The question of efficient dynamic allocation of compute-node resources, such as cores, by independent libraries or runtime systems can be an nightmare. Scientists writing application components have no way to efficiently specify and compose resource-hungry components. As application software stacks become deeper and the interaction of multiple runtime layers compete for resources from the operating system, it has become clear that intelligent cooperation is needed. Resources such as compute cores, in-package memory, and even electrical power must be orchestrated dynamically across application components, with the ability to query each other and respond appropriately. A more integrated solution would reduce intra-application resource competition and improve performance. Furthermore, application runtime systems could request and allocate specific hardware assets and adjust runtime tuning parameters up and down the software stack.
The goal of this workshop is to gather and share the latest scholarly research from the community working on these issues, at all levels of the HPC software stack. This include thread allocation, resource arbitration and management, containers, and so on, from runtime-system designers to compilers. We will also use panel sessions and keynote talks to discuss these issues, share visions, and present solutions.
For this workshop we welcome original work, presenting state of practice and state of the art and covering different aspects of resource arbitration, thread placement, and resource management at the system level for parallel applications on multicore systems. We will also welcome surveys, position papers or standardization proposal. The workshop will cover the following topics :
- Topology abstractions;
- Cache partitioning;
- Energy management;
- Thread management across software components;
- Memory allocation and partitioning;
- Hierarchical and heterogeneous memory;
- Communication progression;
- Containers for improved resource management;
- Software defined networking;
- Cross-layer optimization;
- High-level abstractions to partition resources;
- Runtime system/language/library interaction;
- Parallel programming model coordination;
- Library cooperation;
- Resource conflicts between application components;
- Resource interference in the context of single workloads.
- Emmanuel Jeannot, Inria
- Pete Beckman, Argonne Ntl Lab
- Swann Perarnau, Argonne Ntl Lab
- Dorian Arnold, Emory University.
- Denis Barthou, Bordeaux INP.
- Siegfried Benkner, University of Vienna.
- George Bosilca, Univ Of Tennessee.
- James H Cownie, Intel.
- Carter Edwards, Nvidia.
- Hal Finkel, Argonne Ntl Lab.
- Karl Fuerlinger, LMU, München.
- Balazs Gerofi, U. Tokyo – Riken.
- Brice Goglin, Inria.
- Raymond Namyst, Univ. Of Bordeaux.
- Stephen Olivier, Sandia Ntl Lab.
- Tapasya Patki, Lawrence Livermore Ntl Lab.
- Marc Perache, CEA.
- Swann Perarnau, Argonne Ntl Lab.
- Rolf Riesen, Intel.
- Sameer Shende, U. of Oregon.
- Christian Terboven, RTW Aachen.
How to submit
Papers, in PDF format should be submitted through the easychair web site here. Paper must be formatted the same way as IPDPS papers : submitted manuscripts may not exceed ten (10) single-spaced double-column pages using 10-point size font on 8.5×11 inch pages (IEEE conference style), including figures, tables, and references. The IEEE conference template that can be found here.
Submission deadline: February 1st February 11th, 2019
Author Notification: March 8th, 2019
Workshop Date: Friday May 24, 2019
Camera ready: March 15th, 2019