Hi Chris, Paul,
|--------------------------------------------------------------------------=
-------------------------------------------------------------------|
|"> I faintly remember a presentation that was stateing that Geant4 performance was following more closely the SPECint numbers than the SPECfp|
|numbers. With the explanation that the disicions> that an MC code has |
|to make are as expensive as the actual calculations. I wonder if this is |
|correct also for Fluka." |
|---------------------------------------------------------------------------------------------------------------------------------------------|
Makis did not seem to doubt the "explanation" re Geant4. Do not trust
Geant4 people. Papers and other media in which claims about Geant4
have been made contain untruths.
Well, I am not an expert in the performance monitoring. I do take with a grain of
salt the presentations I am looking at, but I cannot make much more.
As a simulation user I do have an interest in knowing what factors influence
the running time of my simulation. Which I believe can lead us back to the
original question. I am pretty sure that in my simulation the CPU is the limiting factor.
I just want to know what part of it is the most influencial.
Is is the integer performance, the floating performance, the cache size?
I really have no clue and thats why I want to see if someone has actual numbers to base an answer to.
|---------------------------------------------------------------------------------------------------------------------------------------------|
|"If you happen to have a link to the presentation that you mentioned then |
|I'd appreciate if you could send it to me. |
| |
|Cheers |
|Chris" |
|---------------------------------------------------------------------------------------------------------------------------------------------|
Please cite it on the email list. I am also interested in learning
more concerning it.
Regards,
Paul Colin
I am really sorry, but I cannot provide the reference. I do remember that it is very old,
for sure 3 years old. I cannot remember even which community produce it.
Also I am not sure the numbers was refering to micro-benchmaks as Chris implied,
or to macro-benchmarks (ie. ATLAS simulation jobs).
Regards,
Makis
Received on Tue Nov 30 2010 - 11:30:15 CET
This archive was generated by hypermail 2.2.0 : Tue Nov 30 2010 - 11:30:15 CET