SCIENTIFIC COMPUTING AND VISUALIZATION (Fall 12)
Course Number: CSCI 596
Class Number: 30280D
Instructor:
Aiichiro Nakano;
office: VHE 610; phone: (213) 821-2657; email: anakano@usc.edu
Lecture: 3:30-4:50pm M W, ZHS 163
Office Hours: 3:30-4:50pm F
Prerequisites: Basic knowledge of programming, data structures,
linear algebra, and calculus.
Textbooks:
W. D. Gropp, E. Lusk, and A. Skjellum, "Using MPI, 2nd Ed."
(MIT Press, 1999)--recommended
M. Woo, et al., "OpenGL Programming Guide, Version 3.0 and 3.1, 7th Ed."
(Addison-Wesley, 2009)--recommended
A. Grama, A. Gupta, G. Karypis, and V. Kumar, "Introduction to Parallel Computing, 2nd Ed."
(Addison-Wesley, 2003)--recommended
Course Description
Particle and continuum simulations are used as a vehicle to learn basic elements of high
performance scientific computing and visualization. Students will obtain
hands-on experience in: 1) formulating a mathematical model to describe a physical
phenomenon; 2) discretizing the model, which often consists of continuous differential
or integral equations, into algebraic forms in order to allow numerical solution on
computers; 3) designing/analyzing numerical algorithms to solve the algebraic equations
efficiently on parallel computers; 4) translating the algorithms into a program;
5) performing a computer experiment by executing the program;
6) visualizing simulation data in an immersive and interactive virtual environment;
and 7) managing/mining large datasets.
Visualization of 209 million-atom simulation of hypervelocity impact on
a high-strength ceramic plate on a tiled display.
Syllabus
- Basic molecular dynamics (MD) algorithms
- Integration of ordinary differential equations; periodic boundary
condition; linked-list cells
- Parallel MD
- Spatial decomposition (interprocessor caching and migration);
load balancing; scalability analysis; asynchronous MD
- Message passing interface (MPI) vs. shared memory (OpenMP) programming
- Hybrid MPI+OpenMP programming
- Build-it-yourself PC cluster
- Multicore parallel programming (e.g., GPU-CUDA, Cell)
- Grid/cloud scientific computing
- Computation steering on the Grid/cloud--integrated parallel computing, data
storage, and visualization resources via high-speed networks
(e.g., Globus, Grid RPC, MapReduce)
- Grid/cloud enabling parallel applications
- Scientific visualization
- OpenGL programming
- Virtual environment programming--CAVE Library, ImmersaDesk, tiled display
- Scientific data management/mining
- Data compression for scalable I/O
- Graph-based knowledge discovery
- Object-oriented scientific programming
- Parallel software tools for irregular data structures;
object-oriented MD; scripting wrappers
- Other simulation methods
- Stochastic simulations: Monte Carlo method
- Continuum simulations: Schrodinger equation in quantum mechanics
Announcements
- 8/27/12 (M): The class begins.
- 8/31/12 (F): Please register for the course by this date to obtain a computer account needed for assignments.
- 9/10/12 (M): See the topics at the workshop on
Machine Learning in Atomistic Simulations (Sep. 10-12, 2012, Lugano, Switzerland).
- 9/12/12 (W): See GPU Technology Conference: GTC 2013
(Mar. 18-21, 2013, San Jose, CA); also
Efficient molecular dynamics on heterogeneous architectures in GROMACS by B. Hess and S. Pall at GTC2012.
- 9/17/12 (M): See CUDA Fortran compiler.
- 9/17/12 (M): Seminar by Prof. Uwe Bergman (SLAC-Stanford) on
"Science at LCLS - A First Summary".
- 9/19/12 (W): Your HPC account is now ready, and your directory has been created under /home/rcf-proj/csci596.
- 9/21/12 (F): Discussion session for assignment 1 at 3:30pm in VHE 610.
- 9/28/12 (F): Discussion session for assignment 2 at 4:00pm in VHE 610.
- 10/3/11 (W): HPCC tour, please be at the entrance of 3434 Grand building at 3:40 pm sharp;
see access to 3434 Grand.
Also, do not forget to bring your student ID;
photo 1; photo 2.
- 10/12/12 (F): Discussion session for assignment 3 at 4:30pm in VHE 610.
- 10/19/12 (F): Discussion session for assignment 4 at 3:30pm in VHE 610.
- 11/2/12 (F): Discussion session for assignment 5 at 3:30pm in VHE 610.
- 11/13/12 (T): Discussion session for assignment 6 at 5:00pm in VHE 610.
- 11/19/12 (M): CACS Viz Lab tour.
- 12/5/12 (W): Final poster presentation, 3:30-4:50 pm in MHP 101, refreshments will be served;
see posters from last year's class;
please prepare a poster using
the Powerpoint template (24" by 36"),
print it to a PDF file, and email the PDF file to frntdesk@usc.edu
with the subject line: Poster Printing for CSCI 596, so that the Computer Science Department
can print its hard copy (you need to allow 5 business days for printing by the CS Department).
Lecture Notes
- Introduction;
slides
- Basic molecular dynamics algorithm;
linked-list cell MD algorithm;
slides
- Message Passing Interface;
slides
- Parallel computation of Pi
- Parallel MD algorithm;
introduction;
slides;
Shaw's NT algorithm
- OpenMP
- Hybrid MPI+OpenMP parallel MD
- Visualizing molecular dynamics;
slides
- CUDA
- Pair distribution computation with CUDA;
see also B. G. Levine, et al.,
J. Comput. Phys. 230, 3556 ('11)
- Grid computing
- MapReduce
- Virtual-reality programming
- Massive data visualization, see also:
A. Sharma, et al.,
Presence 12, 85 ('03);
C. Zhang, et al.,
Comput. Phys. Commun. 175, 339 ('06)
- Optimizing molecular dynamics
- Advanced topics in parallel molecular dynamics
- Metascalable divide-and-conquer algorithmic framework
- Miscellaneous lectures
- MSCS-HPCS program: Master of Science in Computer Science
with specialization in High Performance Computing and Simulations; see also
MSCS-HPCS information
- Debugging a MPI program
- Installing OpenGL and GLUT; see also
how to use OpenGL and GLUT with Microsoft Visual Studio
- Lecture note by Prof. James Demmel (UC Berkeley) on
memory hierarchies and processor features, case study: tuning matrix multiply
- See J. Mellor-Crummey, et al.,
Int'l J. Parallel Prog. 29, 217 ('01);
B. Moon, et al.,
IEEE Trans. Knowledge Data Eng. 13, 124 ('01);
M. Frigo, et al., in
Proc. of 40th Symp. on Foundation of Computer Science (FOCS) (IEEE, '99)
Assignments
- 1: Message Passing Interface (due Wednesday, Sep. 26);
see also a book chapter on "hypercube algorithms"
by Ian Foster (Argonne National Laboratory/Univercity of Chicago)
- 2: Parallel computation of Pi (due Wednesday, Oct. 3)
- 3: Parallel molecular dynamics (due Monday, Oct. 15)
- 4: Hybrid MPI+OpenMP parallel molecular dynamics
(due Wednesday, Oct. 24)
- 5: Animating molecular dynamics (due Monday, Nov. 5);
for parallel visualization of MD data mentioned in assignment 5, see:
A. Sharma, et al.,
Presence 12, 85 ('03);
C. Zhang, et al.,
Int'l J. Comput. Sci. 1, 407 ('07);
for tensor-field visualization, see:
L. Hesselink, et al.,
IEEE Computer Graphics & Applications 14, 76 ('93),
W. Ribarsky, et al.,
IEEE Computer 27(7), 57 ('94),
A. Sigfridsson, et al.,
IEEE Visualization 2002, (IEEE, 2002) p. 371
- 6: Pair distribution computation with CUDA (due Wednesday, Nov. 14)
- Final project (poster presentation on Wednesday, Dec. 5);
Powerpoint poster template (24" by 36");
sample posters
Source Codes
- Sequential MD program: md.c, md.h, md.in
- Linked-list cell MD program: lmd.c, lmd.h, lmd.in
- MPI basics: mpi_simple.c, mpi_comm.c, irecv_comm.c, mpi_simple_sample.pbs
- Parallel MD program: pmd.c, pmd.h, pmd.in
- OpenMP basics: omp_example.c, omp_example_set.c, omp_pi_critical.c, omp_pi.c
- Hybrid MPI+OpenMP: hpi.c
- Visualizing MD simulation: atomv.c, atomv.h, md.conf
- CUDA basics: pi.cu, pdf0.c, pos.d
- Quantum dynamics: qd.c, qd.h, qd.in; qd1.c, qd1.h, qd1.in
Useful Links
- Message Passing Interface (MPI)
- OpenMP
- OpenGL
- CUDA
- Parallel Computing
- Network/Grid/Cloud Scientific Computing
- Virtual Reality/Visualization
- CAVE programming
at Electronic Visualization Laboratory at University of Illinois at Chicago
- IEEE Virtual Reality Conference
- ACM SIGGRAPH Conference
- IEEE VisWeek
- VMD:
Visual Molecular Dynamics at University of Illinois at Urbana-Champaign
-
Atomsviewer: A scalable molecular visualization code
- VisIT visualization tool
at Lawrence Livermore National Laboratory
- ParaView parallel visualization application
at Los Alamos National Laboratory
- VISTA scalable volume renderer
at Sandiego Supercomputing Center
- Scientific Object Oriented Programming
- Linux Cluster
- Network/Interconnect
- Supercomputing & Information Technology for Science & Engineering
- Computational Science
- Numerical Methods
