Dalvan Griebler

@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}

}

@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}

}

@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},

journal = {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: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: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{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{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}

}

@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: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{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},

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}

}

@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},

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}

}

@article{larcc:openebula_openstack:REABTIC:15,

title = {Understanding, Discussing and Analyzing the OpenNebula's and OpenStack's IaaS Management Layers},

author = {Demétrius Roveda and Adriano Vogel and Dalvan Griebler},

url = {http://larcc.setrem.com.br/wp-content/uploads/2017/04/ROVEDA_REABTIC_2015A.pdf},

doi = {10.5281/zenodo.59467},

year  = {2015},

date = {2015-08-01},

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

volume = {1},

number = {3},

pages = {15},

publisher = {SETREM},

address = {Três de Maio, Brazil},

abstract = {The OpenNebula and OpenStack tools have been used for large corporations and research centers to implement IaaS clouds. The management layer is an important element for the user and administrator because it deals with the resources monitoring, development support, orchestration, and integration with other cloud platforms and services. The goal of this paper is to discuss and analyze the differences in the management layer for pointing out advantages and disadvantages of the tools. The results demonstrated that OpenNebula is more restrict and focused on simplicity in almost all comparisons while OpenStack is fragmented, complex and robust.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@inproceedings{ADORNES:SEKE:15,

title = {A Unified MapReduce Domain-Specific Language for Distributed and Shared Memory Architectures},

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

url = {http://dx.doi.org/10.18293/SEKE2015-204},

doi = {10.18293/SEKE2015-204},

year  = {2015},

date = {2015-07-01},

booktitle = {The 27th International Conference on Software Engineering & Knowledge Engineering},

pages = {6},

publisher = {Knowledge Systems Institute Graduate School},

address = {Pittsburgh, USA},

abstract = {MapReduce is a suitable and efficient parallel programming pattern for processing big data analysis. In recent years, many frameworks/languages have implemented this pattern to achieve high performance in data mining applications, particularly for distributed memory architectures (e.g., clusters). Nevertheless, the industry of processors is now able to offer powerful processing on single machines (e.g., multi-core). Thus, these applications may address the parallelism in another architectural level. The target problems of this paper are code reuse and programming effort reduction since current solutions do not provide a single interface to deal with these two architectural levels. Therefore, we propose a unified domain-specific language in conjunction with transformation rules for code generation for Hadoop and Phoenix++. We selected these frameworks as state-of-the-art MapReduce implementations for distributed and shared memory architectures, respectively. Our solution achieves a programming effort reduction from 41.84% and up to 95.43% without significant performance losses (below the threshold of 3%) compared to Hadoop and Phoenix++.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GRIEBLER:SEKE:14,

title = {Performance and Usability Evaluation of a Pattern-Oriented Parallel Programming Interface for Multi-Core Architectures},

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

url = {https://gmap.pucrs.br/dalvan/papers/2014/CR_SEKE_2014.pdf},

year  = {2014},

date = {2014-07-01},

booktitle = {The 26th International Conference on Software Engineering & Knowledge Engineering},

pages = {25-30},

publisher = {Knowledge Systems Institute Graduate School},

address = {Vancouver, Canada},

abstract = {Multi-core architectures have increased the power of parallelism by coupling many cores in a single chip. This becomes even more complex for developers to exploit the avail-able parallelism in order to provide high performance scalable programs. To address these challenges, we propose the DSL-POPP (Domain-Specific Language for Pattern-Oriented Parallel Programming), which links the pattern-based approach in the programming interface as an alternative to reduce the effort of parallel software development, and achieve good performance in some applications. In this paper, the objective is to evaluate the usability and performance of the master/slave pattern and compare it to the Pthreads library. Moreover, experiments have shown that the master/slave interface of the DSL-POPP reduces up to 50% of the programming effort, without significantly affecting the performance.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gmap:RUI:PDP:14,

title = {Evaluating the Impact of Transactional Characteristics on the Performance of Transactional Memory Applications},

author = {Fernando Rui and Márcio Castro and Dalvan Griebler and Luiz Gustavo Fernandes},

url = {https://doi.org/10.1109/PDP.2014.57},

doi = {10.1109/PDP.2014.57},

year  = {2014},

date = {2014-02-01},

booktitle = {22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing},

pages = {93-97},

publisher = {IEEE},

address = {Torino, Italy},

series = {PDP'14},

abstract = {Transactional Memory (TM) is reputed by many researchers to be a promising solution to ease parallel programming on multicore processors. This model provides the scalability of fine-grained locking while avoiding common issues of traditional mechanisms, such as deadlocks. During these almost twenty years of research, several TM systems and benchmarks have been proposed. However, TM is not yet widely adopted by the scientific community to develop parallel applications due to unanswered questions in the literature, such as "how to identify if a parallel application can exploit TM to achieve better performance?" or "what are the reasons of poor performances of some TM applications?". In this work, we contribute to answer those questions through a comparative evaluation of a set of TM applications on four different state- of-the-art TM systems. Moreover, we identify some of the most important TM characteristics that impact directly the performance of TM applications. Our results can be useful to identify opportunities for optimizations.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{GRIEBLER:SBLP:13,

title = {Towards a Domain-Specific Language for Patterns-Oriented Parallel Programming},

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

url = {http://dx.doi.org/10.1007/978-3-642-40922-6_8},

doi = {10.1007/978-3-642-40922-6_8},

year  = {2013},

date = {2013-10-01},

booktitle = {Programming Languages - 17th Brazilian Symposium - SBLP},

volume = {8129},

pages = {105-119},

publisher = {Springer Berlin Heidelberg},

address = {Brasilia, Brazil},

series = {Lecture Notes in Computer Science},

abstract = {Pattern-oriented programming has been used in parallel code development for many years now. During this time, several tools (mainly frameworks and libraries) proposed the use of patterns based on programming primitives or templates. The implementation of patterns using those tools usually requires human expertise to correctly set up communication/synchronization among processes. In this work, we propose the use of a Domain Specific Language to create pattern-oriented parallel programs (DSL-POPP). This approach has the advantage of offering a higher programming abstraction level in which communication/synchronization among processes is hidden from programmers. We compensate the reduction in programming flexibility offering the possibility to use combined and/or nested parallel patterns (i.e., parallelism in levels), allowing the design of more complex parallel applications. We conclude this work presenting an experiment in which we develop a parallel application exploiting combined and nested parallel patterns in order to demonstrate the main properties of DSL-POPP.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{RAEDER:WSCAD:11,

title = {Performance Prediction of Parallel Applications with Parallel Patterns Using Stochastic Methods},

author = {Mateus Raeder and Dalvan Griebler and Lucas Baldo and Luiz G. Fernandes},

url = {https://doi.org/10.1109/WSCAD-SSC.2011.18},

doi = {10.1109/WSCAD-SSC.2011.18},

year  = {2011},

date = {2011-10-01},

booktitle = {Sistemas Computacionais (WSCAD-SSC), XII Simpósio em Sistemas Computacionais de Alto Desempenho},

pages = {1-13},

publisher = {IEEE},

address = {Espírito Santo, Brasil},

abstract = {One of the main problems in the high performance computing area is the difficulty to define the best strategy to parallelize an application. In this context, the use of analytical methods to evaluate the performance behavior of such applications seems to be an interesting alternative and can help to identify the best implementation strategies. In this work, the Stochastic Automata Network formalism is adopted to model and evaluate the performance of parallel applications, specially developed for clusters of workstations platforms. The methodology used is based on the construction of generic models to describe classical parallel implementation schemes, like Master/Slave, Parallel Phases, Pipeline and Divide and Conquer. Those models are adapted to represent cases of real applications through the definition of input parameters values. Finally, aiming to verify the accuracy of the adopted technique, some comparisons with real applications implementation results are presented.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}