Supercomputing and mathematica

The last time I went to a “Supercomputing” conference, Jim Gray came by to talk to me and Cort about PowerPC Linux. That must have been in 2000 or 1999. We had gone by the AIX booth and been roundly sneered at by IBMs Operating System Gurus and were walking away, somewhat crestfallen, when Gray stopped by to talk and to illustrate why he was such a widely admired person. Yesterday, I went by SC08 here in the Capital of Texas, snuck into a talk by one of the poor people who survived my Operating System class back before 2000 and roamed the floor looking at all that, as we highly trained and educated technical people say, “stuff” on the floor.

The problem of parallel computing is, of course, the standard topic of Supercomputing  and currently Supercomputing seems to be a celebration of MPI. I was amazed to see that people have added parallel constructs and even MPI to Mathematica. Why not just try to automatically extract parallelism from the high level constructs?

Not as strange as the Tokyo University use of parallel Ruby for scientific computing though.