Content uploaded by Piotr Przymus
Author content
All content in this area was uploaded by Piotr Przymus on Aug 07, 2015
Content may be subject to copyright.
A preview of the PDF is not available
A Bi-objective Optimization Framework for Heterogeneous CPU/GPU Query Plans
Abstract and Figures
Graphics Processing Units (GPU) have significantly more applications than just rendering images. They are also used in general-purpose computing to solve problems that can benefit from massive parallel processing. However, there are tasks that either hardly suit GPU or fit GPU only partially. The latter class is the focus of this paper. We elaborate on hybrid CPU/GPU computation and build optimization methods that seek the equilibrium between these two computation platforms. The method is based on heuristic search for bi-objective Pareto optimal execution plans in presence of multiple concurrent queries. The underlying model mimics the commodity market where devices are producers and queries are consumers. The value of resources of computing devices is controlled by supply-and-demand laws. Our model of the optimization criteria allows finding solutions of problems not yet addressed in heterogeneous query processing. Furthermore, it also offers lower time complexity and higher accuracy than other methods.
Figures - uploaded by Piotr Przymus
Author content
All figure content in this area was uploaded by Piotr Przymus
Content may be subject to copyright.
The vast amount of processing power and memory bandwidth provided by modern graphics cards make them an interesting platform for data-intensive applications. Unsurprisingly, the database research community identified GPUs as effective co-processors for data processing several years ago. In the past years, there were many approaches to make use of GPUs at different levels of a database system. In this paper, we explore the design space of GPU-accelerated database management systems. Based on this survey, we present key properties, important trade-offs and typical challenges of GPU-aware database architectures, and identify major open challenges. Additionally, we survey existing GPU-accelerated DBMSs and classify their architectural properties. Then, we summarize typical optimizations implemented in GPU-accelerated DBMSs. Finally, we propose a reference architecture, indicating how GPU acceleration can be integrated in existing DBMSs.
Nowadays, we can observe increasing interest in processing and exploration of time series. Growing volumes of data and needs of efficient processing pushed research in new directions. This paper presents a lossless lightweight compression planner intended to be used in a time series database system. We propose a novel compression method which is ultra fast and tries to find the best possible compression ratio by composing several lightweight algorithms tuned dynamically for incoming data. The preliminary results are promising and open new horizons for data intensive monitoring and analytic systems.
Nowadays, we can observe increasing interest in processing and exploration of time series. Growing volumes of data and needs of efficient processing pushed research in new directions. GPU devices combined with fast compression and decompression algorithms open new horizons for data intensive systems. In this paper we present improved cascaded compression mechanism for time series databases build on Big Table–like solution. We achieved extremely fast compression methods with good compression ratio.
In recent years, an increased interest in processing and exploration of time-series has been observed. Due to the growing volumes of data, extensive studies have been conducted in order to find new and effective methods for storing and processing data. Research has been carried out in different directions, including hardware based solutions or NoSQL databases. We present a prototype query engine based on GPGPU and NoSQL database plus a new model of data storage using lightweight compression. Our solution improves the time series database performance in all aspects and after some modifications can be also extended to general-purpose databases in the future.
In many scientific and industrial applications GPGPU (General-Purpose Computing on Graphics Processing Units) programming reported excellent speed-up when compared to traditional CPU (central processing unit) based libraries. However, for data intensive applications this benefit may be much smaller or may completely disappear due to time consuming memory transfers. Up to now, gain from processing on the GPU was noticeable only for problems where data transfer could be compensated by calculations, which usually mean large data sets and complex computations. This paper evaluates a new method of data decompression directly in GPU shared memory which minimizes data transfers on the path from disk, through main memory, global GPU device memory, to GPU processor. The method is successfully applied to pattern matching problems. Results of experiments show considerable speed improvement for large and small data volumes which is a significant step forward in GPGPU computing.
In this paper, we demonstrate and discuss the economical results of applying a fixed, a dynamic and a stochastic approximation
based pricing policy in a free commodity market model designed for computational grids. We present the pricing policies and
our economy-driven scheduling heuristic as a part of our market model in which we assume resource owners desire to profit
or recover their costs, and users desire to execute their jobs within the limits of their budget and time. The comparison
experiments revealed that our dynamic pricing policy is more successful as a means for achieving social welfare in the market.
A survey of current continuous nonlinear multi-objective optimization (MOO) concepts and methods is presented. It consolidates and relates seemingly different terminology and methods. The methods are divided into three major categories: methods with a priori articulation of preferences, methods with a posteriori articulation of preferences, and methods with no articulation of preferences. Genetic algorithms are surveyed as well. Commentary is provided on three fronts, concerning the advantages and pitfalls of individual methods, the different classes of methods, and the field of MOO as a whole. The Characteristics of the most significant methods are summarized. Conclusions are drawn that reflect often-neglected ideas and applicability to engineering problems. It is found that no single approach is superior. Rather, the selection of a specific method depends on the type of information that is provided in the problem, the users preferences, the solution requirements, and the availability of software.
Current database research identified the computational power of GPUs as a way to increase the performance of database systems. Since GPU algorithms are not necessarily faster than their CPU counterparts, it is important to use the GPU only if it is beneficial for query processing. In a general database context, only few research projects address hybrid query processing, i.e., using a mix of CPU- and GPU-based processing to achieve optimal performance. In this paper, we extend our CPU/GPU scheduling framework to support hybrid query processing in database systems. We point out fundamental problems and provide an algorithm to create a hybrid query plan for a query using our scheduling framework.
Current database research identified the use of computational power of GPUs as a way to increase the performance of database systems. As GPU algorithms are not necessarily faster than their CPU counterparts, it is important to use the GPU only if it is beneficial for query processing. In a general database context, only few research projects address hybrid query processing, i.e., using a mix of CPU- and GPU-based processing to achieve optimal performance. In this paper, we extend our CPU/GPU scheduling framework to support hybrid query processing in database systems. We point out fundamental problems and propose an algorithm to create a hybrid query plan for a query using our scheduling framework. Additionally, we provide cost metrics, accounting for the possible overlapping of data transfers and computation on the GPU. Furthermore, we present algorithms to create hybrid query plans for query sequences and query trees.
GPU acceleration is a promising approach to speed up query processing of database systems by using low cost graphic processors as coprocessors. Two major trends have emerged in this area: (1) The development of frameworks for scheduling tasks in heterogeneous CPU/GPU platforms, which is mainly in the context of coprocessing for applications and does not consider specifics of database-query processing and optimization. (2) The acceleration of database operations using efficient GPU algorithms, which typically cannot be applied easily on other database systems, because of their analytical-algorithm-specific cost models. One major challenge is how to combine traditional database query processing with GPU coprocessing techniques and efficient database operation scheduling in a GPU-aware query optimizer. In this thesis, we develop a hybrid query processing engine, which extends the traditional physical optimization process to generate hybrid query plans and to perform a cost-based optimization in a way that the advantages of CPUs and GPUs are combined. Furthermore, we aim at a portable solution between different GPU-accelerated database management systems to maximize applicability. Preliminary results indicate great potential.