Vectorized data processing on the cell broadband engine

Héman, Sándor; Nes, Niels; Żukowski, Marcin; Boncz, Peter

doi:10.1145/1363189.1363195

Cited by 32 publications

(16 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Qiao et al show how to batch a collection of aggregate operations running on a multicore machine so as to avoid cache thrashing [22]. Héman et al describe ways to use the vector processing capabilities of the Cell processor to improve the performance of the MonetDB/X100 system [17].…”

Section: Parallelism and Contentionmentioning

confidence: 99%

Automatic contention detection and amelioration for data-intensive operations

Cieslewicz

Ross

Satsumi

et al. 2010

Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data

View full text Add to dashboard Cite

To take full advantage of the parallelism offered by a multicore machine, one must write parallel code. Writing parallel code is difficult. Even when one writes correct code, there are numerous performance pitfalls. For example, an unrecognized data hotspot could mean that all threads effectively serialize their access to the hotspot, and throughput is dramatically reduced. Previous work has demonstrated that database operations suffer from such hotspots when naively implemented to run in parallel on a multi-core processor.In this paper, we aim to provide a generic framework for performing certain kinds of concurrent database operations in parallel. The formalism is similar to user-defined aggregates and Google's MapReduce in that users specify certain functions for parts of the computation that need to be performed over large volumes of data. We provide infrastructure that allows multiple threads on a multi-core machine to concurrently perform read and write operations on shared data structures, automatically mitigating hotspots and other performance hazards.Our goal is not to squeeze the last drop of performance out of a particular platform. Rather, we aim to provide a framework within which a programmer can, without detailed knowledge of concurrent and parallel programming, develop code that efficiently utilizes a multi-core machine.

show abstract

Section: Parallelism and Contentionmentioning

confidence: 99%

Automatic contention detection and amelioration for data-intensive operations

Cieslewicz

Ross

Satsumi

et al. 2010

Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data

View full text Add to dashboard Cite

show abstract

“…In the last few years, there has been growing interest in different non-conventional parallel processing architectures such as Graphics processors [11,14], cell broadband engine [10,15], etc. These processors were originally designed for different application domains, but recent results have shown promise in the use of these processors for data management operations.…”

Section: Discussionmentioning

confidence: 99%

Thread cooperation in multicore architectures for frequency counting over multiple data streams

et al. 2009

View full text Add to dashboard Cite

Many real-world data stream analysis applications such as network monitoring, click stream analysis, and others require combining multiple streams of data arriving from multiple sources. This is referred to as multi-stream analysis. To deal with high stream arrival rates, it is desirable that such systems be capable of supporting very high processing throughput. The advent of multicore processors and powerful servers driven by these processors calls for efficient parallel designs that can effectively utilize the parallelism of the multicores, since performance improvement is possible only through effective parallelism. In this paper, we address the problem of parallelizing multi-stream analysis in the context of multicore processors. Specifically, we concentrate on parallelizing frequent elements, top-k, and frequency counting over multiple streams. We discuss the challenges in designing an efficient parallel system for multi-stream processing. Our evaluation and analysis reveals that traditional "contention" based locking results in excessive overhead and wait, which in turn leads to severe performance degradation in modern multicore architectures. Based on our analysis, we propose a "cooperation" based locking paradigm for efficient parallelization of frequency counting. The proposed "cooperation" based paradigm removes waits associated with synchronization, and allows replacing locks by much cheaper atomic synchronization primitives. Our implementation of the proposed paradigm to parallelize a well known frequency counting algorithm shows the benefits of the proposed "cooperation" based locking paradigm when compared to the traditional "contention" based locking paradigm. In our experiments, the proposed "cooperation" based design outperforms the traditional "contention" based design by a factor of 2 − 5.5X for synthetic zipfian data sets.

show abstract

“…So far, this question has mostly been discussed in the context of data processing on specialized hardware, like graphics cards and FPGAs. The usual approach relies on using a separate set of hand-tuned hardware-conscious database operators for each supported device type [19,23,28]. The left side of Figure 1 illustrates this approach.…”

Section: The Need For Hardware Abstractionmentioning

confidence: 99%

“…Besides graphics cards, there is a plethora of work on data processing on other non-traditional architectures: The work of Mueller et al explained how to express database operations using the building blocks of FPGAs [28]. Gold et al analyzed data processing on network processors [15] and Heman et al addresses data processing on Cell processors [23].…”

Section: Related Workmentioning

confidence: 99%

Hardware-oblivious parallelism for in-memory column-stores

Heimel

Saecker²,

Pirk

et al. 2013

Proc. VLDB Endow.

View full text Add to dashboard Cite

The multi-core architectures of today's computer systems make parallelism a necessity for performance critical applications. Writing such applications in a generic, hardware-oblivious manner is a challenging problem: Current database systems thus rely on laborintensive and error-prone manual tuning to exploit the full potential of modern parallel hardware architectures like multi-core CPUs and graphics cards. We propose an alternative design for a parallel database engine, based on a single set of hardware-oblivious operators, which are compiled down to the actual hardware at runtime. This design reduces the development overhead for parallel database engines, while achieving competitive performance to hand-tuned systems.We provide a proof-of-concept for this design by integrating operators written using the parallel programming framework OpenCL into the open-source database MonetDB. Following this approach, we achieve efficient, yet highly portable parallel code without the need for optimization by hand. We evaluated our implementation against MonetDB using TPC-H derived queries and observed a performance that rivals that of MonetDB's query execution on the CPU and surpasses it on the GPU. In addition, we show that the same set of operators runs nearly unchanged on a GPU, demonstrating the feasibility of our approach.

show abstract

Vectorized data processing on the cell broadband engine

Cited by 32 publications

References 20 publications

Automatic contention detection and amelioration for data-intensive operations

Automatic contention detection and amelioration for data-intensive operations

Thread cooperation in multicore architectures for frequency counting over multiple data streams

Hardware-oblivious parallelism for in-memory column-stores

Contact Info

Product

Resources

About