Difference between revisions of "Projects"

(Current Projects)
 
(194 intermediate revisions by 3 users not shown)
Line 1: Line 1:
<div id="main">
+
__NOTOC__
 +
= Current Projects =
  
<div id="header">
+
<div id = "tablecontent">
 +
<div id = "row">
  
 +
<div id = "left">
 +
[[Image:sim.jpg|left|185x150px|link=]]
 +
 +
==== Intel Parallel Computing Center ====
 +
 +
The Intel PCC at SDSC for Earthquake Simulation is an interdisciplinary research center with the goal of modernizing SCEC’s highly scalable 3D earthquake modeling environment, called AWP-ODC. The modernizations will leverage the latest multi-core Intel Xeon processors and many-core, self-hosted, next-generation Intel Xeon Phi processors architecture.
 +
[http://www.sdsc.edu/News%20Items/PR20160209_earthquake_center.html More info]
 
</div>
 
</div>
<div id="menu">
 
  
* [[Main Page|Home]]
+
<div id = "right">
* [[Projects|Projects]]
+
[[Image:fault-tolerance.jpg|left|185x150px|link=]]
* [[Software|Software]]
+
 
* [[Personnel|Personnel]]
+
==== Fault Tolerance Project ====
* [[Publications|Publications]]
 
* [[News|News]]
 
* [[Contact|Contact]]
 
  
 +
Current checkpoint/restart approach may introduce an unacceptable amount of overhead into some file systems. In collaboration with CSM, we are developing a fault tolerance framework in which the survival application processes will adapt itself to failures. In collaborating with ORNL, we are integrating ADIOS to scale checkpointing up on Lustre file system. [http://www.olcf.ornl.gov/center-projects/adios/ More info]
 
</div>
 
</div>
  
<div id="page_body" style="min-height: 350px&gt;  &lt;h1&gt;Projects&lt;/h1&gt;  &lt;div id=">
+
</div>
 +
<div id = "row">
  
== Current Projects ==
+
<div id = "left">
 +
[[Image:shmovcaltech.jpg|left|185x150px|link=]]
  
{| class="personnel_tbl"
+
==== Supercomputing On Demand: SDSC Supports Event-Driven Science ====
| width="448" valign="top" |
 
[[Image:CFM.jpg|160px|left]]
 
  
==== Simulating Earthquake Faults (FESD) ====
+
HPGeoC supports on-demand CalTech users for urgent science earthquake applications. National Science Foundation (NSF) XSEDE supercomputing resource Trestles is allocated to open this new computing paradigm. We've developed novel ways of utilizing this type of allocation as well as scheduling and job handling procedures. [http://shakemovie.caltech.edu/ More info]
 +
</div>
  
HPGeoC Researchers are assisting researchers from six other universities and the US Geological Survey (USGS) to develop detailed, large-scale computer simulations of earthquake faults under a new $4.6 million National Science Foundation (NSF) grant announced September 2011. The initial focus is on the North Americn plate boundary and the San Andreas system of Northern and Southern California.<br />
+
<div id = "right">
[http://www.sdsc.edu/News%20Items/PR092311_earthquake.html/ More info &gt;]
+
[[Image:p7.jpg|left|185x150px|link=]]
| width="448" valign="top" |
 
| width="448" valign="top" |
 
[[Image:10hz.jpg|160px|left]]
 
  
==== GPU Acceleration Project ====
+
==== Blue Waters PAID  ====
  
HPGeoC has developed a hybrid CUDA MPI paradigm with AWP-ODC code that achieved 2.3 Pflop/s sustained performance and enabled a rough fault 0-10Hz modeling simulation on ORNL Titan. This code is also used to study the effects of nonlinearity on surface waves during large quakes on the San Anderas fault. <br />[https://www.olcf.ornl.gov/2013/12/16/titan-simulates-earthquake-physics-necessary-for-safer-building-design/ More info &gt;]
+
Supported by NSF Petascale Application Improvement Discovery (PAID) program through NCSA, this project will tune the SCEC community code AWP-ODC on Blue Waters for performance efficiency on Kepler. Our research will investigate how earthquake ruptures produce high frequency ground motions. High frequency ground motions are known to have an important impact on seismic hazards. Existing HPC systems cannot achieve the physical scale range needed to explore the source of high frequencies. [http://www.ncsa.illinois.edu/News/Stories/big_one/ More info]
|-
+
</div>
| width="448" valign="top" |
 
[[Image:shmovcaltech.jpg|140px]]
 
  
==== Supercomputing On Demand: SDSC Supports Event-Driven Science ====
+
</div>
 +
<div id = "row">
  
HPGeoC supports on-demand CalTech users for urgent science earthquake applications. National Science Foundation (NSF) XSEDE supercomputing resource Trestles is allocated to open this new computing paradigm. We've developed novel ways of utilizing this type of allocation as well as scheduling and job handling procedures.<br />[http://shakemovie.caltech.edu/ More info &gt;]
+
<div id = "left">
| width="448" valign="top" |
+
[[Image:CS.jpg|left|185x150px|link=]]
[[Image:petashake.jpg|185px]]
 
  
==== Petascale Inference in Earthquake System Science (PetaShake-2) ====
+
==== CyberShake SGT Calculation ====
  
This is a SCEC project with cross-disciplinary, multi-institutional CME Collaboration. We are providing a platform-independent petascale earthquake application that is able to enlist petascale computing to tackle PetaShake problems through a graduated series of milestone calculations.<br />[http://scec.usc.edu/research/cme/projects/petashake More info &gt;]
+
AWP-ODC is a highly scalable, parallel finite-difference application developed at SDSC and SDSU to simulate dynamic rupture and wave propagation that occurs during an earthquake. We have developed strain Green's tensor (SGT) creation and seismogram synthesis. The GPU-based SGT calculations resulted in 6.5x speedup on XK7 compared to XE6, this improved computational efficency in the waveform modeling of CyberShake research will save hundreds of millions of processor-core hours to create a California state-wide physics-based seismic hazard map. [http://scec.usc.edu/scecpedia/CyberShake More info]
|-
+
</div>
| width="448" valign="top" |
 
[[Image:petasha-3.jpg|185px]]
 
  
==== Petascale Cyberfacility for Physics-based Seismic Hazard Analysis (PetaSHA-3) ====
+
<div id = "right">
 +
[[Image:Viz3.jpg|left|185x150px|link=]]
  
The SCEC PetaSHA-3 project is sponsored by NSF to provide society with better predictions of earthquake hazards. This project will provide the high- performance computing required to achieve the objectives for earthquake source physics and ground motion prediction outlined in the SCEC3 (2007-2012) research plan.<br />[http://scec.usc.edu/research/cme/projects/petasha-3 More info &gt;]
+
==== SCEC Data Visualization ====
| width="448" valign="top" |
 
[[Image:m8.jpg|185px]]
 
  
==== SCEC M8 Simulation ====
+
This project focuses on the visualization of a series of large earthquake simulations in the interest of gaining scientific insight into the impact of Southern San Andreas Fault earthquake scenarios on Southern California. In addition to creating its own software, the group also uses tools installed and maintained on SDSC computational resources. [http://visservices.sdsc.edu/projects/scec/ More info]
 +
</div>
  
M8 is the largest earthquake simulation ever conducted, a collaborative effort led by SCEC and requiring collaboration of more than 30 seismologists and computational scientists, supported by DOE INCITE allocation award. It presented tremendous computational and I/O challenges. The simulation was conducted on NCCS Jaguar, a ACM Gordon Bell finalist at Supercomputing'10. <br />[http://www.sdsc.edu/News%20Items/PR081910_m8_earthqua.html More info&gt;]
+
</div>
|-
+
<div id = "row">
| width="448" valign="top" |
 
[[Image:p7.jpg|185px]]
 
  
==== Blue Waters Project ====
+
<div id = "left">
 +
[[Image:CFM.jpg|left|185x150px|link=]]
  
This is part of NSF PRAC award. On Blue Waters, our research will investigate how earthquake ruptures produce high frequency ground motions.  High frequency ground motions are known to have an important impact on seismic hazards. Existing HPC systems cannot achieve the physical scale range needed to explore the source of high frequencies.<br />[http://www.ncsa.illinois.edu/News/Stories/big_one/ More info &gt;]
+
==== Simulating Earthquake Faults (FESD) ====
| width="448" valign="top" |
 
[[Image:fault-tolerance.jpg|185px]]
 
  
==== Fault Tolerance Project ====
+
HPGeoC Researchers are assisting researchers from six other universities and the US Geological Survey (USGS) to develop detailed, large-scale computer simulations of earthquake faults under a new $4.6 million National Science Foundation (NSF) grant announced September 2011. The initial focus is on the North American plate boundary and the San Andreas system of Northern and Southern California.
 +
[http://www.sdsc.edu/News%20Items/PR092311_earthquake.html More info]
 +
</div>
  
Current checkpoint/restart approach may introduce an unacceptable amount of overhead into some file systems. In collaboration with CSM, we are developing a fault tolerance framework in which the survival application processes will adapt itself to failures. In collaborating with ORNL, we are integrating ADIOS to scale checkpointing up on Lustre file system. <br />[http://www.olcf.ornl.gov/center-projects/adios/ More info &gt;]
+
<div id = "right">
|-
+
[[Image:plasticity.jpg|left|185x150px|link=]]
| width="448" valign="top" |
 
[[Image:plasticity.jpg|185px]]
 
  
 
==== San Andreas Fault Zone Plasticity ====
 
==== San Andreas Fault Zone Plasticity ====
  
Producing realistic seismograms at high frequencies will require several improvements in anelastic wave propagation engines, including the implementation of nonlinear material behavior. This project supports the development of nonlinear material behavior in both the CPU- and GPU-based wave propagation solvers. Simulations of the ShakeOut earthquake scenario have shown that nonlinearity could reduce the earlier predictions of long period (0 - 0.5 Hz) ground motions in the Los Angeles basin by 30-70. <br />[http://onlinelibrary.wiley.com/doi/10.1002/2014GL059411/abstract/ More info &gt;]
+
Producing realistic seismograms at high frequencies will require several improvements in anelastic wave propagation engines, including the implementation of nonlinear material behavior. This project supports the development of nonlinear material behavior in both the CPU- and GPU-based wave propagation solvers. Simulations of the ShakeOut earthquake scenario have shown that nonlinearity could reduce the earlier predictions of long period (0 - 0.5 Hz) ground motions in the Los Angeles basin by 30-70. [http://onlinelibrary.wiley.com/doi/10.1002/2014GL059411/abstract/ More info]
| width="448" valign="top" |
+
</div>
[[Image:CS.jpg|120px]]
 
  
==== CyberShake SGT Calculation ====
+
</div>
 +
</div>
 +
 
 +
= Recent Completions =
 +
 
 +
<div id = "tablecontent">
 +
<div id = "row">
 +
 
 +
<div id = "left">
 +
[[Image:m8.jpg|left|185x150px|link=]]
 +
 
 +
==== SCEC M8 Simulation ====
 +
 
 +
M8 is the largest earthquake simulation ever conducted, a collaborative effort led by SCEC and requiring collaboration of more than 30 seismologists and computational scientists, supported by DOE INCITE allocation award. It presented tremendous computational and I/O challenges. The simulation was conducted on NCCS Jaguar, a ACM Gordon Bell finalist at Supercomputing'10. [http://www.sdsc.edu/News%20Items/PR081910_m8_earthqua.html More info]
 +
</div>
 +
 
 +
<div id = "right">
 +
[[Image:10hz.jpg|left|185x150px|link=]]
 +
 
 +
==== GPU Acceleration Project ====
 +
 
 +
HPGeoC has developed a hybrid CUDA MPI paradigm with AWP-ODC code that achieved 2.3 Pflop/s sustained performance and enabled a rough fault 0-10Hz modeling simulation on ORNL Titan. This code is also used to study the effects of nonlinearity on surface waves during large quakes on the San Andreas fault. [https://www.olcf.ornl.gov/2013/12/16/titan-simulates-earthquake-physics-necessary-for-safer-building-design/ More info]
 +
</div>
 +
 
 +
</div>
 +
<div id = "row">
  
AWP-ODC is a highly scalable, parallel finite-difference application developed at SDSC and SDSU to simulate dynamic rupture and wave propagation that occurs during an earthquake. We have developed strain Green's tensor (SGT) creation and seismogram synthesis. The GPU-based SGT calculations resulted in 6.5x speedup on XK7 compared to XE6, this improved computational efficency in the waveform modeling of CyberShake research will save hundreds of millions of processor-core hours to create a California state-wide physics-based seismic hazard map. <br />[http://scec.usc.edu/scecpedia/CyberShake More info &gt;]
+
<div id = "left">
|-
+
[[Image:hecura-2.jpg|left|185x150px|link=]]
| width="448" valign="top" |
 
[[Image:hecura-2.jpg|185px]]
 
  
 
==== Topology-aware Communication and Scheduling (HECURA-2) ====
 
==== Topology-aware Communication and Scheduling (HECURA-2) ====
  
 
Topology-aware MPI communication, mapping, and scheduling is a new research area. This is to take advantage of the topological path to communication optimization  (either point-to-point or collective). We are participating in a joint project between OSU, TACC and SDSC as a case study in how to implement new topology-aware MPI software at the application level.
 
Topology-aware MPI communication, mapping, and scheduling is a new research area. This is to take advantage of the topological path to communication optimization  (either point-to-point or collective). We are participating in a joint project between OSU, TACC and SDSC as a case study in how to implement new topology-aware MPI software at the application level.
| width="448" valign="top" |
+
</div>
[[Image:Viz3.jpg|185px]]
+
 
 +
<div id = "right">
 +
[[Image:petashake.jpg|left|185x150px|link=]]
 +
 
 +
==== Petascale Inference in Earthquake System Science (PetaShake-2) ====
 +
 
 +
This is a SCEC project with cross-disciplinary, multi-institutional CME Collaboration. We are providing a platform-independent petascale earthquake application that is able to enlist petascale computing to tackle PetaShake problems through a graduated series of milestone calculations. [https://scec.usc.edu/scecpedia/PetaSHA2_Project More info]
 +
</div>
 +
 
 +
</div>
 +
<div id = "row">
 +
 
 +
<div id = "left">
 +
[[Image:petasha-3.jpg|left|185x150px|link=]]
  
==== SCEC Data Visualization ====
+
==== Petascale Cyberfacility for Physics-based Seismic Hazard Analysis (PetaSHA-3) ====
  
This project focuses on the visualization of a series of large earthquake simulations in the interest of gaining scientific insight into the impact of Southern San Andreas Fault earthquake scenarios on Southern California. In addition to creating its own software, the group also uses tools installed and maintained on SDSC computational resources.<br />[http://visservices.sdsc.edu/projects/scec/ More info &gt;]
+
The SCEC PetaSHA-3 project is sponsored by NSF to provide society with better predictions of earthquake hazards. This project will provide the high- performance computing required to achieve the objectives for earthquake source physics and ground motion prediction outlined in the SCEC3 (2007-2012) research plan. [https://scec.usc.edu/scecpedia/PetaSHA3_Project More info]
|}
+
</div>
  
== Recent Completions ==
+
</div>
 +
</div>
  
* [http://scec.usc.edu/research/cme/projects/petashake PetaShake-1] Advanced computational platform designed to support high-resolution simulations of large earthauakes on initial NSF petascale machines, supported by NSF OCI and GEO grant
+
= Finished Projects =
 +
 
 +
* [https://scec.usc.edu/scecpedia/PetaSHA1_Project PetaShake-1] Advanced computational platform designed to support high-resolution simulations of large earthquakes on initial NSF petascale machines, supported by NSF OCI and GEO grant
 
* <span style="color:#3366BB"> HECURA-1 </span> In collaboration with OSU and TACC, we developed non-blocking one-sided and two-sided communication and computation/communication overlap to improve the parallel efficiency of SCEC seismic applications.
 
* <span style="color:#3366BB"> HECURA-1 </span> In collaboration with OSU and TACC, we developed non-blocking one-sided and two-sided communication and computation/communication overlap to improve the parallel efficiency of SCEC seismic applications.
 
* [http://scec.usc.edu/research/cme/projects/petasha-2 PetaSHA-1/2]Cross-disciplinary, multi-institutional collaboration, coordinated by SCEC, each 2-year EAR/IF project with the same name to develop a cyberfacility with a common simulation framework for executing SHA computational pathways
 
* [http://scec.usc.edu/research/cme/projects/petasha-2 PetaSHA-1/2]Cross-disciplinary, multi-institutional collaboration, coordinated by SCEC, each 2-year EAR/IF project with the same name to develop a cyberfacility with a common simulation framework for executing SHA computational pathways
Line 111: Line 146:
 
* Parallelization of Regional Spectral Method (RSM)
 
* Parallelization of Regional Spectral Method (RSM)
  
== High Performance Computing Allocations ==
+
= High Performance Computing Allocations =
  
 
* [https://www.xsede.org/allocations NSF XSEDE XRAC Allocations]
 
* [https://www.xsede.org/allocations NSF XSEDE XRAC Allocations]
Line 118: Line 153:
 
* [http://www.alcf.anl.gov/programs/esp ANL Early Science Program Allocation]
 
* [http://www.alcf.anl.gov/programs/esp ANL Early Science Program Allocation]
  
== Sources of Funding ==
+
= Sources of Funding =
  
 
* [http://www.scec.org Southern California Earthquake Center (SCEC)]
 
* [http://www.scec.org Southern California Earthquake Center (SCEC)]
 
* [http://www.nsf.gov National Science Foundation (NSF)]
 
* [http://www.nsf.gov National Science Foundation (NSF)]
 
* [http://www.xsede.org XSEDE]
 
* [http://www.xsede.org XSEDE]
 
+
* [https://software.intel.com/en-us/ipcc Intel]
</div></div><div id="footer">[[Image:spacer.gif]]</div>
+
* [http://www.nvidia.com/content/global/global.php NVIDIA]
 +
* [http://www.wmkeck.org Keck Foundation]

Latest revision as of 13:25, 28 April 2016

Current Projects

Sim.jpg

Intel Parallel Computing Center

The Intel PCC at SDSC for Earthquake Simulation is an interdisciplinary research center with the goal of modernizing SCEC’s highly scalable 3D earthquake modeling environment, called AWP-ODC. The modernizations will leverage the latest multi-core Intel Xeon processors and many-core, self-hosted, next-generation Intel Xeon Phi processors architecture. More info

Shmovcaltech.jpg

Supercomputing On Demand: SDSC Supports Event-Driven Science

HPGeoC supports on-demand CalTech users for urgent science earthquake applications. National Science Foundation (NSF) XSEDE supercomputing resource Trestles is allocated to open this new computing paradigm. We've developed novel ways of utilizing this type of allocation as well as scheduling and job handling procedures. More info

CS.jpg

CyberShake SGT Calculation

AWP-ODC is a highly scalable, parallel finite-difference application developed at SDSC and SDSU to simulate dynamic rupture and wave propagation that occurs during an earthquake. We have developed strain Green's tensor (SGT) creation and seismogram synthesis. The GPU-based SGT calculations resulted in 6.5x speedup on XK7 compared to XE6, this improved computational efficency in the waveform modeling of CyberShake research will save hundreds of millions of processor-core hours to create a California state-wide physics-based seismic hazard map. More info

CFM.jpg

Simulating Earthquake Faults (FESD)

HPGeoC Researchers are assisting researchers from six other universities and the US Geological Survey (USGS) to develop detailed, large-scale computer simulations of earthquake faults under a new $4.6 million National Science Foundation (NSF) grant announced September 2011. The initial focus is on the North American plate boundary and the San Andreas system of Northern and Southern California. More info

Recent Completions

M8.jpg

SCEC M8 Simulation

M8 is the largest earthquake simulation ever conducted, a collaborative effort led by SCEC and requiring collaboration of more than 30 seismologists and computational scientists, supported by DOE INCITE allocation award. It presented tremendous computational and I/O challenges. The simulation was conducted on NCCS Jaguar, a ACM Gordon Bell finalist at Supercomputing'10. More info

Hecura-2.jpg

Topology-aware Communication and Scheduling (HECURA-2)

Topology-aware MPI communication, mapping, and scheduling is a new research area. This is to take advantage of the topological path to communication optimization  (either point-to-point or collective). We are participating in a joint project between OSU, TACC and SDSC as a case study in how to implement new topology-aware MPI software at the application level.

Petasha-3.jpg

Petascale Cyberfacility for Physics-based Seismic Hazard Analysis (PetaSHA-3)

The SCEC PetaSHA-3 project is sponsored by NSF to provide society with better predictions of earthquake hazards. This project will provide the high- performance computing required to achieve the objectives for earthquake source physics and ground motion prediction outlined in the SCEC3 (2007-2012) research plan. More info

Finished Projects

  • PetaShake-1 Advanced computational platform designed to support high-resolution simulations of large earthquakes on initial NSF petascale machines, supported by NSF OCI and GEO grant
  • HECURA-1 In collaboration with OSU and TACC, we developed non-blocking one-sided and two-sided communication and computation/communication overlap to improve the parallel efficiency of SCEC seismic applications.
  • PetaSHA-1/2Cross-disciplinary, multi-institutional collaboration, coordinated by SCEC, each 2-year EAR/IF project with the same name to develop a cyberfacility with a common simulation framework for executing SHA computational pathways
  • TeraShake The TeraShake Simulations model the rupture of a 230 kilometer stretch of the San Andreas fault and the consequent 7.7 magnitude earthquake. TeraShake wasa multi-institution collaboration led by SCEC/CME.
  • Shakeout The Great California Shakeout is a statewide earthquake drill. It is held in October each year and serves as preparation for what to do before, during, and after an earthquake.
  • Parallelization of Regional Spectral Method (RSM)

High Performance Computing Allocations

Sources of Funding