Dalvan Griebler

@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},

urldate = {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}

}

@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},

urldate = {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}

}

@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: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}

}

@inproceedings{SCHEER:WSCAD:21,

title = {Performance Data Visualization of Linux Events on Multicores},

author = {Claudio Scheer and Renato Hoffmann and Dalvan Griebler and Isabel Manssour and Luiz Fernandes},

url = {https://doi.org/10.5753/wscad.2021.18516},

doi = {10.5753/wscad.2021.18516},

year  = {2021},

date = {2021-01-01},

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

pages = {108-119},

publisher = {SBC},

address = {Belo Horizonte},

abstract = {Profiling tools are essential to understand the behavior of parallel applications and assist in the optimization process. However, tools such as Perf generate a large amount of data. This way, they require significant storage space, which also complicates reasoning about this large volume of data. Therefore, we propose VisPerf: a tool-chain and an interactive visualization dashboard for Perf data. The VisPerf tool-chain profiles the application and pre-processes the data, reducing the storage space required by about 50 times. Moreover, we used the visualization dashboard to quickly understand the performance of different events and visualize specific threads and functions of a real-world application.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@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},

urldate = {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},

urldate = {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},

urldate = {2019-06-01},

journal = {The 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}

}

@inproceedings{ROCKENBACH:stream-multigpus:IPDPSW:19,

title = {Stream Processing on Multi-cores with GPUs: Parallel Programming Models' Challenges},

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

url = {https://doi.org/10.1109/IPDPSW.2019.00137},

doi = {10.1109/IPDPSW.2019.00137},

year  = {2019},

date = {2019-05-01},

booktitle = {International Parallel and Distributed Processing Symposium Workshops (IPDPSW)},

pages = {834-841},

publisher = {IEEE},

address = {Rio de Janeiro, Brazil},

series = {IPDPSW'19},

abstract = {The stream processing paradigm is used in several scientific and enterprise applications in order to continuously compute results out of data items coming from data sources such as sensors. The full exploitation of the potential parallelism offered by current heterogeneous multi-cores equipped with one or more GPUs is still a challenge in the context of stream processing applications. In this work, our main goal is to present the parallel programming challenges that the programmer has to face when exploiting CPUs and GPUs' parallelism at the same time using traditional programming models. We highlight the parallelization methodology in two use-cases (the Mandelbrot Streaming benchmark and the PARSEC's Dedup application) to demonstrate the issues and benefits of using heterogeneous parallel hardware. The experiments conducted demonstrate how a high-level parallel programming model targeting stream processing like the one offered by SPar can be used to reduce the programming effort still offering a good level of performance if compared with state-of-the-art programming models.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{STEIN:LZSS-multigpu:PDP:19,

title = {Stream Parallelism on the LZSS Data Compression Application for Multi-Cores with GPUs},

author = {Charles Michael Stein and Dalvan Griebler and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/EMPDP.2019.8671624},

doi = {10.1109/EMPDP.2019.8671624},

year  = {2019},

date = {2019-02-01},

booktitle = {27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {247-251},

publisher = {IEEE},

address = {Pavia, Italy},

series = {PDP'19},

abstract = {GPUs have been used to accelerate different data parallel applications. The challenge consists in using GPUs to accelerate stream processing applications. Our goal is to investigate and evaluate whether stream parallel applications may benefit from parallel execution on both CPU and GPU cores. In this paper, we introduce new parallel algorithms for the Lempel-Ziv-Storer-Szymanski (LZSS) data compression application. We implemented the algorithms targeting both CPUs and GPUs. GPUs have been used with CUDA and OpenCL to exploit inner algorithm data parallelism. Outer stream parallelism has been exploited using CPU cores through SPar. The parallel implementation of LZSS achieved 135 fold speedup using a multi-core CPU and two GPUs. We also observed speedups in applications where we were not expecting to get it using the same combine data-stream parallel exploitation techniques.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{MARON:parametric-parsec:PDP:19,

title = {Should PARSEC Benchmarks be More Parametric? A Case Study with Dedup},

author = {Carlos A. F. Maron and Adriano Vogel and Dalvan Griebler and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/EMPDP.2019.8671592},

doi = {10.1109/EMPDP.2019.8671592},

year  = {2019},

date = {2019-02-01},

booktitle = {27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {217-221},

publisher = {IEEE},

address = {Pavia, Italy},

series = {PDP'19},

abstract = {Parallel applications of the same domain can present similar patterns of behavior and characteristics. Characterizing common application behaviors can help for understanding performance aspects in the real-world scenario. One way to better understand and evaluate applications' characteristics is by using customizable/parametric benchmarks that enable users to represent important characteristics at run-time. We observed that parameterization techniques should be better exploited in the available benchmarks, especially on stream processing domain. For instance, although widely used, the stream processing benchmarks available in PARSEC do not support the simulation and evaluation of relevant and modern characteristics. Therefore, our goal is to identify the stream parallelism characteristics present in PARSEC. We also implemented a ready to use parameterization support and evaluated the application behaviors considering relevant performance metrics for stream parallelism (service time, throughput, latency). We choose Dedup to be our case study. The experimental results have shown performance improvements in our parameterization support for Dedup. Moreover, this support increased the customization space for benchmark users, which is simple to use. In the future, our solution can be potentially explored on different parallel architectures and parallel programming frameworks.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{SERPA:memory-gpu-multicore:PDP:19,

title = {Memory Performance and Bottlenecks in Multicore and GPU Architectures},

author = {Matheus S. Serpa and Francis B. Moreira and Philippe O. A. Navaux and Eduardo H. M. Cruz and Matthias Diener and Dalvan Griebler and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/EMPDP.2019.8671628},

doi = {10.1109/EMPDP.2019.8671628},

year  = {2019},

date = {2019-02-01},

booktitle = {27th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {233-236},

publisher = {IEEE},

address = {Pavia, Italy},

series = {PDP'19},

abstract = {Nowadays, there are several different architectures available not only for the industry, but also for normal consumers. Traditional multicore processors, GPUs, accelerators such as the Sunway SW26010, or even energy efficiency-driven processors such as the ARM family, present very different architectural characteristics. This wide range of characteristics presents a challenge for the developers of applications. Developers must deal with different instruction sets, memory hierarchies, or even different programming paradigms when programming for these architectures. Therefore, the same application can perform well when executing on one architecture, but poorly on another architecture. To optimize an application, it is important to have a deep understanding of how it behaves on different architectures. The related work in this area mostly focuses on a limited analysis encompassing execution time and energy. In this paper, we perform a detailed investigation on the impact of the memory subsystem of different architectures, which is one of the most important aspects to be considered. For this study, we performed experiments in the Broadwell CPU and Pascal GPU, using applications from the Rodinia benchmark suite. In this way, we were able to understand why an application performs well on one architecture and poorly on others.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{EWALD:WSCAD:18,

title = {Parallel and Distributed Processing Support for a Geospatial Data Visualization DSL},

author = {Endrius Ewald and Adriano Vogel and Cassiano Rista and Dalvan Griebler and Isabel Manssour and Luiz G. Fernandes},

url = {https://doi.org/10.1109/WSCAD.2018.00042},

doi = {10.1109/WSCAD.2018.00042},

year  = {2018},

date = {2018-10-01},

booktitle = {Symposium on High Performance Computing Systems (WSCAD)},

pages = {221-228},

publisher = {IEEE},

address = {São Paulo, Brazil},

abstract = {The amount of data generated worldwide related to geolocalization has exponentially increased. However, the fast processing of this amount of data is a challenge from the programming perspective, and many available solutions require learning a variety of tools and programming languages. This paper introduces the support for parallel and distributed processing in a DSL for Geospatial Data Visualization to speed up the data pre-processing phase. The results have shown the MPI version with dynamic data distribution performing better under medium and large data set files, while MPI-I/O version achieved the best performance with small data set files.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{larcc:multithreading_cloud:WSCAD:18,

title = {On the Performance of Multithreading Applications under Private Cloud Conditions},

author = {Anderson M Maliszewski and Dalvan Griebler and Adriano Vogel and Claudio Schepke},

url = {https://doi.org/10.1109/WSCAD.2018.00055},

doi = {10.1109/WSCAD.2018.00055},

year  = {2018},

date = {2018-10-01},

booktitle = {Symposium on High Performance Computing Systems (WSCAD)},

pages = {273-273},

publisher = {IEEE},

address = {São Paulo, Brazil},

abstract = {IaaS private clouds provide an attractive environment for scientific applications. However, the performance is a challenge, as additional abstraction layers imposed by the virtualization can cause overheads and bottlenecks. This paper contributes to a performance analysis of applications with dedicated and shared resources environments under private cloud conditions, deployed with container (LXC) or kernel-based (KVM) instances. We selected five benchmarks from PARSEC suite. In the experimental results, identify a performance pattern of behavior among the applications was hard. For a set of multi-threading applications, the KVM-based cloud instances achieved better performance, however, in the other set of applications, the LXC-based cloud instances performed better.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GRIEBLER:SLO-SPar-Nornir:REPARA:18,

title = {Service Level Objectives via C++11 Attributes},

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

url = {http://dx.doi.org/10.1007/978-3-030-10549-5_58},

doi = {10.1007/978-3-030-10549-5_58},

year  = {2018},

date = {2018-08-01},

booktitle = {Euro-Par 2018: Parallel Processing Workshops},

pages = {745-756},

publisher = {Springer},

address = {Turin, Italy},

series = {Lecture Notes in Computer Science},

abstract = {In recent years, increasing attention has been given to the possibility of guaranteeing Service Level Objectives (SLOs) to users about their applications, either regarding performance or power consumption. SLO can be implemented for parallel applications since they can provide many control knobs (e.g., the number of threads to use, the clock frequency of the cores, etc.) to tune the performance and power consumption of the application. Different from most of the existing approaches, we target sequential stream processing applications by proposing a solution based on C++ annotations. The user specifies which parts of the code to parallelize and what type of requirements should be enforced on that part of the code. Our solution first automatically parallelizes the annotated code and then applies self-adaptation approaches at run-time to enforce the user-expressed objectives. We ran experiments on different real-world applications, showing its simplicity and effectiveness.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{VOGEL:Adaptive-Latency-SPar:AutoDaSP:18,

title = {Autonomic and Latency-Aware Degree of Parallelism Management in SPar},

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

url = {http://dx.doi.org/10.1007/978-3-030-10549-5_3},

doi = {10.1007/978-3-030-10549-5_3},

year  = {2018},

date = {2018-08-01},

booktitle = {Euro-Par 2018: Parallel Processing Workshops},

pages = {28-39},

publisher = {Springer},

address = {Turin, Italy},

series = {Lecture Notes in Computer Science},

abstract = {Stream processing applications became a representative workload in current computing systems. A significant part of these applications demands parallelism to increase performance. However, programmers are often facing a trade-off between coding productivity and performance when introducing parallelism. SPar was created for balancing this trade-off to the application programmers by using the C++11 attributes’ annotation mechanism. In SPar and other programming frameworks for stream processing applications, the manual definition of the number of replicas to be used for the stream operators is a challenge. In addition to that, low latency is required by several stream processing applications. We noted that explicit latency requirements are poorly considered on the state-of-the-art parallel programming frameworks. Since there is a direct relationship between the number of replicas and the latency of the application, in this work we propose an autonomic and adaptive strategy to choose the proper number of replicas in SPar to address latency constraints. We experimentally evaluated our implemented strategy and demonstrated its effectiveness on a real-world application, demonstrating that our adaptive strategy can provide higher abstraction levels while automatically managing the latency.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{GRIEBLER:JS:18,

title = {Stream Parallelism with Ordered Data Constraints on Multi-Core Systems},

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

url = {https://doi.org/10.1007/s11227-018-2482-7},

doi = {10.1007/s11227-018-2482-7},

issn = {0920-8542},

year  = {2018},

date = {2018-07-01},

urldate = {2018-07-01},

journal = {The Journal of Supercomputing},

volume = {75},

number = {8},

pages = {4042-4061},

publisher = {Springer},

abstract = {It is often a challenge to keep input/output tasks/results in order for parallel computations ver data streams, particularly when stateless task operators are replicated to increase parallelism when there are irregular tasks. Maintaining input/output order requires additional coding effort and may significantly impact the application's actual throughput. Thus, we propose a new implementation technique designed to be easily integrated with any of the existing C++ parallel programming frameworks that support stream parallelism. In this paper, it is first implemented and studied using SPar, our high-level domain-specific language for stream parallelism. We discuss the results of a set of experiments with real-world applications revealing how significant performance improvements may be achieved when our proposed solution is integrated within SPar, especially for data compression applications. Also, we show the results of experiments performed after integrating our solution within FastFlow and TBB, revealing no significant overheads.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{larcc:NAS_cloud_LXC_KVM:HPCS:2018,

title = {The NAS Benchmark Kernels for Single and Multi-Tenant Cloud Instances with LXC/KVM},

author = {Anderson M Maliszewski and Dalvan Griebler and Claudio Schepke and Alexander Ditter and Dietmar Fey and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/HPCS.2018.00066},

doi = {10.1109/HPCS.2018.00066},

year  = {2018},

date = {2018-07-01},

booktitle = {International Conference on High Performance Computing & Simulation (HPCS)},

pages = {359-366},

publisher = {IEEE},

address = {Orleans, France},

series = {HPCS'18},

abstract = {Private IaaS clouds are an attractive environment for scientific workloads and applications. It provides advantages such as almost instantaneous availability of high-performance computing in a single node as well as compute clusters, easy access for researchers, and users that do not have access to conventional supercomputers. Furthermore, a cloud infrastructure provides elasticity and scalability to ensure and manage any software dependency on the system with no third-party dependency for researchers. However, one of the biggest challenges is to avoid significant performance degradation when migrating these applications from physical nodes to a cloud environment. Also, we lack more research investigations for multi-tenant cloud instances. In this paper, our goal is to perform a comparative performance evaluation of scientific applications with single and multi-tenancy cloud instances using KVM and LXC virtualization technologies under private cloud conditions. All analyses and evaluations were carried out based on NAS Benchmark kernels to simulate different types of workloads. We applied statistic significance tests to highlight the differences. The results have shown that applications running on LXC-based cloud instances outperform KVM-based cloud instances in 93.75% of the experiments w.r.t single tenant. Regarding multi-tenant, LXC instances outperform KVM instances in 45% of the results, where the performance differences were not as significant as expected.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{larcc:parsec_cloudstack_lxc_kvm:ISCC:2018,

title = {Performance of Data Mining, Media, and Financial Applications under Private Cloud Conditions},

author = {Dalvan Griebler and Adriano Vogel and Carlos A F Maron and Anderson M Maliszewski and Claudio Schepke and Luiz Gustavo Fernandes},

url = {https://dx.doi.org/10.1109/ISCC.2018.8538759},

doi = {10.1109/ISCC.2018.8538759},

year  = {2018},

date = {2018-06-01},

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

pages = {1530-1346},

publisher = {IEEE},

address = {Natal, Brazil},

series = {ISCC'18},

abstract = {This paper contributes to a performance analysis of real-world workloads under private cloud conditions. We selected six benchmarks from PARSEC related to three mainstream application domains (financial, data mining, and media processing). Our goal was to evaluate these application domains in different cloud instances and deployment environments, concerning container or kernel-based instances and using dedicated or shared machine resources. Experiments have shown that performance varies according to the application characteristics, virtualization technology, and cloud environment. Results highlighted that financial, data mining, and media processing applications running in the LXC instances tend to outperform KVM when there is a dedicated machine resource environment. However, when two instances are sharing the same machine resources, these applications tend to achieve better performance in the KVM instances. Finally, financial applications achieved better performance in the cloud than media and data mining.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{larcc:network_performance_container:ISCC:2018,

title = {Evaluating, Estimating, and Improving Network Performance in Container-based Clouds},

author = {Cassiano Rista and Marcelo Teixeira and Dalvan Griebler and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/ISCC.2018.8538558},

doi = {10.1109/ISCC.2018.8538558},

year  = {2018},

date = {2018-06-01},

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

pages = {1530-1346},

publisher = {IEEE},

address = {Natal, Brazil},

series = {ISCC'18},

abstract = {Cloud computing has recently attracted a great deal of interest from both industry and academia, emerging as an important paradigm to improve resource utilization, efficiency, flexibility, and pay-per-use. However, cloud platforms inherently include a virtualization layer that imposes performance degradation on network-intensive applications. Thus, it is crucial to anticipate possible performance degradation to resolve system bottlenecks. This paper uses the Petri Nets approach to create different models for evaluating, estimating, and improving network performance in container-based cloud environments. Based on model estimations, we assessed the network bandwidth utilization of the system under different setups. Then, by identifying possible bottlenecks, we show how the system could be modified to improve performance. We then tested how the model would behave through real-world experiments. When the model indicates probable bandwidth saturation, we propose a link aggregation approach to increase bandwidth, using lightweight virtualization to reduce virtualization overhead. Results reveal that our model anticipates the structural and behavioral characteristics of the network in the cloud environment. Therefore, it systematically improves network efficiency, which saves effort, time, and money.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GRIEBLER:NAS-CPP:PDP:18,

title = {Efficient NAS Benchmark Kernels with C++ Parallel Programming},

author = {Dalvan Griebler and Junior Loff and Gabriele Mencagli and Marco Danelutto and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/PDP2018.2018.00120},

doi = {10.1109/PDP2018.2018.00120},

year  = {2018},

date = {2018-03-01},

booktitle = {26th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {733-740},

publisher = {IEEE},

address = {Cambridge, UK},

series = {PDP'18},

abstract = {Benchmarking is a way to study the performance of new architectures and parallel programming frameworks. Well-established benchmark suites such as the NAS Parallel Benchmarks (NPB) comprise legacy codes that still lack portability to C++ language. As a consequence, a set of high-level and easy-to-use C++ parallel programming frameworks cannot be tested in NPB. Our goal is to describe a C++ porting of the NPB kernels and to analyze the performance achieved by different parallel implementations written using the Intel TBB, OpenMP and FastFlow frameworks for Multi-Cores. The experiments show an efficient code porting from Fortran to C++ and an efficient parallelization on average.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{GRIEBLER:IJPP:18,

title = {High-Level and Productive Stream Parallelism for Dedup, Ferret, and Bzip2},

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

url = {https://doi.org/10.1007/s10766-018-0558-x},

doi = {10.1007/s10766-018-0558-x},

issn = {1573-7640},

year  = {2018},

date = {2018-02-01},

journal = {International Journal of Parallel Programming},

volume = {47},

number = {1},

pages = {253-271},

publisher = {Springer},

abstract = {Parallel programming has been a challenging task for application programmers. Stream processing is an application domain present in several scientific, enterprise, and financial areas that lack suitable abstractions to exploit parallelism. Our goal is to assess the feasibility of state-of-the-art frameworks/libraries (Pthreads, TBB, and FastFlow) and the SPar domain-specific language for real-world streaming applications (Dedup, Ferret, and Bzip2) targeting multi-core architectures. SPar was specially designed to provide high-level and productive stream parallelism abstractions, supporting programmers with standard C++-11 annotations. For the experiments, we implemented three streaming applications. We discussed SPar’s programmability advantages compared to the frameworks in terms of productivity and structured parallel programming. The results demonstrate that SPar improves productivity and provides the necessary features to achieve similar performances compared to the state-of-the-art.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{GRIEBLER:WSCAD:17,

title = {High-Level and Efficient Stream Parallelism on Multi-core Systems with SPar for Data Compression Applications},

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

url = {https://gmap.pucrs.br/dalvan/papers/2017/CR_WSCAD_2017.pdf},

year  = {2017},

date = {2017-10-01},

booktitle = {XVIII Simpósio em Sistemas Computacionais de Alto Desempenho},

pages = {16-27},

publisher = {SBC},

address = {Campinas, SP, Brasil},

abstract = {The stream processing domain is present in several real-world applications that are running on multi-core systems. In this paper, we focus on data compression applications that are an important sub-set of this domain. Our main goal is to assess the programmability and efficiency of domain-specific language called SPar. It was specially designed for expressing stream parallelism and it promises higher-level parallelism abstractions without significant performance losses. Therefore, we parallelized Lzip and Bzip2 compressors with SPar and compared with state-of-the-art frameworks. The results revealed that SPar is able to efficiently exploit stream parallelism as well as provide suitable abstractions with less code intrusion and code re-factoring.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GRIEBLER:PARCO:17,

title = {Towards Distributed Parallel Programming Support for the SPar DSL},

author = {Dalvan Griebler and Luiz Gustavo Fernandes},

url = {https://doi.org/10.3233/978-1-61499-843-3-563},

doi = {10.3233/978-1-61499-843-3-563},

year  = {2017},

date = {2017-09-01},

booktitle = {Parallel Computing is Everywhere, Proceedings of the International 

 Conference on Parallel Computing},

pages = {563-572},

publisher = {IOS Press},

address = {Bologna, Italy},

series = {ParCo'17},

abstract = {SPar was originally designed to provide high-level abstractions for stream parallelism in C++ programs targeting multi-core systems. This work proposes distributed parallel programming support for SPar targeting cluster environments. The goal is to preserve the original semantics while source-to-source code transformations will be turned into MPI (Message Passing Interface) parallel code. The results of the experiments presented in the paper demonstrate improved programmability without significant performance losses.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GRIEBLER:REPARA:17,

title = {Higher-Level Parallelism Abstractions for Video Applications with SPar},

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

url = {https://doi.org/10.3233/978-1-61499-843-3-698},

doi = {10.3233/978-1-61499-843-3-698},

year  = {2017},

date = {2017-09-01},

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

pages = {698-707},

publisher = {IOS Press},

address = {Bologna, Italy},

series = {ParCo'17},

abstract = {SPar is a Domain-Specific Language (DSL) designed to provide high-level parallel programming abstractions for streaming applications. Video processing application domain requires parallel processing to extract and analyze information quickly. When using state-of-the-art frameworks such as FastFlow and TBB, the application programmer has to manage source code re-factoring and performance optimization to implement parallelism efficiently. Our goal is to make this process easier for programmers through SPar. Thus we assess SPar's programming language and its performance in traditional video applications. We also discuss different implementations compared to the ones of SPar. Results demonstrate that SPar maintains the sequential code structure, is less code intrusive, and provides higher-level programming abstractions without introducing notable performance losses. Therefore, it represents a good choice for application programmers from the video processing domain.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{LEDUR:COMPSAC:17,

title = {A High-Level DSL for Geospatial Visualizations with Multi-core Parallelism Support},

author = {Cleverson Ledur and Dalvan Griebler and Isabel Manssour and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/COMPSAC.2017.18},

doi = {10.1109/COMPSAC.2017.18},

year  = {2017},

date = {2017-07-01},

booktitle = {41th IEEE Computer Society Signature Conference on Computers, Software and Applications},

pages = {298-304},

publisher = {IEEE},

address = {Torino, Italy},

series = {COMPSAC'17},

abstract = {The amount of data generated worldwide associated with geolocalization has exponentially increased over the last decade due to social networks, population demographics, and the popularization of Global Positioning Systems. Several methods for geovisualization have already been developed, but many of them are focused on a specific application or require learning a variety of tools and programming languages. It becomes even more difficult when users have to manage a large amount of data because state-of-the-art alternatives require the use of third-party pre-processing tools. We present a novel Domain-Specific Language (DSL), which focuses on large data geovisualizations. Through a compiler, we support automatic visualization generations and data pre-processing. The system takes advantage of multi-core parallelism to speed-up data pre-processing abstractly. Our experiments were designated to highlight the programming effort and performance of our DSL. The results have shown a considerable programming effort reduction and efficient parallelism support with respect to the sequential version.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{larcc:link_aggregation:HPCS:2017,

title = {Improving the Network Performance of a Container-Based Cloud Environment for Hadoop Systems},

author = {Cassiano Rista and Dalvan Griebler and Carlos A. F. Maron and Luiz Gustavo Fernandes},

url = {http://ieeexplore.ieee.org/document/8035136/},

doi = {10.1109/HPCS.2017.97},

year  = {2017},

date = {2017-07-01},

booktitle = {International Conference on High Performance Computing & Simulation (HPCS)},

pages = {619-626},

publisher = {IEEE},

address = {Genoa, Italy},

series = {HPCS'17},

abstract = {Cloud computing has emerged as an important paradigm to improve resource utilization, efficiency, flexibility, and the pay-per-use billing structure. However, cloud platforms cause performance degradations due to their virtualization layer and may not be appropriate for the requirements of high-performance applications, such as big data. This paper tackles the problem of improving network performance in container-based cloud instances to create a viable alternative to run network intensive Hadoop applications. Our approach consists of deploying link aggregation via the IEEE 802.3ad standard to increase the available bandwidth and using LXC (Linux Container) cloud instances to create a Hadoop cluster. In order to evaluate the efficiency of our approach and the overhead added by the container-based cloud environment, we ran a set of experiments to measure throughput, latency, bandwidth utilization, and completion times. The results prove that our approach adds minimal overhead in cloud environment as well as increases throughput and reduces latency. Moreover, our approach demonstrates a suitable alternative for running Hadoop applications, reducing completion times up to 33.73%},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{GRIEBLER:PPL:17,

title = {SPar: A DSL for High-Level and Productive Stream Parallelism},

author = {Dalvan Griebler and Marco Danelutto and Massimo Torquati and Luiz Gustavo Fernandes},

url = {http://dx.doi.org/10.1142/S0129626417400059},

doi = {10.1142/S0129626417400059},

year  = {2017},

date = {2017-03-01},

urldate = {2017-03-01},

journal = {Parallel Processing Letters},

volume = {27},

number = {01},

pages = {1740005},

publisher = {World Scientific},

abstract = {This paper introduces SPar, an internal C++ Domain-Specific Language (DSL) that supports the development of classic stream parallel applications. The DSL uses standard C++ attributes to introduce annotations tagging the notable components of stream parallel applications: stream sources and stream processing stages. A set of tools process SPar code (C++ annotated code using the SPar attributes) to generate FastFlow C++ code that exploits the stream parallelism denoted by SPar annotations while targeting shared memory multi-core architectures. We outline the main SPar features along with the main implementation techniques and tools. Also, we show the results of experiments assessing the feasibility of the entire approach as well as SPar’s performance and expressiveness.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{larcc:intra-cloud_networking_cloudstack:PDP:17,

title = {An Intra-Cloud Networking Performance Evaluation on CloudStack Environment},

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

url = {http://ieeexplore.ieee.org/document/7912689/},

doi = {10.1109/PDP.2017.40},

year  = {2017},

date = {2017-03-01},

booktitle = {25th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {5},

publisher = {IEEE},

address = {St. Petersburg, Russia},

series = {PDP'17},

abstract = {Infrastructure-as-a-Service (IaaS) is a cloud on-demand commodity built on top of virtualization technologies and managed by IaaS tools. In this scenario, performance is a relevant matter because a set of aspects may impact and increase the system overhead.Specific on the network, the use of virtualized capabilities may cause performance degradation (eg.,latency, throughput). The goal of this paper is to contribute to networking performance evaluation, providing new insights for private IaaS clouds. To achieve our goal, we deploy CloudStack environments and conduct experiments with different configurations and techniques. The research findings demonstrate that KVM-based cloud instances have small network performance degradation regarding throughput (about 0.2% for coarse-grained and 6.8% for fine-grained messages) while container-based instances have even better results. On the other hand, the KVM instances present worst latency (about 12.4% on coarse-grained and two times more on fine-grained messages w.r.t. native environment) and better in container-based instances, where the performance results are close to the native environment. Furthermore, we demonstrate a performance optimization of applications running on KVM.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{larcc:saas_analytics:REABTIC:16,

title = {Towards a Software as a Service for Biodigestor Analytics},

author = {Ricardo Pieper and Dalvan Griebler and Adalberto Lovato},

url = {http://larcc.setrem.com.br/wp-content/uploads/2017/04/PIEPER_REABTIC_2016.pdf},

doi = {10.5281/zenodo.345587},

year  = {2016},

date = {2016-08-01},

journal = {Revista Eletrônica Argentina-Brasil de Tecnologias da Informação e da Comunicação (REABTIC)},

volume = {1},

number = {5},

pages = {15},

publisher = {SETREM},

address = {Três de Maio, Brazil},

abstract = {The field of machine learning is becoming even more important in the last years. The ever-increasing amount of data and complexity of computational problems challenges the currently available technology. Meanwhile, anaerobic digesters represent a good alternative for renewable energy production in Brazil. However, performing efficient and accurate predictions/analytics while completely abstracting machine learning details from end-users might not be a simple task to achieve. Usually, such tools are made for a specific scenario and may not fit with particular and general needs. Our goal was to create a SaaS for biogas data analytics by using a neural network. Therefore, an open source, cloud-enabled SaaS (Software as a Service) was developed and deployed in LARCC (Laboratory of Advanced Researches on Cloud Computing) at SETREM. The results have shown the SaaS application is able to perform predictions. The neural network's accuracy is not significantly worse than a state-of-the-art implementation, and its training speed is faster. The user interface demonstrates to be intuitive, and the predictions were accurate when providing the training algorithm with sufficient data. In addition, the file processing and network training time were good enough under traditional workload conditions.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@phdthesis{GRIEBLER:PHD:16,

title = {Domain-Specific Language & Support Tool for High-Level Stream Parallelism},

author = {Dalvan Griebler},

url = {http://tede2.pucrs.br/tede2/handle/tede/6776},

year  = {2016},

date = {2016-06-01},

address = {Porto Alegre, Brazil},

school = {Faculdade de Informática - PPGCC - PUCRS},

abstract = {Stream-based systems are representative of several application domains including video, audio, networking, graphic processing, etc. Stream programs may run on different kinds of parallel architectures (desktop, servers, cell phones, and supercomputers) and represent significant workloads on our current computing systems. Nevertheless, most of them are still not parallelized. Moreover, when new software has to be developed, programmers often face a trade-off between coding productivity, code portability, and performance. To solve this problem, we provide a new Domain-Specific Language (DSL) that naturally/on-the-fly captures and represents parallelism for stream-based applications. The aim is to offer a set of attributes (through annotations) that preserves the program's source code and is not architecture-dependent for annotating parallelism. We used the C++ attribute mechanism to design a ``textitde-facto'' standard C++ embedded DSL named SPar. However, the implementation of DSLs using compiler-based tools is difficult, complicated, and usually requires a significant learning curve. This is even harder for those who are not familiar with compiler technology. Therefore, our motivation is to simplify this path for other researchers (experts in their domain) with support tools (our tool is CINCLE) to create high-level and productive DSLs through powerful and aggressive source-to-source transformations. In fact, parallel programmers can use their expertise without having to design and implement low-level code. The main goal of this thesis was to create a DSL and support tools for high-level stream parallelism in the context of a programming framework that is compiler-based and domain-oriented. Thus, we implemented SPar using CINCLE. SPar supports the software developer with productivity, performance, and code portability while CINCLE provides sufficient support to generate new DSLs. Also, SPar targets source-to-source transformation producing parallel pattern code built on top of FastFlow and MPI. Finally, we provide a full set of experiments showing that SPar provides better coding productivity without significant performance degradation in multi-core systems as well as transformation rules that are able to achieve code portability (for cluster architectures) through its generalized attributes.},

keywords = {},

pubstate = {published},

tppubtype = {phdthesis}

}

@inproceedings{larcc:IaaS_private:PDP:16,

title = {Private IaaS Clouds: A Comparative Analysis of OpenNebula, CloudStack and OpenStack},

author = {Adriano Vogel and Dalvan Griebler and Carlos A. F. Maron and Claudio Schepke and Luiz Gustavo Fernandes},

url = {http://ieeexplore.ieee.org/document/7445407/},

doi = {10.1109/PDP.2016.75},

year  = {2016},

date = {2016-02-01},

booktitle = {24th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)},

pages = {672-679},

publisher = {IEEE},

address = {Heraklion Crete, Greece},

series = {PDP'16},

abstract = {Despite the evolution of cloud computing in recent years, the performance and comprehensive understanding of the available private cloud tools are still under research. This paper contributes to an analysis of the Infrastructure as a Service (IaaS) domain by mapping new insights and discussing the challenges for improving cloud services. The goal is to make a comparative analysis of OpenNebula, OpenStack and CloudStack tools, evaluating their differences on support for flexibility and resiliency. Also, we aim at evaluating these three cloud tools when they are deployed using a mutual hypervisor (KVM) for discovering new empirical insights. Our research results demonstrated that OpenStack is the most resilient and CloudStack is the most flexible for deploying an IaaS private cloud. Moreover, the performance experiments indicated some contrasts among the private IaaS cloud instances when running intensive workloads and scientific applications.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@article{ADORNES:IJSEKE:15,

title = {Coding Productivity in MapReduce Applications for Distributed and Shared Memory Architectures},

author = {Daniel Adornes and Dalvan Griebler and Cleverson Ledur and Luiz G. Fernandes},

url = {http://dx.doi.org/10.1142/S0218194015710096},

doi = {10.1142/S0218194015710096},

year  = {2015},

date = {2015-12-01},

urldate = {2015-12-01},

journal = {International Journal of Software Engineering and Knowledge Engineering},

volume = {25},

number = {10},

pages = {1739-1741},

publisher = {World Scientific},

abstract = {MapReduce was originally proposed as a suitable and efficient approach for analyzing and processing large amounts of data. Since then, many researches contributed with MapReduce implementations for distributed and shared memory architectures. Nevertheless, different architectural levels require different optimization strategies in order to achieve high-performance computing. Such strategies in turn have caused very different MapReduce programming interfaces among these researches. This paper presents some research notes on coding productivity when developing MapReduce applications for distributed and shared memory architectures. As a case study, we introduce our current research on a unified MapReduce domain-specific language with code generation for Hadoop and Phoenix++, which has achieved a coding productivity increase from 41.84% and up to 94.71% without significant performance losses (below 3%) compared to those frameworks.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{LEDUR:AICCSA:15,

title = {Towards a Domain-Specific Language for Geospatial Data Visualization Maps with Big Data Sets},

author = {Cleverson Ledur and Dalvan Griebler and Isabel Manssour and Luiz G. Fernandes},

url = {http://dx.doi.org/10.1109/AICCSA.2015.7507178},

doi = {10.1109/AICCSA.2015.7507178},

year  = {2015},

date = {2015-11-01},

booktitle = {ACS/IEEE International Conference on Computer Systems and Applications},

pages = {8},

publisher = {IEEE},

address = {Marrakech, Marrocos},

series = {AICCSA'15},

abstract = {Data visualization is an alternative for representing information and helping people gain faster insights. However, the programming/creating of a visualization for large data sets is still a challenging task for users with low-level of software development knowledge. Our goal is to increase the productivity of experts who are familiar with the application domain. Therefore, we proposed an external Domain-Specific Language (DSL) that allows massive input of raw data and provides a small dictionary with suitable data visualization keywords. Also, we implemented it to support efficient data filtering operations and generate HTML or Javascript output code files (using Google Maps API). To measure the potential of our DSL, we evaluated four types of geospatial data visualization maps with four different technologies. The experiment results demonstrated a productivity gain when compared to the traditional way of implementing (e.g., Google Maps API, OpenLayers, and Leaflet), and efficient algorithm implementation.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GRIEBLER:PARCO:15,

title = {An Embedded C++ Domain-Specific Language for Stream Parallelism},

author = {Dalvan Griebler and Marco Danelutto and Massimo Torquati and Luiz G. Fernandes},

url = {http://dx.doi.org/10.3233/978-1-61499-621-7-317},

doi = {10.3233/978-1-61499-621-7-317},

year  = {2015},

date = {2015-09-01},

booktitle = {Parallel Computing: On the Road to Exascale, Proceedings of the International Conference on Parallel Computing},

pages = {317-326},

publisher = {IOS Press},

address = {Edinburgh, Scotland, UK},

series = {ParCo'15},

abstract = {This paper proposes a new C++ embedded Domain-Specific Language (DSL) for expressing stream parallelism by using standard C++11 attributes annotations. The main goal is to introduce high-level parallel abstractions for developing stream based parallel programs as well as reducing sequential source code rewriting. We demonstrated that by using a small set of attributes it is possible to produce different parallel versions depending on the way the source code is annotated. The performances of the parallel code produced are comparable with those obtained by manual parallelization.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}