For applications, report available information that addresses the following points.

1. What is the application and its significance?
2. What equations are being solved, and what are the algorithms used to solve them?
3. What hardware does the application run on, and what levels of parallelism are employed typically?
   1. How well does the application scale?
   2. What are the bottlenecks or other limitations and how did the developers attempt to deal with them?
   3. Are there any outstanding performance bottlenecks or limitations that the code developers plan to address in the future?
4. What programming tools, libraries, or compilers were used?
5. Does the application produce large amounts of data? If so, are the management, access, and manipulation of the data considered a technical challenge?
6. Is the application still in use? Are there applications that solve the same problem? Is there any competition? Is the software a commercial product?

For development tools, your report should address the following points.

1. What is the tool and its significance?
2. What problem does it solve, and what is the theory of operation?
3. What hardware does the application run on, and what levels of parallelism are employed typically?
   1. How well does the tool scale, and what applications has it been used to develop?
   2. What are the tool's limitations and how did the developers attempt to deal with them? Were they successful?
   3. Are there any outstanding limitations that the code developers plan to address in the future?
4. How widely is the tool used?
5. Is the tool used to manage large amounts of data?
6. Is the tool still in use? Are there alternatives that solve the same problem? Is the tool a commercial product?

Submitting your assignment

Turn in hard copy in class, but post a URL in the Assignment # 1 Conference of the course web board pointing to your responses for part (2). (Part 1 will only be turned in to me). Your document should be in HTML, PDF, or text format.

Suggestions for places to look

Here are some applications

• NAMD, a parallel molecular dynamics code.
• http://www.cs.ucsd.edu/groups/hpcl/scg/mcellk
• www.qcmethod.com The Quasicontinuum (QC) method, a mixed continuum and atomistic approach for simulating the mechanical response of polycrystalline materials at zero temperature.
• SuperLU, a general purpose library for the direct solution of large, sparse, non-symmetric systems of linear equations on high performance machines.
• Parallel Structured Adaptive Mesh Refinement, esp HyperClaw
• SCEC Community Modeling Environment
• NWChem computational chemistry package.
• ENZO Cosmology code

Here are some tools

• Uniform Parallel C UPC. There are many implementations.
• The Titanium Programming Language
• CILK, a parallel programming language.
• Matlab*P
• Global Arrays
• CHOMBO adaptive mesh refinement infrastructure for implementing finite difference methods for the solution of partial differential equations on block-structured adaptively refined grids.
• BePOP project for software performance tuning.
• Performance Prediction (SDSC)
• Tuning and Analysis Utilities (TAU)
• Paradyn Parallel Performance Tools.
• Tau: Tuning and Analysis Utilities.
• KeLP, a parallel programming framework.
• Charm++, a parallel programming library and language.
• ParMETIS unstructured mesh partitioner.
• Totalview parallel debugger.
• Vampir/GuideView

Here are some web sites describing applications and tools

• Center for Applied Scientific Computing (turbulence studies)
• http://www.llnl.gov/CASC/projects.shtml
• http://www.emsl.pnl.gov/proj/
• http://seesar.lbl.gov/
• Theoretical and Computational Biophysics group (Beckman Institute)