Compute Pairwise Manhattan Distance and Pearson Correlation Coefficient of Data Points with GPU

Chang, Dar-Jen; Desoky, A.; Ouyang, Mingxing; Rouchka, Eric C.

doi:10.1109/snpd.2009.34

Cited by 56 publications

(26 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All-pairs computations occur in a variety of applications, ranging from pairwise Manhattan distance computations in bioinformatics [6] to N-Body simulations in physics [4]. These applications follow a common computation scheme: for two sets of entities, the same computation is performed for all pairs of entities from the first set combined with entities from the second set.…”

Section: Patterns Of Parallelism (Skeletons)mentioning

confidence: 99%

See 1 more Smart Citation

Towards High-Level Programming for Systems with Many Cores

Gorlatch

Steuwer

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Application development for modern high-performance systems with many cores, i.e., comprising multiple Graphics Processing Units (GPUs) and multi-core CPUs, currently exploits low-level programming approaches like CUDA and OpenCL, which leads to complex, lengthy and error-prone programs. In this paper, we advocate a high-level programming approach for such systems, which relies on the following two main principles: a) the model is based on the current OpenCL standard, such that programs remain portable across various many-core systems, independently of the vendor, and all low-level code optimizations can be applied; b) the model extends OpenCL with three high-level features which simplify many-core programming and are automatically translated by the system into OpenCL code. The high-level features of our programming model are as follows: 1) memory management is simplified and automated using parallel container data types (vectors and matrices); 2) a data (re)distribution mechanism supports data partitioning and generates automatic data movements between multiple GPUs; 3) computations are precisely and concisely expressed using parallel algorithmic patterns (skeletons). The well-defined skeletons allow for semantics-preserving transformations of SkelCL programs which can be applied in the process of program development, as well as in the compilation and optimization phase. We demonstrate how our programming model and its implementation are used to express several parallel applications, and we report first experimental results on evaluating our approach in terms of program size and target performance.

show abstract

Section: Patterns Of Parallelism (Skeletons)mentioning

confidence: 99%

“…In [6], the so-called Pairwise Manhattan Distance (PMD) is studied as a fundamental operation in hierarchical clustering for data analysis. PMD is obtained by computing the Manhattan distance for every pair of rows of a given matrix.…”

Section: Patterns Of Parallelism (Skeletons)mentioning

confidence: 99%

Towards High-Level Programming for Systems with Many Cores

Gorlatch

Steuwer

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…In [3], the so-called Pairwise Manhattan Distance (PMD) is studied as a fundamental operation in hierarchical clustering for data analysis. PMD is obtained by computing the Manhattan distance for every pair of rows of a given matrix.…”

Section: The Allpairs Skeleton and Its Implementationmentioning

confidence: 99%

“…In this paper, we aim at allpairs computations which occur in a variety of applications, ranging from matrix multiplication and pairwise Manhattan distance computations in bioinformatics [3] to N-Body simulations in physics [2]. These applications share a common computational pattern: for two sets of entities, the same computation is performed independently for all pairs in which entities from the first set are combined with entities from the second set.…”

Section: Introductionmentioning

confidence: 99%

“…These applications share a common computational pattern: for two sets of entities, the same computation is performed independently for all pairs in which entities from the first set are combined with entities from the second set. Previous work discussed specific allpairs applications and their parallel implementations on multi-core CPUs [2], the Cell processor [18], and GPUs [3,16]; it demonstrated that developing well-performing implementations for allpairs is challenging, especially on GPU systems, as it requires exploiting their complex memory hierarchy and assumes a deep knowledge of the target hardware architecture.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Introducing and Implementing the Allpairs Skeleton for Programming Multi-GPU Systems

Steuwer

Friese

Albers

et al. 2013

Int J Parallel Prog

View full text Add to dashboard Cite

Algorithmic skeletons simplify software development: they abstract typical patterns of parallelism and provide their efficient implementations, allowing the application developer to focus on the structure of algorithms, rather than on implementation details. This becomes especially important for modern parallel systems with multiple Graphics Processing Units (GPUs) whose programming is complex and error-prone, because state-of-the-art programming approaches like CUDA and OpenCL lack high-level abstractions.We define a new algorithmic skeleton for allpairs computations which occur in real-world applications, ranging from bioinformatics to physics. We develop the skeleton's generic parallel implementation for multi-GPU Systems in OpenCL. To enable the automatic use of the fast GPU memory, we identify and implement an optimized version of the allpairs skeleton with a customizing function that follows a certain memory access pattern.We use matrix multiplication as an application study for the allpairs skeleton and its two implementations and demonstrate that the skeleton greatly simplifies programming, saving up to 90% of lines of code as compared to OpenCL. The performance of our optimized implementation is up to 6.8 times higher as compared with the generic implementation and is competitive to the performance of a manually written optimized OpenCL code.

show abstract