Dear all,
the GPU porting of PWSCF carried in the past months is going to hit an
important milestone: the GPU Technology Conference in San Jose (USA). For that
date, we would like to deliver the full package and finally merge the GPU
branch into the main code.
What it is really important in a project like this is a detailed and a
365-degree assessment of the performance, taking into account as many different
scenario (read as many different type of input/calculation) as possible. In the
next (missing) two months we are going to finalize some important piece of code
and run tests. A lot of tests. As much tests as we can.
The purpose of this email is to collect from users new benchmark inputs that
reflect real scientific challenges. We are looking to new input for serial and
parallel calculations, small or big (not very big... let's say "medium")
systems, gamma or k-point, with or without magnetization, with or without
exact-exchange, etc...
What we are especially looking for "special" inputs. I mean, inputs that are
able to intensively stress some specific (and well localized) part of the code.
Do not hesitate to contact me. I look forward to receiving new test cases!
At the end it will be a pleasure to officially acknowledge all the people that
will contribute.
Regards,
Filippo
--
Mr. Filippo SPIGA, Computational Scientist, <filippo.spiga_at_ichec.ie>
Irish Centre for High-End Computing (ICHEC) - www.ichec.ie
The Tower - Trinity Technology & Enterprise Campus
Grand Canal Quay - Dublin 2 - Ireland
Tel: +353-1-5241608 ex. 40 ~ Mob: +353-85-816-8710
website: http://filippospiga.me ~ skype: filippo.spiga
?Nobody will drive us out of Cantor's paradise.? ~ David Hilbert
