This is the second of two assessed coursework exercises, both based on
``FullDiagOdd'' computational chemistry application.
You may work in groups of two or three if you wish, but your report must
include an explicit statement of who did what.
Submit your work electronically via CATE.
Copy the source code directory tree to your own directory:
cp -r /homes/awb01/Teaching/ACA06/FullDiagOdd ./
Now compile the program:
Now you can run the program:
This reads input from the file 5a.dat, and
writes its output to screen.
You have been provided with a selection of input files of various
sizes: the short-running ones are for use with simulators; for serious
runs on real hardware use the longer-running examples like ``11a.dat!''.
Basically, your job is to figure out how to run
this program as fast as you possibly can,
and to write a brief report explaining how you did it.
- You can choose any hardware platform you wish.
You are encouraged to find interesting and diverse
machines to experiment with. The goal is high
performance on your chosen platform
so it is OK to choose an interesting machine
even if it's not the fastest available.
On linux type ``cat /proc/cpuinfo''.
Try the Apple G5s, possibly PDAs, DSP processors, graphics
co-processor or FPGA.
- Make sure
the machine is quiescent before doing timing experiments.
Always repeat experiments for statistical significance.
- Choose a problem size which suits the performance of the
machine you choose - the runtime must be large enough
for an improvements to be evident.
- The numerical results reported by the application
need not be absolutely identical, but if not you must
justify the correctness of your
- You can achieve full marks even if you do not
achieve the maximum performance.
- Marks are awarded for
- Systematic analysis of the application's behaviour
- Systematic evaluation of performance improvement hypotheses
- Drawing conclusions from your experience
- A professional, well-presented report detailing the
results of your work.
- You should produce a compact report in the style of an academic paper for presentation at an
international conference such as Supercomputing (www.sc2000.org).
The report must not be more than 7 pages in length.
You may find it useful to find out about:
- Cachegrind and cg_annotate
- kcachegrind - kcachegrind.sourceforge.net - graphical interface to cachegrind
- gprof - standard command-line profiling tool.
- kprof - kprof.sourceforge.net - graphical interface to gprof
- VTune - Intel's (Windows and Linux) tool for understanding
CPU performance issues and mapping them back to source code
(http://www.intel.com/software/products/vtune/). Free trial.
- AMD's CodeAnalyst (installed on CSG Athlon machines -
StartProgrammingAMD) (if you have an
- Sun's Performance Analyzer
(if you have a Sun Sparc machine)
http://oprofile.sourceforge.net/news/ (requires kernel rebuild)
You could investigate the potential benefits of more sophisticated compiler
- Intel's compilers
installed on various Linux systems in the Department).
- Codeplay's compilers (www.codeplay.com) (free demo download?)
- IBM's compilers for Apple G5 - XL C/C++ Advanced Edition (a beta download was available, possible donation from Apple or IBM?)
You are strongly invited to modify the source code to investigate
performance optimisation opportunities.
The main criterion for assessment is this: you should have a
reasonably sensible hypothesis for how to improve performance, and you
should evaluate your hypothesis in a systematic way, using
experiments together, if possible, with analysis.
Hand in a concise report which
Please do not write more than seven pages.
- Explains what hardware and software you
- What hypothesis (or hypotheses) you investigated,
- How you evaluated what the
potential advantage could be,
- How you explored the effectiveness
of the approach experimentally
- What conclusions can you draw from your work
- If you worked in a group, indicate who was responsible for
Paul Kelly, Imperial College, 2006
- ... results1
- The gcc flag -ffloat-store is sometimes useful to check whether the difference in output is
due purely to register allocation.
- ... machine)2
- To do this you will need to build the
code using a native Windows compiler. This is easier if
you can use the Fortran sources, see the