Damaris: Addressing performance variability in data management for post-petascale simulations
- Argonne National Lab. (ANL), Argonne, IL (United States)
- Inria, Rennes - Bretagne Atlantique Research Centre (France)
- Univ. of Illinois at Urbana-Champaign, Urbana, IL (United States)
- Univ. of Wisconsin, Madison, WI (United States)
With exascale computing on the horizon, reducing performance variability in data management tasks (storage, visualization, analysis, etc.) is becoming a key challenge in sustaining high performance. Here, this variability significantly impacts the overall application performance at scale and its predictability over time. In this article, we present Damaris, a system that leverages dedicated cores in multicore nodes to offload data management tasks, including I/O, data compression, scheduling of data movements, in situ analysis, and visualization. We evaluate Damaris with the CM1 atmospheric simulation and the Nek5000 computational fluid dynamic simulation on four platforms, including NICS’s Kraken and NCSA’s Blue Waters. Our results show that (1) Damaris fully hides the I/O variability as well as all I/O-related costs, thus making simulation performance predictable; (2) it increases the sustained write throughput by a factor of up to 15 compared with standard I/O approaches; (3) it allows almost perfect scalability of the simulation up to over 9,000 cores, as opposed to state-of-the-art approaches that fail to scale; and (4) it enables a seamless connection to the VisIt visualization software to perform in situ analysis and visualization in a way that impacts neither the performance of the simulation nor its variability. In addition, we extended our implementation of Damaris to also support the use of dedicated nodes and conducted a thorough comparison of the two approaches—dedicated cores and dedicated nodes—for I/O tasks with the aforementioned applications.
- Research Organization:
- Argonne National Laboratory (ANL), Argonne, IL (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), Basic Energy Sciences (BES); Central Michigan University; National Center for Atmospheric Research
- Grant/Contract Number:
- AC02-06CH11357
- OSTI ID:
- 1346736
- Journal Information:
- ACM Transactions on Parallel Computing, Vol. 3, Issue 3; ISSN 2329-4949
- Publisher:
- Association for Computing MachineryCopyright Statement
- Country of Publication:
- United States
- Language:
- English
Understanding the causes of performance variability in HPC workloads
|
conference | January 2005 |
Parallel I/O performance: From events to ensembles
|
conference | April 2010 |
A Flexible Framework for Asynchronous in Situ and in Transit Analytics for Scientific Simulations
|
conference | May 2014 |
High end scientific codes with computational I/O pipelines: improving their end-to-end performance
|
conference | January 2011 |
Scalable I/O forwarding framework for high-performance computing systems
|
conference | August 2009 |
Flexible IO and integration for scientific codes through the adaptable IO system (ADIOS)
|
conference | January 2008 |
On implementing MPI-IO portably and with high performance
|
conference | January 1999 |
Electronic poster: co-visualization of full data and in situ data extracts from unstructured grid cfd at 160k cores
|
conference | January 2011 |
Design and Evaluation of Multiple-Level Data Staging for Blue Gene Systems
|
journal | June 2011 |
Enabling high-speed asynchronous data extraction and transfer using DART
|
journal | January 2010 |
Scaling parallel I/O performance through I/O delegate and caching system
|
conference | November 2008 |
On the role of burst buffers in leadership-class storage systems
|
conference | April 2012 |
A Steering Environment for Online Parallel Visualization of Legacy Parallel Simulations
|
conference | October 2006 |
An Adaptive Framework for Simulation and Online Remote Visualization of Critical Climate Applications in Resource-constrained Environments
|
conference | November 2010 |
pClock: an arrival curve based approach for QoS guarantees in shared storage systems
|
conference | January 2007 |
Design, Modeling, and Evaluation of a Scalable Multi-level Checkpointing System
|
conference | November 2010 |
MPI-IO/GPFS, an optimized implementation of MPI-IO on top of GPFS
|
conference | January 2001 |
QoS support for end users of I/O-intensive applications using shared storage systems
|
conference | January 2011 |
Examples of in transit visualization
|
conference | January 2011 |
ExaViz: a flexible framework to analyse, steer and interact with molecular dynamics simulations
|
journal | January 2014 |
Scalable parallel building blocks for custom data analysis
|
conference | October 2011 |
CALCioM: Mitigating I/O Interference in HPC Systems through Cross-Application Coordination
|
conference | May 2014 |
The ParaView Coprocessing Library: A scalable, general purpose in situ visualization library
|
conference | October 2011 |
Scalable systems software---From mesh generation to scientific visualization: an end-to-end approach to parallel supercomputing
|
conference | January 2006 |
A Benchmark Simulation for Moist Nonhydrostatic Numerical Models
|
journal | December 2002 |
Functional Partitioning to Optimize End-to-End Performance on Many-core Architectures
|
conference | November 2010 |
Interactive simulation and visualization
|
journal | January 1999 |
In-situ processing and visualization for ultrascale simulations
|
journal | July 2007 |
Damaris: How to Efficiently Leverage Multicore Parallelism to Achieve Scalable, Jitter-free I/O
|
conference | September 2012 |
Visualizing with VTK: a tutorial
|
journal | January 2000 |
Enabling In-situ Execution of Coupled Scientific Workflow on Multi-core Platform
|
conference | May 2012 |
DataStager: scalable data staging services for petascale applications
|
conference | January 2009 |
In-situ I/O processing: a case for location flexibility
|
conference | January 2011 |
Managing Variability in the IO Performance of Petascale Storage Systems
|
conference | November 2010 |
High-level buffering for hiding periodic output cost in scientific simulations
|
journal | March 2006 |
Provisioning a Multi-tiered Data Staging Area for Extreme-Scale Machines
|
conference | June 2011 |
Data sieving and collective I/O in ROMIO
|
conference | January 1999 |
PreDatA – preparatory data analytics on peta-scale machines
|
conference | April 2010 |
I/O threads to reduce checkpoint blocking for an electromagnetics solver on Blue Gene/P and Cray XK6
|
conference | January 2012 |
In-situ Feature-Based Objects Tracking for Large-Scale Scientific Simulations
|
conference | November 2012 |
Extreme Scaling of Production Visualization Software on Diverse Architectures
|
journal | May 2010 |
Comparative evaluation of overlap strategies with study of I/O overlap in MPI-IO
|
journal | October 2008 |
A study of I/O methods for parallel visualization of large-scale data
|
journal | February 2005 |
In Situ Visualization at Extreme Scale: Challenges and Opportunities
|
journal | November 2009 |
In Situ Visualization for Large-Scale Combustion Simulations
|
journal | May 2010 |
Understanding Performance Interference of I/O Workload in Virtualized Cloud Environments
|
conference | July 2010 |
Concurrent Visualization in a Production Supercomputing Environment
|
journal | September 2006 |
Scheduling the I/O of HPC Applications Under Congestion
|
conference | May 2015 |
CoSS: proposing a contract-based storage system for HPC
|
conference | January 2017 |
Similar Records
Active Flash: Performance-Energy Tradeoffs for Out-of-Core Processing on Non-Volatile Memory Devices
Distributed Data-Flow for In-Situ Visualization and Analysis at Petascale