| 8:45-9:00 |
Opening remarks |
||
| 9:00-10:00 |
What Parallel HLLs Need [Talk]
Keynote Speaker: Laxmikant Kale University of Illinois, Urbana-Champaign http://charm.cs.illinois.edu Abstract: Higher levels of abstractions that increase productivity can be designed by specializing them in specific ways. Domain-specific languages, interaction pattern specific languages, APGAS languages, or high-level frameworks leverage their own specializations to raise abstraction levels and increase productivity. In this talk, I will present some common support that all such higher level abstractions need, and the need to encapsulate that support in a single common substrate. In particular, the support includes automatic resource management, and other runtime adaptation support, including that for tolerating component failures or handling power/energy issues. Further, I will explore the need to interoperate and coordinate across multiple such paradigms, so that one can construct multi-paradigm applications with ease. I will illustrate the talk with my group's experience in designing multiple interaction-pattern-specific HLLs, and on interoperability among them as well with traditional message-passing paradigm of MPI. |
| 10:30-11:00 |
Atanas Atanasov, Hans-Joachim Bungartz, Kristof Unterweger, Tobias Weinzierl and Roland Wittmann. "A Case Study on Multi-Component Multi-Cluster Interaction with an AMR Solver" [Talk] |
||
| 11:00-11:30 |
Raul Torres, Leonidas Linardakis, Julian Kunkel and Thomas Ludwig. "ICON DSL: A Domain Specific Language for Climate Modeling" [Talk] |
||
| 11:30-12:00 |
Didem Unat, Cy Chan, Weiqun Zhang, John Bell and John Shalf. "Tiling as a Durable Abstraction for Parallelism and Data Locality" [Talk] |
| 1:30-2:30pm |
Adjusting to Exascale Computing — Do DSLs Stand a Chance?
[Talk] Keynote Speaker: Patrick McCormick Los Alamos National Laboratory Abstract: The current MPI+Fortran ecosystem has sustained HPC application software development for the past decade, but was architected for coarse-grained concurrency and bulk-synchronous algorithms. The trends in computer architecture have turned the model for achieving good performance upside-down, and will require rethinking algorithms and our entire programming environment. There are already promising avenues of exploration underway to mitigate these effects. Future hardware constraints on bandwidth and memory capacity, together with exponential growth in explicit on-chip parallelism will likely require a mass migration to new algorithms and software architecture that is as broad and disruptive as the migration from vector to parallel computing systems that occurred 15 years ago. The challenge is to efficiently express massive concurrency, parallelism, and hierarchical data locality without subjecting the programmer to overwhelming complexity. This talk will give a glimpse of DOE's program to overcome these obstacles and discuss the challenges we face in making domain-specific languages a successful part of the solution. |
||
| 2:30-3:00 |
Tan Nguyen and Scott Baden. "Preliminary Scaling Results on Multiple Hybrid Nodes of Knights Corner and Sandy Bridge Processors" [Talk] |
| 3:30-4:00 |
Matthew Le, Kevin Williams and Eric Van Wyk. "A Composable Domain Specific Language Extension for Spatio-Temporal Data Mining" |
||
| 4:00-4:30 |
Songqing Yue and Jeff Gray. "OpenFortran: Extending Fortran with Meta-programming" |
||
| 4:30-4:45 |
Closing Remarks |