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {164-168},

publisher = {IEEE},

address = {Naples, Italy},

series = {PDP'23},

abstract = {Several solutions aim to simplify the burdening task of parallel programming. The GrPPI library is one of them. It allows users to implement parallel code for multiple backends through a unified, abstract, and generic layer while promising minimal overhead on performance. An outspread evaluation of GrPPI regarding stream parallelism with representative metrics for this domain, such as throughput and latency, was not yet done. In this work, we evaluate GrPPI focused on stream processing. We evaluate performance, memory usage, and programming effort and compare them against handwritten parallel code. For this, we use the benchmarking framework SPBench to build custom GrPPI benchmarks. The basis of the benchmarks is real applications, such as Lane Detection, Bzip2, Face Recognizer, and Ferret. Experiments show that while performance is competitive with handwritten code in some cases, in other cases, the infeasibility of fine-tuning GrPPI is a crucial drawback. Despite this, programmability experiments estimate that GrPPI has the potential to reduce by about three times the development time of parallel applications.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{GARCIA:JS:23,

title = {Micro-batch and data frequency for stream processing on multi-cores},

author = {Adriano Marques Garcia and Dalvan Griebler and Claudio Schepke and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1007/s11227-022-05024-y},

doi = {10.1007/s11227-022-05024-y},

year  = {2023},

date = {2023-01-01},

journal = {The Journal of Supercomputing},

volume = {79},

number = {8},

pages = {9206-9244},

publisher = {Springer},

abstract = {Latency or throughput is often critical performance metrics in stream processing. Applications’ performance can fluctuate depending on the input stream. This unpredictability is due to the variety in data arrival frequency and size, complexity, and other factors. Researchers are constantly investigating new ways to mitigate the impact of these variations on performance with self-adaptive techniques involving elasticity or micro-batching. However, there is a lack of benchmarks capable of creating test scenarios to further evaluate these techniques. This work extends and improves the SPBench benchmarking framework to support dynamic micro-batching and data stream frequency management. We also propose a set of algorithms that generates the most commonly used frequency patterns for benchmarking stream processing in related work. It allows the creation of a wide variety of test scenarios. To validate our solution, we use SPBench to create custom benchmarks and evaluate the impact of micro-batching and data stream frequency on the performance of Intel TBB and FastFlow. These are two libraries that leverage stream parallelism for multi-core architectures. Our results demonstrated that our test cases did not benefit from micro-batches on multi-cores. For different data stream frequency configurations, TBB ensured the lowest latency, while FastFlow assured higher throughput in shorter pipelines.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ARAUJO:SPE:23,

title = {NAS Parallel Benchmarks with CUDA and Beyond},

author = {Gabriell Araujo and Dalvan Griebler and Dinei A. Rockenbach and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1002/spe.3056},

doi = {10.1002/spe.3056},

year  = {2023},

date = {2023-01-01},

journal = {Software: Practice and Experience},

volume = {53},

number = {1},

pages = {53-80},

publisher = {Wiley},

abstract = {NAS Parallel Benchmarks (NPB) is a standard benchmark suite used in the evaluation of parallel hardware and software. Several research efforts from academia have made these benchmarks available with different parallel programming models beyond the original versions with OpenMP and MPI. This work joins these research efforts by providing a new CUDA implementation for NPB. Our contribution covers different aspects beyond the implementation. First, we define design principles based on the best programming practices for GPUs and apply them to each benchmark using CUDA. Second, we provide ease of use parametrization support for configuring the number of threads per block in our version. Third, we conduct a broad study on the impact of the number of threads per block in the benchmarks. Fourth, we propose and evaluate five strategies for helping to find a better number of threads per block configuration. The results have revealed relevant performance improvement solely by changing the number of threads per block, showing performance improvements from 8% up to 717% among the benchmarks. Fifth, we conduct a comparative analysis with the literature, evaluating performance, memory consumption, code refactoring required, and parallelism implementations. The performance results have shown up to 267% improvements over the best benchmarks versions available. We also observe the best and worst design choices, concerning code size and the performance trade-off. Lastly, we highlight the challenges of implementing parallel CFD applications for GPUs and how the computations impact the GPU's behavior.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{GARCIA:Computing:23,

title = {SPBench: a framework for creating benchmarks of stream processing applications},

author = {Adriano Marques Garcia and Dalvan Griebler and Claudio Schepke and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1007/s00607-021-01025-6},

doi = {10.1007/s00607-021-01025-6},

year  = {2023},

date = {2023-01-01},

journal = {Computing},

volume = {105},

number = {5},

pages = {1077-1099},

publisher = {Springer},

abstract = {In a fast-changing data-driven world, real-time data processing systems are becoming ubiquitous in everyday applications. The increasing data we produce, such as audio, video, image, and, text are demanding quickly and efficiently computation. Stream Parallelism allows accelerating this computation for real-time processing. But it is still a challenging task and most reserved for experts. In this paper, we present SPBench, a framework for benchmarking stream processing applications. It aims to support users with a set of real-world stream processing applications, which are made accessible through an Application Programming Interface (API) and executable via Command Line Interface (CLI) to create custom benchmarks. We tested SPBench by implementing parallel benchmarks with Intel Threading Building Blocks (TBB), FastFlow, and SPar. This evaluation provided useful insights and revealed the feasibility of the proposed framework in terms of usage, customization, and performance analysis. SPBench demonstrated to be a high-level, reusable, extensible, and easy of use abstraction to build parallel stream processing benchmarks on multi-core architectures.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{LOFF:COLA:22,

title = {Combining stream with data parallelism abstractions for multi-cores},

author = {Júnior Löff and Renato Barreto Hoffmann and Dalvan Griebler and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1016/j.cola.2022.101160},

doi = {10.1016/j.cola.2022.101160},

year  = {2022},

date = {2022-12-01},

journal = {Journal of Computer Languages},

volume = {73},

pages = {101160},

publisher = {Elsevier},

abstract = {Stream processing applications have seen an increasing demand with the raised availability of sensors, IoT devices, and user data. Modern systems can generate millions of data items per day that require to be processed timely. To deal with this demand, application programmers must consider parallelism to exploit the maximum performance of the underlying hardware resources. In this work, we introduce improvements to stream processing applications by exploiting fine-grained data parallelism (via Map and MapReduce) inside coarse-grained stream parallelism stages. The improvements are including techniques for identifying data parallelism in sequential codes, a new language, semantic analysis, and a set of definition and transformation rules to perform source-to-source parallel code generation. Moreover, we investigate the feasibility of employing higher-level programming abstractions to support the proposed optimizations. For that, we elect SPar programming model as a use case, and extend it by adding two new attributes to its language and implementing our optimizations as a new algorithm in the SPar compiler. We conduct a set of experiments in representative stream processing and data-parallel applications. The results showed that our new compiler algorithm is efficient and that performance improved by up to 108.4x in data-parallel applications. Furthermore, experiments evaluating stream processing applications towards the composition of stream and data parallelism revealed new insights. The results showed that such composition may improve latencies by up to an order of magnitude. Also, it enables programmers to exploit different degrees of stream and data parallelism to accomplish a balance between throughput and latency according to their necessity.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Ernstsson:IJPP:22,

title = {Assessing Application Efficiency and Performance Portability in Single-Source Programming for Heterogeneous Parallel Systems},

author = {August Ernstsson and Dalvan Griebler and Christoph Kessler},

url = {https://doi.org/10.1007/s10766-022-00746-1},

doi = {10.1007/s10766-022-00746-1},

year  = {2022},

date = {2022-12-01},

journal = {International Journal of Parallel Programming},

volume = {51},

number = {5},

pages = {61-82},

publisher = {Springer},

abstract = {We analyze the performance portability of the skeleton-based, single-source multi-backend high-level programming framework SkePU across multiple different CPU–GPU heterogeneous systems. Thereby, we provide a systematic application efficiency characterization of SkePU-generated code in comparison to equivalent hand-written code in more low-level parallel programming models such as OpenMP and CUDA. For this purpose, we contribute ports of the STREAM benchmark suite and of a part of the NAS Parallel Benchmark suite to SkePU. We show that for STREAM and the EP benchmark, SkePU regularly scores efficiency values above 80% and in particular for CPU systems, SkePU can outperform hand-written code..},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{ROCKENBACH:SBLP:22,

title = {High-Level Stream and Data Parallelism in C++ for GPUs},

author = {Dinei A. Rockenbach and Júnior Löff and Gabriell Araujo and Dalvan Griebler and Luiz G. Fernandes},

url = {https://doi.org/10.1145/3561320.3561327},

doi = {10.1145/3561320.3561327},

year  = {2022},

date = {2022-10-01},

booktitle = {XXVI Brazilian Symposium on Programming Languages (SBLP)},

pages = {41-49},

publisher = {ACM},

address = {Uberlândia, Brazil},

series = {SBLP'22},

abstract = {GPUs are massively parallel processors that allow solving problems that are not viable to traditional processors like CPUs. However, implementing applications for GPUs is challenging to programmers as it requires parallel programming to efficiently exploit the GPU resources. In this sense, parallel programming abstractions, notably domain-specific languages, are fundamental for improving programmability. SPar is a high-level Domain-Specific Language (DSL) that allows expressing stream and data parallelism in the serial code through annotations using C++ attributes. This work elaborates on a methodology and tool for GPU code generation by introducing new attributes to SPar language and transformation rules to SPar compiler. These new contributions, besides the gains in simplicity and code reduction compared to CUDA and OpenCL, enabled SPar achieve of higher throughput when exploring combined CPU and GPU parallelism, and when using batching.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ANDRADE:WSCAD:22,

title = {Opinião de Brasileiros Sobre a Produtividade no Desenvolvimento de Aplicações Paralelas},

author = {Gabriella Andrade and Dalvan Griebler and Rodrigo Santos and Luiz Gustavo Fernandes},

url = {https://doi.org/10.5753/wscad.2022.226392},

doi = {10.5753/wscad.2022.226392},

year  = {2022},

date = {2022-10-01},

booktitle = {Anais do XXII Simpósio em Sistemas Computacionais de Alto Desempenho (WSCAD)},

pages = {276-287},

publisher = {SBC},

address = {Florianópolis, Brasil},

abstract = {A partir da popularização das arquiteturas paralelas, surgiram várias interfaces de programação a fim de facilitar a exploração de tais arquiteturas e aumentar a produtividade dos desenvolvedores. Entretanto, desenvolver aplicações paralelas ainda é uma tarefa complexa para desenvolvedores com pouca experiência. Neste trabalho, realizamos uma pesquisa para descobrir a opinião de desenvolvedores de aplicações paralelas sobre os fatores que impedem a produtividade. Nossos resultados mostraram que a experiência dos desenvolvedores é uma das principais razões para a baixa produtividade. Além disso, os resultados indicaram formas para contornar este problema, como melhorar e incentivar o ensino de programação paralela em cursos de graduação.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ANDRADE:SEAA:22,

title = {Analyzing Programming Effort Model Accuracy of High-Level Parallel Programs for Stream Processing},

author = {Gabriella Andrade and Dalvan Griebler and Rodrigo Santos and Christoph Kessler and August Ernstsson and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/SEAA56994.2022.00043},

doi = {10.1109/SEAA56994.2022.00043},

year  = {2022},

date = {2022-09-01},

booktitle = {48th Euromicro Conference on Software Engineering and Advanced Applications (SEAA 2022)},

pages = {229-232},

publisher = {IEEE},

address = {Gran Canaria, Spain},

series = {SEAA'22},

abstract = {Over the years, several Parallel Programming Models (PPMs) have supported the abstraction of programming complexity for parallel computer systems. However, few studies aim to evaluate the productivity reached by such abstractions since this is a complex task that involves human beings. There are several studies to develop predictive methods to estimate the effort required to program applications in software engineering. In order to evaluate the reliability of such metrics, it is necessary to assess the accuracy in different programming domains. In this work, we used the data of an experiment conducted with beginners in parallel programming to determine the effort required for implementing stream parallelism using FastFlow, SPar, and TBB. Our results show that some traditional software effort estimation models, such as COCOMO II, fall short, while Putnam's model could be an alternative for high-level PPMs evaluation. To overcome the limitations of existing models, we plan to create a parallelism-aware model to evaluate applications in this domain in future work.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GARCIA:PDP:22,

title = {Evaluating Micro-batch and Data Frequency for Stream Processing Applications on Multi-cores},

author = {Adriano Marques Garcia and Dalvan Griebler and Claudio Schepke and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/PDP55904.2022.00011},

doi = {10.1109/PDP55904.2022.00011},

year  = {2022},

date = {2022-04-01},

booktitle = {30th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {10-17},

publisher = {IEEE},

address = {Valladolid, Spain},

series = {PDP'22},

abstract = {In stream processing, data arrives constantly and is often unpredictable. It can show large fluctuations in arrival frequency, size, complexity, and other factors. These fluctuations can strongly impact application latency and throughput, which are critical factors in this domain. Therefore, there is a significant amount of research on self-adaptive techniques involving elasticity or micro-batching as a way to mitigate this impact. However, there is a lack of benchmarks and tools for helping researchers to investigate micro-batching and data stream frequency implications. In this paper, we extend a benchmarking framework to support dynamic micro-batching and data stream frequency management. We used it to create custom benchmarks and compare latency and throughput aspects from two different parallel libraries. We validate our solution through an extensive analysis of the impact of micro-batching and data stream frequency on stream processing applications using Intel TBB and FastFlow, which are two libraries that leverage stream parallelism on multi-core architectures. Our results demonstrated up to 33% throughput gain over latency using micro-batches. Additionally, while TBB ensures lower latency, FastFlow ensures higher throughput in the parallel applications for different data stream frequency configurations.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{MENCAGLI:PDP:22,

title = {Towards Parallel Data Stream Processing on System-on-Chip CPU+GPU Devices},

author = {Gabriele Mencagli and Dalvan Griebler and Marco Danelutto},

url = {https://doi.org/10.1109/PDP55904.2022.00014},

doi = {10.1109/PDP55904.2022.00014},

year  = {2022},

date = {2022-04-01},

booktitle = {30th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {34-38},

publisher = {IEEE},

address = {Valladolid, Spain},

series = {PDP'22},

abstract = {Data Stream Processing is a pervasive computing paradigm with a wide spectrum of applications. Traditional streaming systems exploit the processing capabilities provided by homogeneous Clusters and Clouds. Due to the transition to streaming systems suitable for IoT/Edge environments, there has been the urgent need of new streaming frameworks and tools tailored for embedded platforms, often available as System-onChips composed of a small multicore CPU and an integrated onchip GPU. Exploiting this hybrid hardware requires special care in the runtime system design. In this paper, we discuss the support provided by the WindFlow library, showing its design principles and its effectiveness on the NVIDIA Jetson Nano board.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{GOMES:IJCSIT:22,

title = {Steam++: An Extensible End-to-end Framework for Developing IoT Data Processing Applications in the Fog},

author = {Márcio Miguel Gomes and Rodrigo Rosa Righi and Cristiano André Costa and Dalvan Griebler},

url = {http://dx.doi.org/10.5121/ijcsit.2022.14103},

doi = {10.5121/ijcsit.2022.14103},

year  = {2022},

date = {2022-02-01},

journal = {International Journal of Computer Science & Information Technology},

volume = {14},

number = {1},

pages = {31-51},

publisher = {AIRCC},

abstract = {IoT applications usually rely on cloud computing services to perform data analysis such as filtering, aggregation, classification, pattern detection, and prediction. When applied to specific domains, the IoT needs to deal with unique constraints. Besides the hostile environment such as vibration and electricmagnetic interference, resulting in malfunction, noise, and data loss, industrial plants often have Internet access restricted or unavailable, forcing us to design stand-alone fog and edge computing solutions. In this context, we present STEAM++, a lightweight and extensible framework for real-time data stream processing and decision-making in the network edge, targeting hardware-limited devices, besides proposing a micro-benchmark methodology for assessing embedded IoT applications. In real-case experiments in a semiconductor industry, we processed an entire data flow, from values sensing, processing and analysing data, detecting relevant events, and finally, publishing results to a dashboard. On average, the application consumed less than 500kb RAM and 1.0% of CPU usage, processing up to 239 data packets per second and reducing the output data size to 14% of the input raw data size when notifying events.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{LOFF:IJPP:22,

title = {DSParLib: A C++ Template Library for Distributed Stream Parallelism},

author = {Júnior Löff and Renato Barreto Hoffmann and Ricardo Pieper and Dalvan Griebler and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1007/s10766-022-00737-2},

doi = {10.1007/s10766-022-00737-2},

year  = {2022},

date = {2022-01-01},

journal = {International Journal of Parallel Programming},

volume = {50},

number = {5},

pages = {454-485},

publisher = {Springer},

abstract = {Stream processing applications deal with millions of data items continuously generated over time. Often, they must be processed in real-time and scale performance, which requires the use of distributed parallel computing resources. In C/C++, the current state-of-the-art for distributed architectures and High-Performance Computing is Message Passing Interface (MPI). However, exploiting stream parallelism using MPI is complex and error-prone because it exposes many low-level details to the programmer. In this work, we introduce a new parallel programming abstraction for implementing distributed stream parallelism named DSParLib. Our abstraction of MPI simplifies parallel programming by providing a pattern-based and building block-oriented development to inter-connect, model, and parallelize data streams found in modern applications. Experiments conducted with five different stream processing applications and the representative PARSEC Ferret benchmark revealed that DSParLib is efficient and flexible. Also, DSParLib achieved similar or better performance, required less coding, and provided simpler abstractions to express parallelism with respect to handwritten MPI programs.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{HOFFMANN:Jsuper:2022,

title = {OpenMP as runtime for providing high-level stream parallelism on multi-cores},

author = {Renato Barreto Hoffmann and Júnior Löff and Dalvan Griebler and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1007/s11227-021-04182-9},

doi = {10.1007/s11227-021-04182-9},

year  = {2022},

date = {2022-01-01},

journal = {The Journal of Supercomputing},

volume = {78},

number = {1},

pages = {7655-7676},

publisher = {Springer},

address = {New York, United States},

abstract = {OpenMP is an industry and academic standard for parallel programming. However, using it for developing parallel stream processing applications is complex and challenging. OpenMP lacks key programming mechanisms and abstractions for this particular domain. To tackle this problem, we used a high-level parallel programming framework (named SPar) for automatically generating parallel OpenMP code. We achieved this by leveraging SPar’s language and its domain-specific code annotations for simplifying the complexity and verbosity added by OpenMP in this application domain. Consequently, we implemented a new compiler algorithm in SPar for automatically generating parallel code targeting the OpenMP runtime using source-to-source code transformations. The experiments in four different stream processing applications demonstrated that the execution time of SPar was improved up to 25.42% when using the OpenMP runtime. Additionally, our abstraction over OpenMP introduced at most 1.72% execution time overhead when compared to handwritten parallel codes. Furthermore, SPar significantly reduces the total source lines of code required to express parallelism with respect to plain OpenMP parallel codes.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{LOFF:SBLP:21,

title = {High-Level Stream and Data Parallelism in C++ for Multi-Cores},

author = {Júnior Löff and Renato Barreto Hoffmann and Dalvan Griebler and Luiz G. Fernandes},

url = {https://doi.org/10.1145/3475061.3475078},

doi = {10.1145/3475061.3475078},

year  = {2021},

date = {2021-10-01},

booktitle = {XXV Brazilian Symposium on Programming Languages (SBLP)},

pages = {41-48},

publisher = {ACM},

address = {Joinville, Brazil},

series = {SBLP'21},

abstract = {Stream processing applications have seen an increasing demand with the increased availability of sensors, IoT devices, and user data. Modern systems can generate millions of data items per day that require to be processed timely. To deal with this demand, application programmers must consider parallelism to exploit the maximum performance of the underlying hardware resources. However, parallel programming is often difficult and error-prone, because programmers must deal with low-level system and architecture details. In this work, we introduce a new strategy for automatic data-parallel code generation in C++ targeting multi-core architectures. This strategy was integrated with an annotation-based parallel programming abstraction named SPar. We have increased SPar’s expressiveness for supporting stream and data parallelism, and their arbitrary composition. Therefore, we added two new attributes to its language and improved the compiler parallel code generation. We conducted a set of experiments on different stream and data-parallel applications to assess the efficiency of our solution. The results showed that the new SPar version obtained similar performance with respect to handwritten parallelizations. Moreover, the new SPar version is able to achieve up to 74.9x better performance with respect to the original ones due to this work.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ANDRADE:SEAA:21,

title = {Assessing Coding Metrics for Parallel Programming of Stream Processing Programs on Multi-cores},

author = {Gabriella Andrade and Dalvan Griebler and Rodrigo Santos and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/SEAA53835.2021.00044},

doi = {10.1109/SEAA53835.2021.00044},

year  = {2021},

date = {2021-09-01},

booktitle = {47th Euromicro Conference on Software Engineering and Advanced Applications (SEAA 2021)},

pages = {291-295},

publisher = {IEEE},

address = {Pavia, Italy},

series = {SEAA'21},

abstract = {From the popularization of multi-core architectures, several parallel APIs have emerged, helping to abstract the programming complexity and increasing productivity in application development. Unfortunately, only a few research efforts in this direction managed to show the usability pay-back of the programming abstraction created, because it is not easy and poses many challenges for conducting empirical software engineering. We believe that coding metrics commonly used in software engineering code measurements can give useful indicators on the programming effort of parallel applications and APIs. These metrics were designed for general purposes without considering the evaluation of applications from a specific domain. In this study, we aim to evaluate the feasibility of seven coding metrics to be used in the parallel programming domain. To do so, five stream processing applications implemented with different parallel APIs for multi-cores were considered. Our experiments have shown COCOMO II is a suitable model for evaluating the productivity of different parallel APIs targeting multi-cores on stream processing applications while other metrics are restricted to the code size.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{LOFF:FGCS:21,

title = {The NAS parallel benchmarks for evaluating C++ parallel programming frameworks on shared-memory architectures},

author = {Júnior Löff and Dalvan Griebler and Gabriele Mencagli and Gabriell Araujo and Massimo Torquati and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1016/j.future.2021.07.021},

doi = {10.1016/j.future.2021.07.021},

year  = {2021},

date = {2021-07-01},

journal = {Future Generation Computer Systems},

volume = {125},

pages = {743-757},

publisher = {Elsevier},

abstract = {The NAS Parallel Benchmarks (NPB), originally implemented mostly in Fortran, is a consolidated suite containing several benchmarks extracted from Computational Fluid Dynamics (CFD) models. The benchmark suite has important characteristics such as intensive memory communications, complex data dependencies, different memory access patterns, and hardware components/sub-systems overload. Parallel programming APIs, libraries, and frameworks that are written in C++ as well as new optimizations and parallel processing techniques can benefit if NPB is made fully available in this programming language. In this paper we present NPB-CPP, a fully C++ translated version of NPB consisting of all the NPB kernels and pseudo-applications developed using OpenMP, Intel TBB, and FastFlow parallel frameworks for multicores. The design of NPB-CPP leverages the Structured Parallel Programming methodology (essentially based on parallel design patterns). We show the structure of each benchmark application in terms of composition of few patterns (notably Map and MapReduce constructs) provided by the selected C++ frameworks. The experimental evaluation shows the accuracy of NPB-CPP with respect to the original NPB source code. Furthermore, we carefully evaluate the parallel performance on three multi-core systems (Intel, IBM Power and AMD) with different C++ compilers (gcc, icc and clang) by discussing the performance differences in order to give to the researchers useful insights to choose the best parallel programming framework for a given type of problem.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{PIEPER:COLA:21,

title = {High-level and Efficient Structured Stream Parallelism for Rust on Multi-cores},

author = {Ricardo Pieper and Júnior Löff and Renato Berreto Hoffmann and Dalvan Griebler and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1016/j.cola.2021.101054},

doi = {10.1016/j.cola.2021.101054},

year  = {2021},

date = {2021-07-01},

journal = {Journal of Computer Languages},

volume = {65},

pages = {101054},

publisher = {Elsevier},

abstract = {This work aims at contributing with a structured parallel programming abstraction for Rust in order to provide ready-to-use parallel patterns that abstract low-level and architecture-dependent details from application programmers. We focus on stream processing applications running on shared-memory multi-core architectures (i.e, video processing, compression, and others). Therefore, we provide a new high-level and efficient parallel programming abstraction for expressing stream parallelism, named Rust-SSP. We also created a new stream benchmark suite for Rust that represents real-world scenarios and has different application characteristics and workloads. Our benchmark suite is an initiative to assess existing parallelism abstraction for this domain, as parallel implementations using these abstractions were provided. The results revealed that Rust-SSP achieved up to 41.1% better performance than other solutions. In terms of programmability, the results revealed that Rust-SSP requires the smallest number of extra lines of code to enable stream parallelism..},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{GOMES:CEE:21,

title = {Simplifying IoT data stream enrichment and analytics in the edge},

author = {Márcio Miguel Gomes and Rodrigo Rosa Righi and Cristiano André Costa and Dalvan Griebler},

url = {https://doi.org/10.1016/j.compeleceng.2021.107110},

doi = {10.1016/j.compeleceng.2021.107110},

year  = {2021},

date = {2021-06-01},

journal = {Computers & Electrical Engineering},

volume = {92},

pages = {107110},

publisher = {Elsevier},

abstract = {Edge devices are usually limited in resources. They often send data to the cloud, where techniques such as filtering, aggregation, classification, pattern detection, and prediction are performed. This process results in critical issues such as data loss, high response time, and overhead. On the other hand, processing data in the edge is not a simple task due to devices’ heterogeneity, resource limitations, a variety of programming languages and standards. In this context, this work proposes STEAM, a framework for developing data stream processing applications in the edge targeting hardware-limited devices. As the main contribution, STEAM enables the development of applications for different platforms, with standardized functions and class structures that use consolidated IoT data formats and communication protocols. Moreover, the experiments revealed the viability of stream processing in the edge resulting in the reduction of response time without compromising the quality of results.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{VOGEL:Computing:23,

title = {Online and Transparent Self-adaptation of Stream Parallel Patterns},

author = {Adriano Vogel and Gabriele Mencagli and Dalvan Griebler and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1007/s00607-021-00998-8},

doi = {10.1007/s00607-021-00998-8},

year  = {2021},

date = {2021-05-01},

journal = {Computing},

volume = {105},

number = {5},

pages = {1039-1057},

publisher = {Springer},

abstract = {Several real-world parallel applications are becoming more dynamic and long-running, demanding online (at run-time) adaptations. Stream processing is a representative scenario that computes data items arriving in real-time and where parallel executions are necessary. However, it is challenging for humans to monitor and manually self-optimize complex and long-running parallel executions continuously. Moreover, although high-level and structured parallel programming aims to facilitate parallelism, several issues still need to be addressed for improving the existing abstractions. In this paper, we extend self-adaptiveness for supporting autonomous and online changes of the parallel pattern compositions. Online self-adaptation is achieved with an online profiler that characterizes the applications, which is combined with a new self-adaptive strategy and a model for smooth transitions on reconfigurations. The solution provides a new abstraction layer that enables application programmers to define non-functional requirements instead of hand-tuning complex configurations. Hence, we contribute with additional abstractions and flexible self-adaptation for responsiveness at run-time. The proposed solution is evaluated with applications having different processing characteristics, workloads, and configurations. The results show that it is possible to provide additional abstractions, flexibility, and responsiveness while achieving performance comparable to the best static configuration executions.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{VOGEL:PDP:21,

title = {Towards On-the-fly Self-Adaptation of Stream Parallel Patterns},

author = {Adriano Vogel and Gabriele Mencagli and Dalvan Griebler and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/PDP52278.2021.00022},

doi = {10.1109/PDP52278.2021.00022},

year  = {2021},

date = {2021-03-01},

booktitle = {29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {889-93},

publisher = {IEEE},

address = {Valladolid, Spain},

series = {PDP'21},

abstract = {Stream processing applications compute streams of data and provide insightful results in a timely manner, where parallel computing is necessary for accelerating the application executions. Considering that these applications are becoming increasingly dynamic and long-running, a potential solution is to apply dynamic runtime changes. However, it is challenging for humans to continuously monitor and manually self-optimize the executions. In this paper, we propose self-adaptiveness of the parallel patterns used, enabling flexible on-the-fly adaptations. The proposed solution is evaluated with an existing programming framework and running experiments with a synthetic and a real-world application. The results show that the proposed solution is able to dynamically self-adapt to the most suitable parallel pattern configuration and achieve performance competitive with the best static cases. The feasibility of the proposed solution encourages future optimizations and other applicabilities.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GARCIA:PDP:21,

title = {Introducing a Stream Processing Framework for Assessing Parallel Programming Interfaces},

author = {Adriano Marques Garcia and Dalvan Griebler and Claudio Schepke and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/PDP52278.2021.00021},

doi = {10.1109/PDP52278.2021.00021},

year  = {2021},

date = {2021-03-01},

booktitle = {29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {84-88},

publisher = {IEEE},

address = {Valladolid, Spain},

series = {PDP'21},

abstract = {Stream Processing applications are spread across different sectors of industry and people's daily lives. The increasing data we produce, such as audio, video, image, and text are demanding quickly and efficiently computation. It can be done through Stream Parallelism, which is still a challenging task and most reserved for experts. We introduce a Stream Processing framework for assessing Parallel Programming Interfaces (PPIs). Our framework targets multi-core architectures and C++ stream processing applications, providing an API that abstracts the details of the stream operators of these applications. Therefore, users can easily identify all the basic operators and implement parallelism through different PPIs. In this paper, we present the proposed framework, implement three applications using its API, and show how it works, by using it to parallelize and evaluate the applications with the PPIs Intel TBB, FastFlow, and SPar. The performance results were consistent with the literature.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{VOGEL:Survey:CCPE:2021,

title = {Self-adaptation on Parallel Stream Processing: A Systematic Review},

author = {Adriano Vogel and Dalvan Griebler and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1002/cpe.6759},

doi = {10.1002/cpe.6759},

year  = {2021},

date = {2021-03-01},

journal = {Concurrency and Computation: Practice and Experience},

volume = {34},

number = {6},

pages = {e6759},

publisher = {Wiley},

abstract = {A recurrent challenge in real-world applications is autonomous management of the executions at run-time. In this vein, stream processing is a class of applications that compute data flowing in the form of streams (e.g., video feeds, images, and data analytics), where parallel computing can help accelerate the executions. On the one hand, stream processing applications are becoming more complex, dynamic, and long-running. On the other hand, it is unfeasible for humans to monitor and manually change the executions continuously. Hence, self-adaptation can reduce costs and human efforts by providing a higher-level abstraction with an autonomic/seamless management of executions. In this work, we aim at providing a literature review regarding self-adaptation applied to the parallel stream processing domain. We present a comprehensive revision using a systematic literature review method. Moreover, we propose a taxonomy to categorize and classify the existing self-adaptive approaches. Finally, applying the taxonomy made it possible to characterize the state-of-the-art, identify trends, and discuss open research challenges and future opportunities.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{VOGEL:SPE:21,

title = {Providing High‐Level Self‐Adaptive Abstractions for Stream Parallelism on Multicores},

author = {Adriano Vogel and Dalvan Griebler and Luiz G. Fernandes},

url = {https://doi.org/10.1002/spe.2948},

doi = {10.1002/spe.2948},

year  = {2021},

date = {2021-01-01},

journal = {Software: Practice and Experience},

volume = {51},

number = {6},

pages = {1194-1217},

publisher = {Wiley},

abstract = {Stream processing applications are common computing workloads that demand parallelism to increase their performance. As in the past, parallel programming remains a difficult task for application programmers. The complexity increases when application programmers must set non-intuitive parallelism parameters, i.e. the degree of parallelism. The main problem is that state-of-the-art libraries use a static degree of parallelism and are not sufficiently abstracted for developing stream processing applications. In this paper, we propose a self-adaptive regulation of the degree of parallelism to provide higher-level abstractions. Flexibility is provided to programmers with two new self-adaptive strategies, one is for performance experts, and the other abstracts the need to set a performance goal. We evaluated our solution using compiler transformation rules to generate parallel code with the SPar domain-specific language. The experimental results with real-world applications highlighted higher abstraction levels without significant performance degradation in comparison to static executions. The strategy for performance experts achieved slightly higher performance than the one that works without user-defined performance goals.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{BORDIN:IEEEAccess:20,

title = {DSPBench: a Suite of Benchmark Applications for Distributed Data Stream Processing Systems},

author = {Maycon Viana Bordin and Dalvan Griebler and Gabriele Mencagli and Claudio F. R. Geyer and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/ACCESS.2020.3043948},

doi = {10.1109/ACCESS.2020.3043948},

year  = {2020},

date = {2020-12-01},

journal = {IEEE Access},

volume = {8},

number = {na},

pages = {222900-222917},

publisher = {IEEE},

abstract = {Systems enabling the continuous processing of large data streams have recently attracted the attention of the scientific community and industrial stakeholders. Data Stream Processing Systems (DSPSs) are complex and powerful frameworks able to ease the development of streaming applications in distributed computing environments like clusters and clouds. Several systems of this kind have been released and currently maintained as open source projects, like Apache Storm and Spark Streaming. Some benchmark applications have often been used by the scientific community to test and evaluate new techniques to improve the performance and usability of DSPSs. However, the existing benchmark suites lack of representative workloads coming from the wide set of application domains that can leverage the benefits offered by the stream processing paradigm in terms of near real-time performance. The goal of this paper is to present a new benchmark suite composed of 15 applications coming from areas like Finance, Telecommunications, Sensor Networks, Social Networks and others. This paper describes in detail the nature of these applications, their full workload characterization in terms of selectivity, processing cost, input size and overall memory occupation. In addition, it exemplifies the usefulness of our benchmark suite to compare real DSPSs by selecting Apache Storm and Spark Streaming for this analysis.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{HOFFMANN:SBLP:20,

title = {Stream Parallelism Annotations for Multi-Core Frameworks},

author = {Renato B. Hoffmann and Dalvan Griebler and Marco Danelutto and Luiz G. Fernandes},

url = {https://doi.org/10.1145/3427081.3427088},

doi = {10.1145/3427081.3427088},

year  = {2020},

date = {2020-10-01},

booktitle = {XXIV Brazilian Symposium on Programming Languages (SBLP)},

pages = {48-55},

publisher = {ACM},

address = {Natal, Brazil},

series = {SBLP'20},

abstract = {Data generation, collection, and processing is an important workload of modern computer architectures. Stream or high-intensity data flow applications are commonly employed in extracting and interpreting the information contained in this data. Due to the computational complexity of these applications, high-performance ought to be achieved using parallel computing. Indeed, the efficient exploitation of available parallel resources from the architecture remains a challenging task for the programmers. Techniques and methodologies are required to help shift the efforts from the complexity of parallelism exploitation to specific algorithmic solutions. To tackle this problem, we propose a methodology that provides the developer with a suitable abstraction layer between a clean and effective parallel programming interface targeting different multi-core parallel programming frameworks. We used standard C++ code annotations that may be inserted in the source code by the programmer. Then, a compiler parses C++ code with the annotations and generates calls to the desired parallel runtime API. Our experiments demonstrate the feasibility of our methodology and the performance of the abstraction layer, where the difference is negligible in four applications with respect to the state-of-the-art C++ parallel programming frameworks. Additionally, our methodology allows improving the application performance since the developers can choose the runtime that best performs in their system.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GARCIA:ICCSA:20,

title = {The Impact of CPU Frequency Scaling on Power Consumption of Computing Infrastructures},

author = {Adriano M. Garcia and Matheus Serpa and Dalvan Griebler and Claudio Schepke and Luiz G. L. Fernandes and Philippe O. A. Navaux},

url = {https://doi.org/10.1007/978-3-030-58817-5_12},

doi = {10.1007/978-3-030-58817-5_12},

year  = {2020},

date = {2020-07-01},

booktitle = {International Conference on Computational Science and its Applications (ICCSA)},

volume = {12254},

pages = {142-157},

publisher = {Springer},

address = {Cagliari, Italy},

series = {ICCSA'20},

abstract = {Since the demand for computing power increases, new architectures emerged to obtain better performance. Reducing the power and energy consumption of these architectures is one of the main challenges to achieving high-performance computing. Current research trends aim at developing new software and hardware techniques to achieve the best performance and energy trade-offs. In this work, we investigate the impact of different CPU frequency scaling techniques such as ondemand, performance, and powersave on the power and energy consumption of multi-core based computer infrastructure. We apply these techniques in PAMPAR, a parallel benchmark suite implemented in PThreads, OpenMP, MPI-1, and MPI-2 (spawn). We measure the energy and execution time of 10 benchmarks, varying the number of threads. Our results show that although powersave consumes up to 43.1% less power than performance and ondemand governors, it consumes the triple of energy due to the high execution time. Our experiments also show that the performance governor consumes up to 9.8% more energy than ondemand for CPU-bound benchmarks. Finally, our results show that PThreads has the lowest power consumption, consuming less than the sequential version for memory-bound benchmarks. Regarding performance, the performance governor achieved 3% of performance over the ondemand.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{larcc:ieee802.3ad_containers:ICCSA:20,

title = {Performance Impact of IEEE 802.3ad in Container-based Clouds for HPC Applications},

author = {Anderson M. Maliszewski and Eduardo Roloff and Dalvan Griebler and Luciano P. Gaspary and Philippe O. A. Navaux},

url = {https://doi.org/10.1007/978-3-030-58817-5_13},

doi = {10.1007/978-3-030-58817-5_13},

year  = {2020},

date = {2020-07-01},

booktitle = {International Conference on Computational Science and its Applications (ICCSA)},

pages = {158-167},

publisher = {Springer},

address = {Cagliari, Italy},

series = {ICCSA'20},

abstract = {Historically, large computational clusters have supported hardware requirements for executing High-Performance Computing (HPC) applications. This model has become out of date due to the high costs of maintaining and updating these infrastructures. Currently, computing resources are delivered as a service because of the cloud computing paradigm. In this way, we witnessed consistent efforts to migrate HPC applications to the cloud. However, if on the one hand cloud computing offers an attractive environment for HPC, benefiting from the pay-per-use model and on-demand resource allocation, on the other, there are still significant performance challenges to be addressed, such as the known network bottleneck. In this article, we evaluate the use of a Network Interface Cards (NIC) aggregation approach, using the IEEE 802.3ad standard to improve the performance of representative HPC applications executed in LXD container based-cloud. We assessed the aggregation impact using two and four NICs with three distinct transmission hash policies. Our results demonstrated that if the correct hash policy is selected, the NIC aggregation can significantly improve the performance of network-intensive HPC applications by up to 40%.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{larcc:network_azure_cost_perf:ISCC:20,

title = {Performance and Cost-Aware in Clouds: A Network Interconnection Assessment},

author = {Anderson M. Maliszewski and Eduardo Roloff and Emmanuell D. Carreño and Dalvan Griebler and Luciano P. Gaspary and Philippe O. A. Navaux},

url = {https://doi.org/10.1109/ISCC50000.2020.9219554},

doi = {10.1109/ISCC50000.2020.9219554},

year  = {2020},

date = {2020-07-01},

booktitle = {IEEE Symposium on Computers and Communications (ISCC)},

pages = {1-6},

publisher = {IEEE},

address = {Rennes, France},

series = {ISCC'20},

abstract = {The availability of computing resources has significantly changed due to the growing adoption of the cloud computing paradigm. Aiming at potential advantages such as cost savings through the pay-per-use method and resource allocation in a scalable/elastic way, we witnessed consistent efforts to execute high-performance computing (HPC) applications in the cloud. Performance in this environment depends heavily upon two main system components: processing power and network interconnection. If, on the one hand, allocating more powerful hardware theoretically boosts performance, on the other hand, it increases the allocation cost. In this paper, we evaluated how the network interconnection impacts on performance and cost efficiency. Our experiments were carried out using NAS Parallel Benchmarks and Alya HPC application on Microsoft Azure public cloud provider, with three different cloud instances/network interconnections. The results revealed that through the use of the accelerated networking approach, which allows the instance to have a high-performance interconnect without additional charges, the performance of HPC applications can be significantly improved with a better cost efficiency.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{STEIN:CCPE:20,

title = {Latency‐aware adaptive micro‐batching techniques for streamed data compression on graphics processing units},

author = {Charles M. Stein and Dinei A. Rockenbach and Dalvan Griebler and Massimo Torquati and Gabriele Mencagli and Marco Danelutto and Luiz G. Fernandes},

url = {https://doi.org/10.1002/cpe.5786},

doi = {10.1002/cpe.5786},

year  = {2020},

date = {2020-05-01},

journal = {Concurrency and Computation: Practice and Experience},

volume = {na},

number = {na},

pages = {e5786},

publisher = {Wiley Online Library},

abstract = {Stream processing is a parallel paradigm used in many application domains. With the advance of graphics processing units (GPUs), their usage in stream processing applications has increased as well. The efficient utilization of GPU accelerators in streaming scenarios requires to batch input elements in microbatches, whose computation is offloaded on the GPU leveraging data parallelism within the same batch of data. Since data elements are continuously received based on the input speed, the bigger the microbatch size the higher the latency to completely buffer it and to start the processing on the device. Unfortunately, stream processing applications often have strict latency requirements that need to find the best size of the microbatches and to adapt it dynamically based on the workload conditions as well as according to the characteristics of the underlying device and network. In this work, we aim at implementing latency‐aware adaptive microbatching techniques and algorithms for streaming compression applications targeting GPUs. The evaluation is conducted using the Lempel‐Ziv‐Storer‐Szymanski compression application considering different input workloads. As a general result of our work, we noticed that algorithms with elastic adaptation factors respond better for stable workloads, while algorithms with narrower targets respond better for highly unbalanced workloads.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{ARAUJO:PDP:20,

title = {Efficient NAS Parallel Benchmark Kernels with CUDA},

author = {Gabriell Alves Araujo and Dalvan Griebler and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/PDP50117.2020.00009},

doi = {10.1109/PDP50117.2020.00009},

year  = {2020},

date = {2020-03-01},

booktitle = {28th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {9-16},

publisher = {IEEE},

address = {Västerås, Sweden, Sweden},

series = {PDP'20},

abstract = {NAS Parallel Benchmarks (NPB) are one of the standard benchmark suites used to evaluate parallel hardware and software. There are many research efforts trying to provide different parallel versions apart from the original OpenMP and MPI. Concerning GPU accelerators, there are only the OpenCL and OpenACC available as consolidated versions. Our goal is to provide an efficient parallel implementation of the five NPB kernels with CUDA. Our contribution covers different aspects. First, best parallel programming practices were followed to implement NPB kernels using CUDA. Second, the support of larger workloads (class B and C) allow to stress and investigate the memory of robust GPUs. Third, we show that it is possible to make NPB efficient and suitable for GPUs although the benchmarks were designed for CPUs in the past. We succeed in achieving double performance with respect to the state-of-the-art in some cases as well as implementing efficient memory usage. Fourth, we discuss new experiments comparing performance and memory usage against OpenACC and OpenCL state-of-the-art versions using a relative new GPU architecture. The experimental results also revealed that our version is the best one for all the NPB kernels compared to OpenACC and OpenCL. The greatest differences were observed for the FT and EP kernels.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{VOGEL:CCIS:20,

title = {Parallel Stream Processing with MPI for Video Analytics and Data Visualization},

author = {Adriano Vogel and Cassiano Rista and Gabriel Justo and Endrius Ewald and Dalvan Griebler and Gabriele Mencagli and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1007/978-3-030-41050-6_7},

doi = {10.1007/978-3-030-41050-6_7},

year  = {2020},

date = {2020-02-01},

booktitle = {High Performance Computing Systems},

volume = {1171},

pages = {102-116},

publisher = {Springer},

address = {Cham},

series = {Communications in Computer and Information Science (CCIS)},

abstract = {The amount of data generated is increasing exponentially. However, processing data and producing fast results is a technological challenge. Parallel stream processing can be implemented for handling high frequency and big data flows. The MPI parallel programming model offers low-level and flexible mechanisms for dealing with distributed architectures such as clusters. This paper aims to use it to accelerate video analytics and data visualization applications so that insight can be obtained as soon as the data arrives. Experiments were conducted with a Domain-Specific Language for Geospatial Data Visualization and a Person Recognizer video application. We applied the same stream parallelism strategy and two task distribution strategies. The dynamic task distribution achieved better performance than the static distribution in the HPC cluster. The data visualization achieved lower throughput with respect to the video analytics due to the I/O intensive operations. Also, the MPI programming model shows promising performance outcomes for stream processing applications.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{PIEPER:SBLP:19,

title = {Structured Stream Parallelism for Rust},

author = {Ricardo Pieper and Dalvan Griebler and Luiz G. Fernandes},

url = {https://doi.org/10.1145/3355378.3355384},

doi = {10.1145/3355378.3355384},

year  = {2019},

date = {2019-10-01},

booktitle = {XXIII Brazilian Symposium on Programming Languages (SBLP)},

pages = {54-61},

publisher = {ACM},

address = {Salvador, Brazil},

series = {SBLP'19},

abstract = {Structured parallel programming has been studied and applied in several programming languages. This approach has proven to be suitable for abstracting low-level and architecture-dependent parallelism implementations. Our goal is to provide a structured and high-level library for the Rust language, targeting parallel stream processing applications for multi-core servers. Rust is an emerging programming language that has been developed by Mozilla Research group, focusing on performance, memory safety, and thread-safety. However, it lacks parallel programming abstractions, especially for stream processing applications. This paper contributes to a new API based on the structured parallel programming approach to simplify parallel software developing. Our experiments highlight that our solution provides higher-level parallel programming abstractions for stream processing applications in Rust. We also show that the throughput and speedup are comparable to the state-of-the-art for certain workloads.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{MENCAGLI:IEEEAccess:19,

title = {Raising the Parallel Abstraction Level for Streaming Analytics Applications},

author = {Gabriele Mencagli and Massimo Torquati and Dalvan Griebler and Marco Danelutto and Luiz Gustavo L. Fernandes},

url = {https://doi.org/10.1109/ACCESS.2019.2941183},

doi = {10.1109/ACCESS.2019.2941183},

year  = {2019},

date = {2019-09-01},

journal = {IEEE Access},

volume = {7},

pages = {131944 - 131961},

publisher = {IEEE},

abstract = {In the stream processing domain, applications are represented by graphs of operators arbitrarily connected and filled with their business logic code. The APIs of existing Stream Processing Systems (SPSs) ease the development of transformations that recur in the streaming practice (e.g., filtering, aggregation and joins). In contrast, their parallelism abstractions are quite limited since they provide support to stateless operators only, or when the state is organized in a set of key-value pairs. This paper presents how the parallel patterns methodology can be revisited for sliding-window streaming analytics. Our vision fosters a design process of the application as composition and nesting of ready-to-use patterns provided through a C++17 fluent interface. Our prototype implements the run-time system of the patterns in the FastFlow parallel library expressing thread-based parallelism. The experimental analysis shows interesting outcomes. First, our pattern-based approach allows easy prototyping of different versions of the application, and the programmer can leverage nesting of patterns to increase performance (up to 37% in one of the two considered test-bed cases). Second, our FastFlow implementation outperforms (three times faster) the handmade porting of our patterns in popular JVM-based SPSs. Finally, in the concluding part of this paper, we explore the use of a task-based run-time system, by deriving interesting insights into how to make our patterns library suitable for multi backends.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{FISHER:Elasticity-Hospital:SENSORS:19,

title = {Towards Evaluating Proactive and Reactive Approaches on Reorganizing Human Resources in IoT-Based Smart Hospitals},

author = {Gabriel Souto Fischer and Rodrigo Rosa Righi and Cristiano André Costa and Guilherme Galante and Dalvan Griebler},

url = {https://doi.org/10.3390/s19173800},

doi = {10.3390/s19173800},

year  = {2019},

date = {2019-09-01},

journal = {Sensors},

volume = {19},

number = {17},

pages = {3800},

publisher = {MDPI},

abstract = {Hospitals play an important role on ensuring a proper treatment of human health. One of the problems to be faced is the increasingly overcrowded patients care queues, who end up waiting for longer times without proper treatment to their health problems. The allocation of health professionals in hospital environments is not able to adapt to the demands of patients. There are times when underused rooms have idle professionals, and overused rooms have fewer professionals than necessary. Previous works have not solved this problem since they focus on understanding the evolution of doctor supply and patient demand, as to better adjust one to the other. However, they have not proposed concrete solutions for that regarding techniques for better allocating available human resources. Moreover, elasticity is one of the most important features of cloud computing, referring to the ability to add or remove resources according to the needs of the application or service. Based on this background, we introduce Elastic allocation of human resources in Healthcare environments (ElHealth) an IoT-focused model able to monitor patient usage of hospital rooms and adapt these rooms for patients demand. Using reactive and proactive elasticity approaches, ElHealth identifies when a room will have a demand that exceeds the capacity of care, and proposes actions to move human resources to adapt to patient demand. Our main contribution is the definition of Human Resources IoT-based Elasticity (i.e., an extension of the concept of resource elasticity in Cloud Computing to manage the use of human resources in a healthcare environment, where health professionals are allocated and deallocated according to patient demand). Another contribution is a cost–benefit analysis for the use of reactive and predictive strategies on human resources reorganization. ElHealth was simulated on a hospital environment using data from a Brazilian polyclinic, and obtained promising results, decreasing the waiting time by up to 96.4% and 96.73% in reactive and proactive approaches, respectively.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{ROCKENBACH:PARCO:19,

title = {High-Level Stream Parallelism Abstractions with SPar Targeting GPUs},

author = {Dinei A. Rockenbach and Dalvan Griebler and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.3233/APC200083},

doi = {10.3233/APC200083},

year  = {2019},

date = {2019-09-01},

booktitle = {Parallel Computing is Everywhere, Proceedings of the International Conference on Parallel Computing (ParCo)},

volume = {36},

pages = {543-552},

publisher = {IOS Press},

address = {Prague, Czech Republic},

series = {ParCo'19},

abstract = {The combined exploitation of stream and data parallelism is demonstrating encouraging performance results in the literature for heterogeneous architectures, which are present on every computer systems today. However, provide parallel software efficiently targeting those architectures requires significant programming effort and expertise. The SPar domain-specific language already represents a solution to this problem providing proven high-level programming abstractions for multi-core architectures. In this paper, we enrich the SPar language adding support for GPUs. New transformation rules are designed for generating parallel code using stream and data parallel patterns. Our experiments revealed that these transformations rules are able to improve performance while the high-level programming abstractions are maintained.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{VOGEL:PARCO:19,

title = {Seamless Parallelism Management for Multi-core Stream Processing},

author = {Adriano Vogel and Dalvan Griebler and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.3233/APC200082},

doi = {10.3233/APC200082},

year  = {2019},

date = {2019-09-01},

booktitle = {Advances in Parallel Computing, Proceedings of the International Conference on Parallel Computing (ParCo)},

volume = {36},

pages = {533-542},

publisher = {IOS Press},

address = {Prague, Czech Republic},

series = {ParCo'19},

abstract = {Video streaming applications have critical performance requirements for dealing with fluctuating workloads and providing results in real-time. As a consequence, the majority of these applications demand parallelism for delivering quality of service to users. Although high-level and structured parallel programming aims at facilitating parallelism exploitation, there are still several issues to be addressed for increasing/improving existing parallel programming abstractions. In this paper, we aim at employing self-adaptivity for stream processing in order to seamlessly manage the application parallelism configurations at run-time, where a new strategy alleviates from application programmers the need to set time-consuming and error-prone parallelism parameters. The new strategy was implemented and validated on SPar. The results have shown that the proposed solution increases the level of abstraction and achieved a competitive performance.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{VOGEL:adaptive-overhead:AutoDaSP:19,

title = {Minimizing Self-Adaptation Overhead in Parallel Stream Processing for Multi-Cores},

author = {Adriano Vogel and Dalvan Griebler and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1007/978-3-030-48340-1_3},

doi = {10.1007/978-3-030-48340-1_3},

year  = {2019},

date = {2019-08-01},

booktitle = {Euro-Par 2019: Parallel Processing Workshops},

volume = {11997},

pages = {12},

publisher = {Springer},

address = {Göttingen, Germany},

series = {Lecture Notes in Computer Science},

abstract = {Stream processing paradigm is present in several applications that apply computations over continuous data flowing in the form of streams (e.g., video feeds, image, and data analytics). Employing self-adaptivity to stream processing applications can provide higher-level programming abstractions and autonomic resource management. However, there are cases where the performance is suboptimal. In this paper, the goal is to optimize parallelism adaptations in terms of stability and accuracy, which can improve the performance of parallel stream processing applications. Therefore, we present a new optimized self-adaptive strategy that is experimentally evaluated. The proposed solution provided high-level programming abstractions, reduced the adaptation overhead, and achieved a competitive performance with the best static executions.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{larcc:communication_overhead_lxd:ISCC:19,

title = {Minimizing Communication Overheads in Container-based Clouds for HPC Applications},

author = {Anderson M. Maliszewski and Adriano Vogel and Dalvan Griebler and Eduardo Roloff and Luz G. Fernandes and Philippe O. A. Navaux},

url = {https://doi.org/10.1109/ISCC47284.2019.8969716},

doi = {10.1109/ISCC47284.2019.8969716},

year  = {2019},

date = {2019-07-01},

booktitle = {IEEE Symposium on Computers and Communications (ISCC)},

pages = {1-6},

publisher = {IEEE},

address = {Barcelona, Spain},

series = {ISCC'19},

abstract = {Although the industry has embraced the cloud computing model, there are still significant challenges to be addressed concerning the quality of cloud services. Network-intensive applications may not scale in the cloud due to the sharing of the network infrastructure. In the literature, performance evaluation studies are showing that the network tends to limit the scalability and performance of HPC applications. Therefore, we proposed the aggregation of Network Interface Cards (NICs) in a ready-to-use integration with the OpenNebula cloud manager using Linux containers. We perform a set of experiments using a network microbenchmark to get specific network performance metrics and NAS parallel benchmarks to analyze the performance impact on HPC applications. Our results highlight that the implementation of NIC aggregation improves network performance in terms of throughput and latency. Moreover, HPC applications have different patterns of behavior when using our approach, which depends on communication and the amount of data transferring. While network-intensive applications increased the performance up to 38%, other applications with aggregated NICs maintained the same performance or presented slightly worse performance.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{GRIEBLER:JS:19,

title = {Simplifying and implementing service level objectives for stream parallelism},

author = {Dalvan Griebler and Adriano Vogel and Daniele De Sensi and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1007/s11227-019-02914-6},

doi = {10.1007/s11227-019-02914-6},

issn = {0920-8542},

year  = {2019},

date = {2019-06-01},

journal = {Journal of Supercomputing},

volume = {76},

pages = {4603-4628},

publisher = {Springer},

abstract = {An increasing attention has been given to provide service level objectives (SLOs) in stream processing applications due to the performance and energy requirements, and because of the need to impose limits in terms of resource usage while improving the system utilization. Since the current and next-generation computing systems are intrinsically offering parallel architectures, the software has to naturally exploit the architecture parallelism. Implement and meet SLOs on existing applications is not a trivial task for application programmers, since the software development process, besides the parallelism exploitation, requires the implementation of autonomic algorithms or strategies. This is a system-oriented programming approach and requires the management of multiple knobs and sensors (e.g., the number of threads to use, the clock frequency of the cores, etc.) so that the system can self-adapt at runtime. In this work, we introduce a new and simpler way to define SLO in the application’s source code, by abstracting from the programmer all the details relative to self-adaptive system implementation. The application programmer specifies which parts of the code to parallelize and the related SLOs that should be enforced. To reach this goal, source-to-source code transformation rules are implemented in our compiler, which automatically generates self-adaptive strategies to enforce, at runtime, the user-expressed objectives. The experiments highlighted promising results with simpler, effective, and efficient SLO implementations for real-world applications.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}