High Performance Computing Networking

I had a good conversation with an ISV yesterday who makes a popular MPI-based simulation application.  One of the things I like to do in these kinds of conversations is ask the ISV engineers two questions: What new features do you want from the MPI implementations that you use? What new features or changes do you want […]

In the previous blog entry, I shared the slides of one of the mini-talks that I gave at EuroMPI 2015 in Bordeaux, France (and don’t forget to start planning for EuroMPI 2016 in Edinburgh, Scottland). The second mini-talk I gave was twofold in itself: I discussed Cisco’s journey from the Verbs API to the Libfabric API, and […]

I recently had the pleasure of attending EuroMPI 2015, hosted by INRIA in Bordeaux, France (…hey, you should attend EuroMPI 2016 in Edinburgh, Scottland!). I gave two mini-talks during my speaking slot, the first of which was entitled: Crazy ideas about revamping MPI_INIT and MPI_FINALIZE.

I recently received an interesting email from Heiko Bauke about a new C++-based message-passing library that he is working on called MPL. His library aims to make a simple-to-use library that exploits the features available in modern C++ compliers — it’s not a simple 1:1 mapping of C-to-C++ bindings like the MPI 2.x C++ bindings were.

Similar to previous versions of the standard, the MPI-3.1 standard is now available in hardcover. Even though I have a copy of the MPI-3.1 PDF for quick/easy reference on my laptop, I find something intangibly inherently useful (and comforting?) in having a paper copy of the standard to thumb through. The books have been (literally) […]

Later today, Sean Hefty will present a paper about the OpenFabrics Interfaces (a.k.a. “libfabric“) at the 2015 IEEE Hot Interconnects conference. Libfabric is the next-generation Linux library being developed by an open source consortium of vendors and academic researchers that implements the OpenFabrics Interfaces, specifically designed to expose application-focused networking functionality to high performance applications (e.g., MPI, PGAS, […]

In my previous blog entry, I answered a user question about how MPI defines its global constants, specifically in the context of interactions with other languages. I went beyond that answer, and also explained why MPI does not define an ABI. In this entry, I’ll go into the “how does MPI interact with other languages?” part […]

Recently, a reader asked me about how MPI defines its global constants. More specifically, the user was asking how MPI defines its interactions with languages other than C and Fortran (i.e., the two officially-supported language bindings). This is a good question, and has implications on both the MPI standards documents and various MPI implementations.  Let’s dive […]

EuroMPI 2015 is presented in cooperation with ACM and SIGHPC in Bordeaux France, 21st – 23rd September, 2015. EuroMPI is the prime annual meeting for researchers, developers, and students in message-passing parallel computing with MPI and related paradigms. Deadline of early registration is Sept 1st, 2015