Tiziano De Matteis | Università di Pisa (original) (raw)

Uploads

Papers by Tiziano De Matteis

This paper addresses the problem of designing scaling strategies for elastic data stream processi... more This paper addresses the problem of designing scaling strategies for elastic data stream processing. Elasticity allows applications to rapidly change their configuration on-the-fly (e.g., the amount of used resources) in response to dynamic workload fluctuations. In this work we face this problem by adopting the Model Predictive Control technique, a control-theoretic method aimed at finding the optimal application configuration along a limited prediction horizon in the future by solving an online optimization problem. Our control strategies are designed to address latency constraints, using Queueing Theory models, and energy consumption by changing the number of used cores and the CPU frequency through the Dynamic Voltage and Frequency Scaling (DVFS) support available in the modern multicore CPUs. The proactive capabilities, in addition to the latency-and energy-awareness, represent the novel features of our approach. To validate our methodology, we develop a thorough set of experiments on a high-frequency trading application. The results demonstrate the high-degree of flexibility and configurability of our approach, and show the effectiveness of our elastic scaling strategies compared with existing state-of-the-art techniques used in similar scenarios.

Lecture Notes in Computer Science, 2015

With the wide diffusion of parallel architectures parallelism has become an indispensable factor ... more With the wide diffusion of parallel architectures parallelism has become an indispensable factor in the application esign. However, the cost of the parallelization process of existing applications is still too high in terms of time-to-development, and often requires a large effort and expertise by the programmer.
The REPARA methodology consists in a systematic way to express parallel patterns by annotating the source code using C++11 attributes transformed automatically in a target parallel code based on parallel programming libraries (e.g. FastFlow, Intel TBB). In this paper we apply this approach in the parallelization of a real high-frequency trading application. The description shows the effectiveness of the approach in easily prototyping several parallel variants of the same code. We also propose an extension of a REPARA attribute to express a user-defined scheduling
strategy, which makes it possible to design a high-throughput
and low-latency parallelization of our code outperforming the
other parallel variants in most of the considered test-cases.

2014 International Conference on High Performance Computing & Simulation (HPCS), 2014

Data Stream Processing (DaSP) is a recent and highly active research field, applied in various re... more Data Stream Processing (DaSP) is a recent and highly active research field, applied in various real world scenarios. Differently than traditional applications, input data is seen as transient continuous streams that must be processed “on the fly”, with critical requirements on throughput, latency and memory occupancy. A parallel solution is often advocated, but the problem of designing and implementing high throughput and low latency DaSP applications is complex per se and because of the presence of multiple streams characterized by high volume, high velocity and high variability. Moreover, parallel DaSP applications must be able to adapt themselves to data dynamics in order to satisfy desired QoS levels. The aim of our work is to study these problems in an integrated way, providing to the programmers a methodological framework for the parallelization of DaSP applications.

2014 IEEE International Symposium on Parallel and Distributed Processing with Applications, 2014

Data Stream Processing (DaSP) is a paradigm characterized by on-line (often real-time) applicatio... more Data Stream Processing (DaSP) is a paradigm characterized by on-line (often real-time) applications working on unlimited data streams whose elements must be processed efficiently "on the fly". DaSP computations are characterized by data-flow graphs of operators connected via streams and working on the received elements according to high throughput and low latency requirements. To achieve these constraints, high-performance DaSP operators requires advanced parallelism models, as well related design and implementation techniques targeting multi-core architectures. In this paper we focus on the parallelization of the window-based stream join, an important operator that raises challenging issues in terms of parallel windows management. We review the state-of-the-art solutions about the stream join parallelization and we propose our novel parallel strategy and its implementation on multicores. As demonstrated by experimental results, our parallel solution introduces two important advantages with respect to the existing solutions: (i) it features an high-degree of configurability in order to address the symmetricity/asymmetricity of input streams (in terms of their arrival rate and window length), (ii) our parallelization provides a high throughput and it is definitely better than the compared solutions in terms of latency, providing an efficient way to perform stream joins on latency-sensible applications.

2014 22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, 2014

Software Engineering / 811: Parallel and Distributed Computing and Networks / 816: Artificial Intelligence and Applications, 2014

Artificial Intelligence and Applications / 794: Modelling, Identification and Control / 795: Parallel and Distributed Computing and Networks / 796: Software Engineering / 792: Web-based Education, 2013

This paper addresses the problem of designing scaling strategies for elastic data stream processi... more This paper addresses the problem of designing scaling strategies for elastic data stream processing. Elasticity allows applications to rapidly change their configuration on-the-fly (e.g., the amount of used resources) in response to dynamic workload fluctuations. In this work we face this problem by adopting the Model Predictive Control technique, a control-theoretic method aimed at finding the optimal application configuration along a limited prediction horizon in the future by solving an online optimization problem. Our control strategies are designed to address latency constraints, using Queueing Theory models, and energy consumption by changing the number of used cores and the CPU frequency through the Dynamic Voltage and Frequency Scaling (DVFS) support available in the modern multicore CPUs. The proactive capabilities, in addition to the latency-and energy-awareness, represent the novel features of our approach. To validate our methodology, we develop a thorough set of experiments on a high-frequency trading application. The results demonstrate the high-degree of flexibility and configurability of our approach, and show the effectiveness of our elastic scaling strategies compared with existing state-of-the-art techniques used in similar scenarios.

Lecture Notes in Computer Science, 2015

With the wide diffusion of parallel architectures parallelism has become an indispensable factor ... more With the wide diffusion of parallel architectures parallelism has become an indispensable factor in the application esign. However, the cost of the parallelization process of existing applications is still too high in terms of time-to-development, and often requires a large effort and expertise by the programmer.
The REPARA methodology consists in a systematic way to express parallel patterns by annotating the source code using C++11 attributes transformed automatically in a target parallel code based on parallel programming libraries (e.g. FastFlow, Intel TBB). In this paper we apply this approach in the parallelization of a real high-frequency trading application. The description shows the effectiveness of the approach in easily prototyping several parallel variants of the same code. We also propose an extension of a REPARA attribute to express a user-defined scheduling
strategy, which makes it possible to design a high-throughput
and low-latency parallelization of our code outperforming the
other parallel variants in most of the considered test-cases.

2014 International Conference on High Performance Computing & Simulation (HPCS), 2014

Data Stream Processing (DaSP) is a recent and highly active research field, applied in various re... more Data Stream Processing (DaSP) is a recent and highly active research field, applied in various real world scenarios. Differently than traditional applications, input data is seen as transient continuous streams that must be processed “on the fly”, with critical requirements on throughput, latency and memory occupancy. A parallel solution is often advocated, but the problem of designing and implementing high throughput and low latency DaSP applications is complex per se and because of the presence of multiple streams characterized by high volume, high velocity and high variability. Moreover, parallel DaSP applications must be able to adapt themselves to data dynamics in order to satisfy desired QoS levels. The aim of our work is to study these problems in an integrated way, providing to the programmers a methodological framework for the parallelization of DaSP applications.

2014 IEEE International Symposium on Parallel and Distributed Processing with Applications, 2014

Data Stream Processing (DaSP) is a paradigm characterized by on-line (often real-time) applicatio... more Data Stream Processing (DaSP) is a paradigm characterized by on-line (often real-time) applications working on unlimited data streams whose elements must be processed efficiently "on the fly". DaSP computations are characterized by data-flow graphs of operators connected via streams and working on the received elements according to high throughput and low latency requirements. To achieve these constraints, high-performance DaSP operators requires advanced parallelism models, as well related design and implementation techniques targeting multi-core architectures. In this paper we focus on the parallelization of the window-based stream join, an important operator that raises challenging issues in terms of parallel windows management. We review the state-of-the-art solutions about the stream join parallelization and we propose our novel parallel strategy and its implementation on multicores. As demonstrated by experimental results, our parallel solution introduces two important advantages with respect to the existing solutions: (i) it features an high-degree of configurability in order to address the symmetricity/asymmetricity of input streams (in terms of their arrival rate and window length), (ii) our parallelization provides a high throughput and it is definitely better than the compared solutions in terms of latency, providing an efficient way to perform stream joins on latency-sensible applications.

2014 22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, 2014

Software Engineering / 811: Parallel and Distributed Computing and Networks / 816: Artificial Intelligence and Applications, 2014

Artificial Intelligence and Applications / 794: Modelling, Identification and Control / 795: Parallel and Distributed Computing and Networks / 796: Software Engineering / 792: Web-based Education, 2013