[Baypiggies] [ANN] Scientific Python at UC Berkeley talk for November 18
fperez.net at gmail.com
Sat Nov 14 11:18:32 CET 2009
I would like to know if in general people want to get these
announcements regarding the UC Berkeley py4science seminars on this
list or not, I don't want to spam people. But last week's event with
Guido drew a huge crowd, some from this list, so perhaps there is
interest (obviously Guido's visit was a special event, but still
there may be interest in these talks amongst this group). If there
isn't let me know and I won't post them again, as you can always see
them at the group page:
But if you find these useful, I'm happy to send the announcements
here, it will be limited to just one email every 2 weeks at most.
So for now here's next week's, I'll refrain from posting these again
if so requested.
Next week, we will have a presentation by Bryan Catanzaro from EECS
on Copperhead, the system we got a glimpse of last week from his
lightning talk. Details below.
When: November 18, 2pm.
Where: UC Berkeley, Evans 508-20
Title: Copperhead: Data-Parallel Python
The need for productive programming languages which can avail
themselves of parallel hardware has never been more acute. The
Copperhead project attempts to address this problem by defining a
subset of Python which can be compiled and executed in a data-parallel
fashion. Copperhead procedures are expressed as standard, fully-legal
Python procedures operating on Numpy datatypes, which are intercepted,
specialized, and compiled to parallel C code at runtime, and then
executed on a high-performance parallel platform. Since the
Copperhead runtime supports only a subset of Python, the runtime will
revert to standard Python execution if specialization fails. The
current Copperhead runtime targets Nvidia Graphics Processors, which
are highly suited for data-parallel computation and provide high
performance. In this talk, I will be discussing the current state of
Copperhead, as well as plans for future development.
More information about the Baypiggies