Cisco Blogs


Cisco Blog > High Performance Computing Networking

Open MPI and the MPI-3 MPI_T interface

Open MPI recently revamped its entire run-time parameter system (a.k.a., “MCA parameter system”) as part of its implementation effort for the “MPI_T” interface from MPI-3.

The MPI_T interface is a standardized interface designed for MPI tools, but can be used by regular MPI application programs, too.

Specifically, MPI_T provides programatic access to two types of MPI implementation data:

  1. Control variables: used to control the behavior of an MPI implementation
  2. Performance variables: provide access to internal MPI implementation performance metrics

Read More »

Tags: , , ,

MPICH 3.0 RC released

The MPICH folks have released an RC candidate for MPICH 3.0:

A new preview release of MPICH, 3.0rc1, is now available for download. The primary focus of this release is to provide full support for the MPI-3 standard.  Other smaller features including support for ARM v7 native atomics are also included.

Read More »

Tags: , , ,

MPI-3 standard available in hardcover

The MPI-3.0 standard is now available in hardcover (it’s green!).  The book is available for cost by Dr. Rolf Rabenseifner at HLRS; no profit is being made by these sales.  Here’s an excerpt from Rolf’s original announcement:

As a service (at costs) for users of the Message Passing Interface,  HLRS has printed the new Standard, Version 3.0 (852 pages)  in hardcover. The price is only 19.50 Euro or 25 US-$.

The book is available through the HLRS web site.

Read More »

Tags: , ,

MPI_Ibarrier: Crazy?

Most people’s reactions to hearing about the new MPI-3 non-blocking “barrier” collective think: huh?

Why on earth would you have a non-blocking barrier?  The whole point of a barrier is to synchronize — how does it make sense not to block while waiting?

The key is re-phrasing that previous question: why would you block while waiting?

Read More »

Tags: , ,

MPI progress

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: , , ,