Cisco Blogs


Cisco Blog > High Performance Computing Networking

MPI progress

July 26, 2012 at 6:20 pm PST

From my blog post about the upcoming MPI-3 draft spec, Geoffrey Irving asked a followup question:

Can you describe the difference between the current situation and true background progression? Does the lack of background progression mean having to occasionally explicitly relinquish control to MPI in order to let one-sided operations proceed? Once true background progression is in place, would it involve extra threads and context switching, or use some other mechanism?

A great question.  He asked it in the context of the new MPI-3 one-sided stuff, but it’s generally applicable for other MPI operations, too (even MPI_SEND / MPI_RECV).

Read More »

Tags: , , ,

EuroMPI 2012 Call for Participation

July 3, 2012 at 7:40 am PST


EuroMPI 2012 -- the prime meeting for researchers, developers, and students in message-passing parallel computing with MPI (and related paradigms) -- calls for active participation in the conference which will take place from September 23rd to September 26th in Vienna, Austria, at the Austrian Academy of Sciences.

Read More »

Tags: , ,

Hardware vs. software: user questions (part 2)

June 29, 2012 at 5:00 am PST

In my prior blog entry, I answered the first of Durga C.’s questions to me.  Here’s all three of his questions:

  1. What is the role of the hardware in an RDMA transaction?  In other words, why does one need special hardware (e.g., InfiniBand, iWARP, RoCE, etc.) hardware to do RDMA as opposed to a “normal” Ethernet NIC? (see prior blog entry)
  2. Further, can you explain why pure software solutions (e.g., Open-MX) are better than nothing when you don’t have hardware support?
  3. Also, what is the difference between “RDMA” and “RMA”?

Let’s explore the last two of those questions. Read More »

Tags: , , , , ,

Hardware vs. software: user questions

June 26, 2012 at 1:20 pm PST

Durga C., long-time listener, first-time caller, sent me a few interesting questions that I thought I’d share with everyone.  Here’s his first question:

  1. What is the role of the hardware in an RDMA transaction?  In other words, why does one need special hardware (e.g., InfiniBand, iWARP, RoCE, etc.) hardware to do RDMA as opposed to a “normal” Ethernet NIC?

This one question is surprisingly complex.  Let’s dive in…

Read More »

Tags: , , , , ,

Registered memory imbalances

June 23, 2012 at 4:36 am PST

In prior blog posts, I’ve talked about the implications of registered memory for both MPI applications and implementations.

Here’s another fun implication that was discovered within the last few months by Nathan Hjelm and Samuel Gutierrez out at Los Alamos National Labs: registered memory imbalances.

As an interesting side note: as far as we can tell, no other MPI implementation attempts to either balance registered memory between MPI processes, or handle the performance implications that occur with grossly imbalanced registered memory consumption.

Let’s review a few key points before defining what registered memory imbalances are.

Read More »

Tags: , , ,