Dear SciNet staff,

I am writing this letter to thank you all for your dedicated effort in providing SciNet users with such an excellent support service.

I have been using you High Performance Computing systems since the very first year of production, and was always impressed by the amount of help I received from your programming staff.

Being at the University of Toronto for five years, I had the chance to have close contact with the staff, I had to opportunity to sit down about a dozen time with one of your experts, which would patiently help me with a wide variety of programming aspects. “I should have come here last year!!!” would I say to myself every time.

Thanks to your help, my code finally compiles and run efficiently in hybrid openmp+mpi, on GPC, TCS or even BGQ, we are currently running one of the world’s largest N-body simulations ever, we are creating one of the vastest mock galaxy catalogues for current and future weak gravitational lensing experiments, and the science seems to be only limited by our imagination. Not to mention the SNUG meetings, during which we get together and discuss tricks and issues.

I all took a different color once I moved away from Toronto after my PhD. It is when I started looking at other HPC
consortium that I actually realized how special and precious SciNet really is. Yes, the machines themselves are superbly
performing, the choice of systems are well balanced for memory, speed and/or networking heavy jobs, and the science
outcome is amazing.

But more important is the help I received, and seeing how hard people work to make the machines perform. As I am
writing this letter, the machines are down, a large thunderstorm in Toronto caused a power failure over night. Here is a section from the SciNet wiki:

********
***Tue Jul 9 02:22:47 EDT: No power at site. Will resolve by 10AM and update here.
Power failure at site and UPS has drained. Major storms and problems throughout Toronto. Staff enroute.
***Tue Jul 9 09:30:52 EDT: Fuse on power lines blew last night. Utility is backed-up dealing with other problems. No ETA for them to restore power at the site
***Tue Jul 9 11:52:02 EDT: Powerstream on-site. Wind/tension damage to two hydro poles caused overhead fuse to blow. Repairs are underway
***Tue Jul 9 12:45:25 EDT: Power has been restored. We need to restart cooling systems, restart and check the filesystems etc. Will have better idea of timeline by 3PM
**********

Noted the part where staff is enroute at 2am? How they keep users informed? I find that remarkable, generous and
dedicated, and I wish to extend my gratitude to all of the SciNet staff for helping us in achieving our goals.

Sincerely,

Joachim