Google Tech Talks
December, 12 2007
ABSTRACT
The advent of multicore processors has generated profound debate on the merits of writing parallel programs with threads and locks. Nonetheless, for many application domains, this remains the standard paradigm for writing parallel programs, and at the moment, there is no apparent universal replacement. And it is the focus of this talk.
Somewhat surprisingly, there are a number of often subtle, but generally fixable, industry-wide problems with current approaches to threads programming. We’ll focus on probably the most widely used environments, consisting of C or C++ with a standard threads library. Problems span the spectrum from system libraries through language implementations through supporting hardware. They get in the way both in that they often make it difficult to write 100% reliable multi-threaded software, and in that they confuse even the basics of the programming model, thus making it hard to teach. A surprising number of “experts” do not understand the basic rules. Arguably, these problems really need to be addressed to even allow a meaningful comparison to other parallel programming approaches.
Since solutions to these problems generally require a coordinated industry effort, we helped to persuade the C++ standards committee to address them by pursuing a coherent approach to threads in the next C++ standard. The talk will outline some of the proposed solutions, and give an update on this effort.
Speaker: Hans Boehm
Hans Boehm is a member of the advanced architecture group at HP Labs. He has worked on many aspects of programming language design and implementation, including garbage collection and concurrency, and he was HP’s representative to the effort to redesign Java’s memory model. He is a past Chair of ACM SIGPLAN, and is an ACM Distinguished Scientist.Duration : 1:10:16
|
James Reinders from Intel answers some common questions relating to software development and evolving technologies.Duration : 0:4:57
|
Google Tech Talks
March 29, 2007
ABSTRACT
We want powerful, linguistic abstractions for concurrent and parallel control of computational devices, be they small or big. As a step towards this, we’ve been developing the Transterpreter[1], a small (8KB), portable VM for a growing family of programming languages. The most complete and interesting language we support is occam-pi[2].
In this talk, we’ll talk a bit about the journey that brought us here, paying particular attention to things we think are cool. Typically, “things we think are cool” involve using linguistic abstraction to make programming tasks involving concurrency and parallelism easier. So, expect to see some wireless sensor network…Duration : 0:43:10
|
Interview with James Evans of the MIT Whitehead Bio-Imaging Institute, regarding the Institute’s mission, applications, computational challenges, and tools.Duration : 0:5:57
|
Interview with Nancy Wilkins-Diehr, SDSC, regarding the Center’s mission, applications, computational challenges, and tools.Duration : 0:5:47
|
Renee James describes her team’s parallel programming programs and how she reaches out to developers for collaboration. Recorded at the Intel Developer Forum on September 20, 2007.
For more on Intel IDF:
http://www.intel.com/idf/usDuration : 0:4:20
|
A political thingDuration : 0:4:41
|
Sun HPC ClusterTools 7 software is based on Open MPI, an open source implementation of MPI. As with previous versions, Sun HPC ClusterTools 7 software offers a comprehensive set of tools for parallel program development and resource management.Duration : 0:1:7
|
|
|
|
