Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Gysi Tobias"'
Autor:
Vasilache, Nicolas, Zinenko, Oleksandr, Bik, Aart J. C., Ravishankar, Mahesh, Raoux, Thomas, Belyaev, Alexander, Springer, Matthias, Gysi, Tobias, Caballero, Diego, Herhut, Stephan, Laurenzo, Stella, Cohen, Albert
Despite significant investment in software infrastructure, machine learning systems, runtimes and compilers do not compose properly. We propose a new design aiming at providing unprecedented degrees of modularity, composability and genericity. This p
Externí odkaz:
http://arxiv.org/abs/2202.03293
Autor:
Gysi, Tobias, Müller, Christoph, Zinenko, Oleksandr, Herhut, Stephan, Davis, Eddie, Wicky, Tobias, Fuhrer, Oliver, Hoefler, Torsten, Grosser, Tobias
Traditional compilers operate on a single generic intermediate representation (IR). These IRs are usually low-level and close to machine instructions. As a result, optimizations relying on domain-specific information are either not possible or requir
Externí odkaz:
http://arxiv.org/abs/2005.13014
While the cost of computation is an easy to understand local property, the cost of data movement on cached architectures depends on global state, does not compose, and is hard to predict. As a result, programmers often fail to consider the cost of da
Externí odkaz:
http://arxiv.org/abs/2001.01653
Autor:
Aditya, Konduri, Gysi, Tobias, Kwasniewski, Grzegorz, Hoefler, Torsten, Donzis, Diego A., Chen, Jacqueline H.
Synchronization overheads pose a major challenge as applications advance towards extreme scales. In current large-scale algorithms, synchronization as well as data communication delay the parallel computations at each time step in a time-dependent pa
Externí odkaz:
http://arxiv.org/abs/1911.05769
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Brice Goglin, James C. Sexton, Thomas C. Schulthess, Adrian Tate, Peter Messmer, Emmanuel Jeannot, Hatem Ltaief, Maciej Besta, Amir Kamil, David Padua, Satoshi Matsuoka, Vitus J. Leung, Armin Groblinger, Anshu Dubey, Mark Abraham, Mauro Bianco, Torsten Hoefler, Romain Ciedat, Miquel Pericas, Naoya Maruyama, Leonidas Linardakis, Chris J. Newburn, Jesús Labarta, Kathryn M. O'Brien, John Shalf, Brad Chamberlain, Robert Ross, Gysi Tobias, Frank Hannig, Karl Fuerlinger, Paul H. J. Kelly, Didem Unat, Marie-Christine Sawley, Harold C. Edwards
Publikováno v:
[Research Report] PADAL Workshop 2014, April 28--29, Swiss National Supercomputing Center (CSCS), Lugano, Switzerland. 2014, pp.54
The goal of the workshop and this report is to identify common themes and standardize concepts for locality-preserving abstractions for exascale programming models. Current software tools are built on the premise that computing is the most expensive
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::64396d7cee8ddefc6212470e40e8e7c9
https://hal.inria.fr/hal-01083080
https://hal.inria.fr/hal-01083080
Autor:
Cumming, Ben, Fourestey, Gilles, Fuhrer, Oliver, Gysi, Tobias, Fatica, Massimiliano, Schulthess, Thomas C.
Publikováno v:
SC14: International Conference for High Performance Computing, Networking, Storage & Analysis; 2014, p819-829, 11p
Autor:
Gysi, Tobias, Müller, Christoph, Zinenko, Oleksandr, Herhut, Stephan, Davis, Eddie, Wicky, Tobias, Fuhrer, Oliver, Hoefler, Torsten, Grosser, Tobias
Most compilers have a single core intermediate representation (IR) (e.g., LLVM) sometimes complemented with vaguely defined IR-like data structures. This IR is commonly low-level and close to machine instructions. As a result, optimizations relying o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dd966a1f5aa697c633733211f5b29f06