Steve Jobs, a young man of 56, passed away this evening. While not so much in traditional HPC, Apple profoundly changed the way we work with … no … the way we use, and think about using computing technology. He is credited with the vision, though Apple has had and does have many very smart people working there. My condolences to his immediate family, and his extended family.
Today, we bought our first Mac book Air. Which you will be able to see in booth 4101 at SC11. His company did have a profound impact upon supercomputing, and computing in general. The democratization of HPC … aiming for the missing middle … is something many folks strive for. Think of the significant processing power in your iPhone, the DSPs and display technology involved with the innovative touch screens. While we can do this processing on ARM cpus today, these calculations were … not so long ago … very HPC like.
Could anyone imagine running a job queuing system on their iPhone (yeah … somewhere I bet Chris D or James Cuff at least looked at this :) )? But many threads had to be run, scheduled, calculations performed …
What Steve Jobs did for HPC was show that it could be useful as something embedded … something very easy to interact with. Not traditional massive scale runs, but localized processing with immediate feedback. Interactive HPC.
In grad school in the late 80s/early 90s, I wanted to interact with the supers using a data glove, a cave (hey, they were hip then!), and set up my runs by grabbing atoms and moving them where they needed to be. That is, make the interface to the science as intuitive as possible. Make it discoverable. Easy to work with.
Its … er .. 20+ years later (whimper) and we still aren’t quite there. But we are far closer.
And we are there in part due to Steve Jobs' drive to make technology easy to use.
We forget this every now and then in HPC. We shouldn’t. Steve was right. For it to be useful, it has to be easy to use in an intuitive manner, in a discoverable manner.