Search Results

Documents authored by Kelly, Paul H. J.


Document
Tensor Computations: Applications and Optimization (Dagstuhl Seminar 22101)

Authors: Paolo Bientinesi, David Ham, Furong Huang, Paul H. J. Kelly, P. (Saday) Sadayappan, and Edward Stow

Published in: Dagstuhl Reports, Volume 12, Issue 3 (2022)


Abstract
This report documents the program and the outcomes of Dagstuhl Seminar 22101 "Tensor Computations: Applications and Optimization". Tensors are higher dimensional analogs of matrices, and represent a key data abstraction for many applications in computational science and data science. Widely used shared infrastructure exists for linear algebra, while, in contrast, for tensor computations, there is no consensus on standard building blocks. This Dagstuhl Seminar aimed to bring together users, and performance optimization specialists, to build such foundations. We present the abstracts of the 5 tutorials and 14 talks given. The working groups and their outcomes so far are then presented.

Cite as

Paolo Bientinesi, David Ham, Furong Huang, Paul H. J. Kelly, P. (Saday) Sadayappan, and Edward Stow. Tensor Computations: Applications and Optimization (Dagstuhl Seminar 22101). In Dagstuhl Reports, Volume 12, Issue 3, pp. 1-14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)


Copy BibTex To Clipboard

@Article{bientinesi_et_al:DagRep.12.3.1,
  author =	{Bientinesi, Paolo and Ham, David and Huang, Furong and Kelly, Paul H. J. and Sadayappan, P. (Saday) and Stow, Edward},
  title =	{{Tensor Computations: Applications and Optimization (Dagstuhl Seminar 22101)}},
  pages =	{1--14},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2022},
  volume =	{12},
  number =	{3},
  editor =	{Bientinesi, Paolo and Ham, David and Huang, Furong and Kelly, Paul H. J. and Sadayappan, P. (Saday) and Stow, Edward},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.12.3.1},
  URN =		{urn:nbn:de:0030-drops-172674},
  doi =		{10.4230/DagRep.12.3.1},
  annote =	{Keywords: Tensor, Optimisation, Linear Algebra, Compilers, Benchmark, Domain Specific Language}
}
Document
Tensor Computations: Applications and Optimization (Dagstuhl Seminar 20111)

Authors: Paolo Bientinesi, David Ham, Furong Huang, Paul H. J. Kelly, Christian Lengauer, and Saday Sadayappan

Published in: Dagstuhl Reports, Volume 10, Issue 3 (2020)


Abstract
Tensors are higher-dimensional analogs of matrices, and represent a key data abstraction for many applications in computational science and data science. In contrast to the wide availability on diverse hardware platforms of high-performance numerical libraries for matrix computations, only limited software infrastructure exists today for high-performance tensor computations. Recent research developments have resulted in the formulation of many machine learning algorithms in terms of tensor computations. Tensor computations have also emerged as fundamental building blocks for many algorithms in data science and computational science. Therefore, several concurrent efforts have targeted the development of libraries, frameworks, and domain-specific compilers to support the rising demand for high-performance tensor computations. However, there is currently very little coordination among the various groups of developers. Further, the groups developing high-performance libraries/frameworks for tensor computations are still rather disconnected from the research community that develops applications using tensors as a key data abstraction. The main goal of this Dagstuhl Seminar has been to bring together the following two communities: first researchers from disciplines developing applications centered around tensor computations, and second researchers developing software infrastructure for efficient tensor computation primitives. Invitees from the former group included experts in machine learning and data analytics, and computational scientists developing tensor-based applications. Invitees from the latter group spanned experts in compiler optimization and experts in numerical methods. A very fruitful exchange of ideas across these four research communities took place, with discussions on the variety of needs and use-cases for tensor computations and the challenges/opportunities in the development of high-performance software to satisfy those needs.

Cite as

Paolo Bientinesi, David Ham, Furong Huang, Paul H. J. Kelly, Christian Lengauer, and Saday Sadayappan. Tensor Computations: Applications and Optimization (Dagstuhl Seminar 20111). In Dagstuhl Reports, Volume 10, Issue 3, pp. 58-70, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2020)


Copy BibTex To Clipboard

@Article{bientinesi_et_al:DagRep.10.3.58,
  author =	{Bientinesi, Paolo and Ham, David and Huang, Furong and Kelly, Paul H. J. and Lengauer, Christian and Sadayappan, Saday},
  title =	{{Tensor Computations: Applications and Optimization (Dagstuhl Seminar 20111)}},
  pages =	{58--70},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2020},
  volume =	{10},
  number =	{3},
  editor =	{Bientinesi, Paolo and Ham, David and Huang, Furong and Kelly, Paul H. J. and Lengauer, Christian and Sadayappan, Saday},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.10.3.58},
  URN =		{urn:nbn:de:0030-drops-134303},
  doi =		{10.4230/DagRep.10.3.58},
  annote =	{Keywords: compilers, computational science, linear algebra, machine learning, numerical methods}
}
Document
Loop Optimization (Dagstuhl Seminar 18111)

Authors: Sebastian Hack, Paul H. J. Kelly, and Christian Lengauer

Published in: Dagstuhl Reports, Volume 8, Issue 3 (2018)


Abstract
This report documents the programme of Dagstuhl Seminar 18111 "Loop Optimization". The seminar brought together experts from three areas: (1) model-based loop optimization, chiefly, in the polyhedron model, (2) rewriting and program transformation, and (3) metaprogramming and symbolic evaluation. Its aim was to review the 20+ years of progress since the Dagstuhl Seminar 9616 "Loop Parallelization" in 1996 and identify the challenges that remain.

Cite as

Sebastian Hack, Paul H. J. Kelly, and Christian Lengauer. Loop Optimization (Dagstuhl Seminar 18111). In Dagstuhl Reports, Volume 8, Issue 3, pp. 39-59, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


Copy BibTex To Clipboard

@Article{hack_et_al:DagRep.8.3.39,
  author =	{Hack, Sebastian and Kelly, Paul H. J. and Lengauer, Christian},
  title =	{{Loop Optimization (Dagstuhl Seminar 18111)}},
  pages =	{39--59},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2018},
  volume =	{8},
  number =	{3},
  editor =	{Hack, Sebastian and Kelly, Paul H. J. and Lengauer, Christian},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.8.3.39},
  URN =		{urn:nbn:de:0030-drops-92960},
  doi =		{10.4230/DagRep.8.3.39},
  annote =	{Keywords: Autotuning, dependence analysis, just-in-time (JIT), loop parallelization, parallel programming, polyhedron model}
}
Document
Performance Portability in Extreme Scale Computing (Dagstuhl Seminar 17431)

Authors: Anshu Dubey, Paul H. J. Kelly, Bernd Mohr, and Jeffrey S. Vetter

Published in: Dagstuhl Reports, Volume 7, Issue 10 (2018)


Abstract
This Dagstuhl Seminar represented a unique opportunity to bring together international experts from the three research communities essential to tackling the HPC performance portability challenge: developers of large-scale computational science software projects, researchers developing parallel programming technologies, and performance specialists. The major research questions for the seminar were to understand challenges, design metrics, and prioritize potential solutions for performance portability, management of data movement in complex applications, composability, and pathways to impact on the research community. The overall conclusion shared by all participants was that performance portability in extreme scale computing can be achieved, especially if parallel applications are designed with performance portability in mind from the beginning. Making legacy application performance portable still requires enormous efforts and expertise. In many instances it will likely require extensive refactoring.

Cite as

Anshu Dubey, Paul H. J. Kelly, Bernd Mohr, and Jeffrey S. Vetter. Performance Portability in Extreme Scale Computing (Dagstuhl Seminar 17431). In Dagstuhl Reports, Volume 7, Issue 10, pp. 84-110, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2018)


Copy BibTex To Clipboard

@Article{dubey_et_al:DagRep.7.10.84,
  author =	{Dubey, Anshu and Kelly, Paul H. J. and Mohr, Bernd and Vetter, Jeffrey S.},
  title =	{{Performance Portability in Extreme Scale Computing (Dagstuhl Seminar 17431)}},
  pages =	{84--110},
  journal =	{Dagstuhl Reports},
  ISSN =	{2192-5283},
  year =	{2018},
  volume =	{7},
  number =	{10},
  editor =	{Dubey, Anshu and Kelly, Paul H. J. and Mohr, Bernd and Vetter, Jeffrey S.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DagRep.7.10.84},
  URN =		{urn:nbn:de:0030-drops-86642},
  doi =		{10.4230/DagRep.7.10.84},
  annote =	{Keywords: Parallel programming, performance portability, productivity, scientific computing}
}
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail