[petsc-dev] exascale applications and PETSc usefulness

[Oxberry, Geoffrey Malcolm]

That description reads like stochastic programming, of which there have been multiple papers recently on adaptive (e.g., in Trilinos/ROL) or parallel algorithms. Having that capability would probably support some work MCS is already doing. Mihai’s published papers in this area, for instance. If TAO were to do something in this area, it would be compelling.

> On Sep 26, 2016, at 4:13 PM, Barry Smith <bsmith at mcs.anl.gov> wrote:
> 
> 
>   Yeah I read the extended abstract for that project. It is completely unclear to me what they will do.
> 
>  Barry
> 
>> On Sep 26, 2016, at 5:12 PM, Richard Mills <richardtmills at gmail.com> wrote:
>> 
>> Hi Barry,
>> 
>> I'm pretty late responding to the thread, but in early 2015 I attended one of the initial DOE workshops where they were discussing a wind power modeling initiative.  I recall that Jed also attended--perhaps he can comment further.  There was a lot of talk about very ambitious multi-scale modeling of wind farms (ranging from detailed modeling of turbine blades all the way up to modeling entire wind farms, perhaps coupling with regional weather/climate models), as well as a lot of talk about optimization for wind farm design, site selection, etc.  The workshop was at the "throw all of your ideas out there" phase, so I'm sure that things were eventually reduced in scope quite a bit, but there are probably several possible applications for PETSc and TAO in whatever ended up going into the Steve Hammond exascale application proposal.
>> 
>> --Richard
>> 
>> On Wed, Sep 7, 2016 at 1:59 PM, Barry Smith <bsmith at mcs.anl.gov> wrote:
>> 
>>    The list of exascale applications funded has been publicly released: http://insidehpc.com/2016/09/the-exascale-computing-project-ecp-announces-39-8-million-in-first-round-application-development-awards/
>> 
>>   I've pasted the ones below that "may" need or utilize capabilities provided by PETSc:
>> 
>>        • Exascale Modeling of Advanced Particle Accelerators, Jean-Luc Vay (LBNL) with LLNL, SLAC
>>        • An Exascale Subsurface Simulator of Coupled Flow, Transport, Reactions and Mechanics, Carl Steefel (LBNL) with LLNL, NETL
>>        • Exascale Predictive Wind Plant Flow Physics Modeling, Steve Hammond (NREL) with SNL, ORNL, University of Texas Austin
>>        • QMCPACK: A Framework for Predictive and Systematically Improvable Quantum‐Mechanics Based Simulations of Materials, Paul Kent (ORNL) with ANL, LLNL, SNL, Stone Ridge Technology, Intel, Nvidia
>>        • Coupled Monte Carlo Neutronics and Fluid Flow Simulation of Small Modular Reactors, Thomas Evans (ORNL, PI) with ANL, INL, MIT
>>        • Transforming Additive Manufacturing through Exascale Simulation (TrAMEx), John Turner (ORNL) with LLNL, LANL, NIST
>>        • NWChemEx: Tackling Chemical, Materials and Biomolecular Challenges in the Exascale Era, T. H. Dunning, Jr. (PNNL), with Ames, ANL, BNL, LBNL, ORNL, PNNL, Virginia Tech
>>        • High-Fidelity Whole Device Modeling of Magnetically Confined Fusion Plasma, Amitava Bhattacharjee (PPPL) with ANL, ORNL, LLNL, Rutgers, UCLA, University of Colorado
>>        • Data Analytics at the Exascale for Free Electron Lasers, Amedeo Perazzo (SLAC) with LANL, LBNL, Stanford
>>        • Transforming Combustion Science and Technology with Exascale Simulations, Jackie Chen (SNL) with LBNL, NREL, ORNL, University of Connecticut
>>        • Cloud-Resolving Climate Modeling of the Earth’s Water Cycle, Mark Taylor (SNL) with ANL, LANL, LLNL, ORNL, PNNL, UCI, CSU
>> 
>> Based on the names alone it is hard to say for some of them. If anyone has useful information on the needs/approaches of these projects please let us know so we can determine if there any place for PETSc.
>> 
>>   Thanks
>> 
>>    Barry
>> 
>> 
>> 
>