IN CONSTRUCTION
This event is supported by INRIA, UIUC, NCSA, ANL, as well as by EDF
Main Topics |
Schedule |
Speaker |
Affiliation |
Type of presentation |
Title (tentative) |
Download |
|
|
|
|
|
|
|
Workshop Day 1 |
Wednesday June 13th |
|
|
|
|
|
|
|
|
|
|
TITLES ARE TEMPORARY (except if in bold font) |
|
Registration |
08:00 |
|
|
|
|
|
Welcome and Introduction |
08:30 |
Marc Snir + Franck Cappello |
INRIA&UIUC |
Background |
Welcome, Workshop objectives and organization |
|
|
08:45 |
Bertrand Braunschweig |
INRIA |
Background |
Welcome to INRIA Rennes |
|
|
09:00 |
Thierry Priol |
INRIA |
Background |
HPC @ INRIA (update) |
|
Sustained Petascale |
09:15 |
Bill Kramer |
NCSA |
Background |
Blue Waters UPDATE and performance metrics. |
|
|
09:45 |
Torsten Hoefler |
NCSA |
Background |
Blue Waters Applications and Scalability/Performance Challenges and performance modeling |
|
|
10:15 |
Break |
|
|
|
|
|
10:45 |
Romain Dolbeau |
INRIA |
Background |
Programming Heterogeneous Many-cores Using Directives |
|
|
11:15 |
Marc Snir |
ANL |
Background |
BlueGene Q: First impression |
|
|
11:45 |
Robert Ross |
ANL |
Background |
BIG DATA |
|
|
12:15 |
Lunch |
|
|
|
|
Mini Workshop1 |
|
|
|
|
|
|
Fault tolerance |
13:30 |
Sanjay Kale and Marc Snir |
UIUC, ANL |
Background |
Fault tolerance needs at NCSA and ANL |
|
|
14:00 |
Ana Gainaru |
NCSA |
Joint Result |
High precision fault prediction for Blue Waters |
|
|
14:30 |
Amina Guermouche |
INRIA |
Joint Result |
TBD |
|
|
15:00 |
Break |
|
|
|
|
|
15:30 |
Mehdi Diouri |
INRIA |
Joint Results |
Fault tolerance and energy consumption |
|
|
16:00 |
Tatiana |
INRIA |
in progress |
TBD |
|
|
16:30 |
Sanjay Kale |
UIUC |
Result |
TBD. |
|
|
17:00 |
Discussions |
|
|
How to address Petascale fault tolerance needs |
|
|
18:00 |
Adjourn |
|
|
|
|
Mini Workshop2 |
|
|
|
|
|
|
I/O and BigData |
13:30 |
Bill Kramer and Rob Ross |
UIUC, ANL |
Background |
I/O and BIGDATA needs at NCSA and ANL |
|
|
14:00 |
Gabriel Antoniu |
INRIA |
Joint Result |
TBD |
|
|
14:30 |
Matthieu Dorier |
INRIA |
Joint Result |
In-Situ Interactive Visualization of HPC Simulations with Damaris |
|
|
15:00 |
Break |
|
|
|
|
|
15:30 |
Dries Kimpe |
ANL |
Background |
Fault tolerance and energy consumption |
|
|
16:00 |
--- |
--- |
--- |
TBD |
|
|
16:30 |
--- |
--- |
--- |
|
|
|
17:00 |
Discussions |
|
|
How to address Petascale I/O and Big Data needs |
|
|
18:00 |
Adjourn |
|
|
|
|
|
|
|
|
|
|
|
Workshop Day 2 |
Thursday June 14th |
|
|
|
|
|
|
|
|
|
|
|
|
Math for HPC |
08:30 |
Frederic Vivien |
INRIA |
Joint Result |
A Unified... |
|
|
09:00 |
Paul Hovland |
ANL |
Background |
TBD. |
|
|
09:30 |
Laurent Hascoet |
INRIA |
Joint Results |
Gradient of MPI-parallel codes |
|
|
10:00 |
Break |
|
|
|
|
Programming languages |
10:30 |
Rajeev Thakur |
ANL |
Background |
TBD. |
|
|
11:00 |
Sanjay Kale |
UIUC |
Background |
TBD. |
|
|
11:30 |
--- |
--- |
--- |
-- |
|
|
12:00 |
Lunch |
|
|
|
|
|
|
|
|
|
|
|
Mini Workshop3 |
|
|
|
|
|
|
Numerical libraries |
13:30 |
Paul Hovland and Bill Gropp |
UIUC, ANL |
Background |
Numerical libraries needs at NCSA and ANL |
|
|
14:00 |
Laura Grigori |
INRIA |
Joint Result |
TBD |
|
|
14:30 |
François Pelegrini |
INRIA |
Joint Result |
TBD |
|
|
15:00 |
Break |
|
|
|
|
|
15:30 |
Jocelyne Erhel |
INRIA |
Background |
TBD |
|
|
16:00 |
Daisuke Takahashi |
U. Tsukuba |
Joint Result |
TBD |
|
|
16:30 |
--- |
--- |
--- |
|
|
|
17:00 |
Discussions |
|
|
How to address Petascale Numerical Libraries needs |
|
|
18:00 |
Adjourn |
|
|
|
|
|
|
|
|
|
|
|
Mini Workshop4 |
|
|
|
|
|
|
Programing Models |
13:30 |
Rajeev Thakur and Sanjay Kale |
UIUC, ANL |
Background |
Programming model needs at NCSA and ANL |
|
|
14:00 |
Jean-François Mehaut |
INRIA |
Joint Result |
TBD |
|
|
14:30 |
Brice Goglin |
INRIA |
Background |
Bringing hardware affinity information into MPI communication strategies |
|
|
15:00 |
Break |
|
|
|
|
|
15:30 |
Thomas Ropars |
EPFL |
Background |
TBD |
|
|
16:00 |
Alexandre Duchateau |
INRIA |
Joint Result |
Global operation optimizations on Multicore. |
|
|
16:30 |
--- |
--- |
--- |
TBD |
|
|
17:00 |
Discussions |
|
|
How to address Petascale programing model needs |
|
|
18:00 |
Adjourn |
|
|
|
|
|
|
|
|
|
|
|
|
19:00 |
Banquet |
|
|
@ Saint Malot |
|
|
|
|
|
|
|
|
Workshop Day 3 |
Friday June 15th |
|
|
|
|
|
|
|
|
|
|
|
|
Mini Workshop5 |
|
|
|
|
|
|
Mapping and Scheduling |
08:30 |
BIll Kramer and Marc Snir |
UIUC, ANL |
Background |
Mapping and Scheduling needs at NCSA and ANL |
|
|
09:00 |
François Teyssier |
INRIA |
Joint Result |
TBD |
|
|
09:30 |
François Pellegrini |
INRIA |
Background |
TBD |
|
|
10:00 |
Torsten Hoefler |
NCSA --> ETH |
Background |
On-node and off-node Topology Mapping for Petascale Computers |
|
|
10:30 |
Joseph Emeras (Olivier Richard) |
INRIA |
Background |
TBD |
|
|
11:00 |
Discussions |
|
|
How to address Petascale Mapping and Scheduling needs |
|
Mini Workshop6 |
|
|
|
|
|
|
HPC/Cloud |
08:30 |
Kate Keahey (main speaker) |
ANL, INRIA |
Background |
HPC Cloud |
|
|
09:00 |
Gabriel Antoniu |
INRIA |
Joint Result |
TBD |
|
|
09:30 |
Frederic Desprez |
INRIA |
Background |
TBD |
|
|
10:00 |
Bogdan Nicolae |
INRIA |
Joint Results |
TBD |
|
|
10:30 |
Derrick Kondo |
INRIA |
Result |
Characterization and Prediction of Host Load in a Google Data Center |
|
|
11:00 |
Discussions |
|
|
How to address HPC Cloud needs |
|
|
|
|
|
|
|
|
|
12:00 |
Franck Cappello and Marc Snir |
|
|
Discussion and Closing |
|
|
|
|
|
|
|
|
|
12:30 |
Lunch |
|
|
|
|
Abstracts
Romain Dolbeau: Programming Heterogeneous Many-cores Using Directives
Pushed by the pace of innovation in the GPU and more generally the many-core technology, the processor landscape is moving at high-speed. This fast evolution makes software development more complex. Furthermore, the impact of the programming style on future performance and portability of the application is difficult to forecast. The use of directives to annotate serial languages (e.g. C/C++/Fortran) looks very promising. They abstract low-level parallelism implementation details while preserving code assets from the evolution of processor architectures. In this presentation, we describe how to use HMPP (Heterogeneous Many-core Parallel Programming) as well as OpenACC directives to program heterogeneous compute nodes. In particular, we provide insights on how GPU / CPU can be exploited in a unified manner and how code tuning issues can be minimized. We extend the discussion to the use of libraries that is currently one of the key elements when addressing GPU and many-cores.
Laurent Hascoet: Gradient of MPI-parallel codes
Automatic Differentiation (AD) is the primary means of obtaining analytic derivatives from a numerical model given as a computer program. Therefore, it is an essential productivity tool in numerous computational science and engineering domains. Computing gradients with the adjoint mode of AD via source transformation is a particularly beneficial but also challenging use of AD. To date only ad hoc solutions for adjoint differentiation of MPI programs have been available, forcing AD users to reason about parallel communication dataflow and dependencies and manually develop adjoint communication code. In this collaboration between Argonne, RWTH Aachen, and INRIA, we characterize the principal problems of adjoining the most frequently used communication idioms. We propose solutions to cover these idioms and consider the consequences for the MPI implementation, the MPI user and MPI-aware program analysis.
Matthieu Dorier: In-Situ Interactive Visualization of HPC Simulations with Damaris
The I/O bottlenecks already present on current petascale systems force to consider new approaches to get insights from running simulations. Trying to bypass storage or drastically reducing the amount of data generated will be of outmost importance for the scales to come and, in particular, for Blue Waters.
This presentation will focus on the specific case of in-situ data analysis collocated with the simulation’s code and running on the same resources. We will first present some common visualization and analysis tools, and show the limitations of their in-situ capabilities. We then present how we enriched the Damaris I/O middleware to support analysis and visualization operations. We show that the use of Damaris on top of existing visualization packages allows us to (1) reduce code instrumentation to a minimum in existing simulations, (2) gather the capabilities of several visualization tools to offer adaptability under a unified data management interface, (3) use dedicated cores to hide the run time impact of in-situ visualization and (4) efficiently use memory through an allocation-based communication model.
Torsten Hoefler: On-node and off-node Topology Mapping for Petascale Computers
Network topology and the efficient mapping from tasks to physical processing elements is an increasing problem as we march towards larger systems. The last generation of Petascale class systems which comes right before a major switch to optical interconnects is highly affected due to their large low-bisection Torus networks. We will explore opportunities to improve communication performance by avoiding network congestion with automated task remapping. We discuss how we combine different approaches, various well-known heuristics, a heuristic based in RCM, INRIA's SCOTCH, and INRIA's tree-map algorithms for achieving highest mapping performance for on-node as well as off-node mappings. We also investigate a theoretical possibility to reduce energy usage due to minimizing dilation of the mapping. This whole work is done in the context of MPI and can readily be adapted to real production applications.
Derrick Kondo: Characterization and Prediction of Host Load in a Google Data Center
[Joint work with Sheng Di, Walfredo Cirne]
Characterization and prediction of system load is essential for optimizing its performance. We characterize and predict host load in a real-world production Google data center, using a detailed trace of over 25 million tasks across over 12,500 hosts. In our characterization, we present valuable statistics and distributions of machine’s maximum load, queue state and relative usage levels. Compared to traditional load from Grids and other HPC systems, we ?nd that Google host load exhibits higher variance due to the high frequency of small tasks. Based on this characterization, we develop and evaluate different methods of machine load prediction using techniques such as autoregression, moving averages, probabilistic methods, and noise ?lters. We ?nd that a linear weighted moving average produces accurate predictions with a 80%-95% success rate, outperforming other methods by 5%-20%. Surprisingly, this method outperforms more sophisticated hybrid prediction methods, which are effective for traditional Grid loads but not data center loads due to its more frequent and severe ?uctuations.
Brice Goglin: Bringing hardware affinity information into MPI communication strategies
Understanding the hardware topology and adapting the software accordingly is increasingly difficult. Resource numbering is not portable across machines or operating systems. There are many levels of memory hierarchy. And the access to I/O and memory resource is not flat anymore. We will summarize the work that we put in the Hardware Locality software to provide applications with a portable and easy-to-use abstraction of hardware details. This deep knowledge of hardware affinities let us optimize MPI communication strategies within nodes or between nodes, for both point-to-point and collective operations. We now look at adding quantitative information to the existing qualitative hierarchy description to improve our locality-based criterias.
Kate Keahey: HPC Cloud
Infrastructure clouds created ideal conditions for users to outsource their infrastructure needs beyond the boundaries of their institution. A typical infrastructure cloud offers (1) on-demand, short-term access, which allows users to flexibly manage peaks in demand, (2) pay-as-you-go model, which helps save costs for bursty usage patterns (i.e., helps manage “valleys” in demand), (3) access via virtualization technologies which provides a safe and cost-effective way for users to manage and customize their own environments, and (4) sheer convenience, as users and institutions no longer have to have specialized IT departments and can focus on their core mission instead. The flexibility of this approach allows users to also outsource as much or as little of their infrastructure procurement as their needs justify: they can keep a resident amount of infrastructure in-house while outsourcing only at times of increased demand, and they can outsource to a variety of providers choosing the best service levels for the price the market has to offer.
The availability of cloud computing gave rise to an interesting debate on its relationship to high performance computing (HPC). Two significant questions emerged in this context: (1) Can supercomputing workloads be run on a cloud? and (2) Can a supercomputer operate as a cloud? Much investigation has been done on the first issue, most notably and conclusively as part of the Magellan project. The second question, which could provide an interesting solution to challenges defined by the first, has not been investigated nearly as much. This talk will present a state-of-art summary of work in this space, discuss the current open challenges, propose relevant solutions in the area of resource management, as well as outline potential future directions and collaborations.