Automatic parallelization via matrix multiplication

Sato, Shigeyuki; Iwasaki, Hideya

doi:10.1145/1993316.1993554

Cited by 20 publications

(32 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As sublists ↑ 7 ,+ 7 is a monoid homomorphism we can execute it in parallel, say using p processors, which leads to the run time O((log p + n p )w 2 ). This complexity resembles the run time of other parallel algorithms to solve the knapsack problem, e.g., one given by [SI11]. The standard sequential algorithm has run time O(nw ).…”

Section: Developing Intuitions By Examplementioning

confidence: 97%

See 1 more Smart Citation

Filter-embedding semiring fusion for programming with MapReduce

Emoto

Fischer

2012

Form. Asp. Comput.

View full text Add to dashboard Cite

We show that MapReduce, the de facto standard for large scale data-intensive parallel programming, can be equipped with a programming theory in calculational form. By integrating the generate-and-test programming paradigm and semirings for aggregation of results, we propose a novel parallel programming framework for MapReduce. The framework consists of two important calculation theorems: the shortcut fusion theorem of semiring homomorphisms bridges the gap between specifications and efficient implementations, and the filterembedding theorem helps to develop parallel programs in a systematic and incremental way.

show abstract

Section: Developing Intuitions By Examplementioning

confidence: 97%

“…This is in contrast to the specification which, when executed, would generate an intermediate result of size | S | 2n . Interestingly, the derived program is equivalent to a program obtained by parallelizing the Viterbi algorithm [He88,HC06] using matrix multiplication over a semiring [SI11].…”

Section: Finding a Most Likely Sequence Of Hidden Statesmentioning

confidence: 99%

Filter-embedding semiring fusion for programming with MapReduce

Emoto

Fischer

2012

Form. Asp. Comput.

View full text Add to dashboard Cite

show abstract

“…Their idea of parallelization was formalized as quantifier elimination and generalized to cover recursive functions by Morihata and Matsuzaki [16]. Sato and Iwasaki [18] presented a lightweight method based on Fisher et al's paper [9] that formalizes a given loop body as matrix multiplication over semiring after extracting maximum operators. Complicated loops of reduce and scan that these studies dealt with are not in the scope of our system.…”

Section: Related Workmentioning

confidence: 99%

“…Complicated loops of reduce and scan that these studies dealt with are not in the scope of our system. A parallelization strategy of extracting loops to be converted to skeletons, which we have adopted, has been presented [18]. In this sense, our contribution to this work is not on automatic parallelization techniques.…”

Section: Related Workmentioning

confidence: 99%

A Generator of Hadoop MapReduce Programs that Manipulate One-dimensional Arrays

Miyazaki

Matsuzaki

Sato

2017

Journal of Information Processing

Self Cite

View full text Add to dashboard Cite

MapReduce is a framework for large-scale data processing proposed by Google, and its open-source implementation, Hadoop MapReduce, is now widely used. Several language systems have been proposed to make developing MapReduce programs easier, for instance, Sawzall, FlumeJava, Pig, Hive, and Crunch. These language systems mainly target applications that can be naturally solved by using a MapReduce-like programming model. In this study, we propose a new MapReduce-program generator that accepts programs manipulating one-dimensional arrays. By using the proposed generator, users only need to write sequential programs to generate Hadoop MapReduce programs automatically. We applied some program optimization techniques to the generation of Hadoop MapReduce programs. In this paper, we also report our experiment results that compare programs generated by the proposed generator with hand-written MapReduce programs.

show abstract

“…Sato and Iwasaki [27] address the parallelization of complex reductions and scans. They transform the loop body into a matrix-multiplication form based on reduce and scan parallel primitives.…”

Section: Related Workmentioning

confidence: 99%

A novel compiler support for automatic parallelization on multicore systems

et al. 2013

View full text Add to dashboard Cite

The widespread use of multicore processors is not a consequence of significant advances in parallel programming.In contrast, multicore processors arise due to the complexity of building power-efficient, high-clock-rate, single-core chips. Automatic parallelization of sequential applications is the ideal solution for making parallel programming as easy as writing programs for sequential computers. However, automatic parallelization remains a grand challenge due to its need for complex program analysis and the existence of unknowns during compilation. This paper proposes a new method for converting a sequential application into a parallel counterpart that can be executed on current multicore processors. It hinges on an intermediate representation based on the concept of domain-independent kernel (e.g., assignment, reduction, recurrence). Such kernel-centric view hides the complexity of the implementation details, enabling the construction of the parallel version even when the source code of the sequential application contains different syntactic variations of the computations (e.g., pointers, arrays, complex control flows). Experiments that evaluate the effectiveness and performance of our approach with respect to state-of-the-art compilers are also presented. The benchmark suite consists of synthetic codes that represent common domain-independent kernels, dense/sparse linear algebra and image processing routines, and full-scale applications from SPEC CPU2000.

show abstract

Automatic parallelization via matrix multiplication

Cited by 20 publications

References 13 publications

Filter-embedding semiring fusion for programming with MapReduce

Filter-embedding semiring fusion for programming with MapReduce

A Generator of Hadoop MapReduce Programs that Manipulate One-dimensional Arrays

A novel compiler support for automatic parallelization on multicore systems

Contact Info

Product

Resources

About