Jon Forrest wrote:
I've been pulling out what little hair I have left while
trying to figure out a bizarre problem with a Linux
cluster I'm running. Here's a short description of the
problem.
I'm managing a 29-node cluster. All the nodes use
the same hardware and boot the same kernel image
(Sci
On Mar 26, 2007, at 1:04 PM, Gilad Shainer wrote:
When Mellanox refers to transport offload, it mean full transport
offload - for all transport semantics. InfiniBand, as you probably
know, provides RDMA AND Send/Receive semantics, and in both cases
you can do Zero-copy operations.
This full fle
On Mon, Mar 26, 2007 at 10:04:13AM -0700, Gilad Shainer wrote:
> This full flexibility provides the programmer with the ability to
> choose the best semantics for his use. Some programmers choose
> Send/Receive and some RDMA. It is all depends on their application.
HPC customers want a fast MPI.
On Wed, Mar 28, 2007 at 03:30:30PM -0400, Tim Chipman wrote:
> Some digging in this list archive suggested a bit of debate (ie,
> Lustre performance would only exceed NFS if lots of large streaming
> intensive I/O access, otherwise it would be worse).
How many MB/s of I/O does your app do? This i
One thing to check is that the switch and NIC are negotiating duplex
correctly... Duplex mis-negotiation (ie switch full, NIC half) used to
be a fairly common cause of FCS errors, although this is rare now as
drivers have gotten a lot better. What will happen is the Full duplex
station will transmi
Slightly off-topic for this list, but I can't think of a more
likely forum to find information on HPC topics.
A couple of colleagues just returned from the "Progress in
Electromagnetics Research Symposium" in Verona. There appears
to be a considerable buzz now around FDTD calculations on GPUs.
A
Hi all,
I've trawled the archives and read via google for a few days now, but have not
got a lot of clarity yet - hence a query to the list. If merited/of use I can
summarize back replies once done.
I'm looking to soon begin deployment of a ~50node (dual socket, dual core
opteron) cluster wi
[resend - I think my first attempt was canned due to being too large,
I've stripped it down to PingPong, Bcast and Reduce]
Hi,
As a follow on to my previous mail, I've gone ahead and run the Intel
MPI Benchmarks (v3.0) on this cluster and gotten the following results -
I'd be curious to know how
I've been pulling out what little hair I have left while
trying to figure out a bizarre problem with a Linux
cluster I'm running. Here's a short description of the
problem.
I'm managing a 29-node cluster. All the nodes use
the same hardware and boot the same kernel image
(Scientific Linux 4.4, l
Hi again Christian,
At 16:59 26.03.2007, Christian Bell wrote:
Hi Håkon,
I'm unsure if i would call significant a
submission comparing results between
configurations not compared at scale (in
appearance large versus small switch, much
heavier shared-memory component at small process
count
Hi,
As a follow on to my previous mail, I've gone ahead and run the Intel
MPI Benchmarks (v3.0) on this cluster and gotten the following results -
I'd be curious to know how they compare to other similar clusters.
Also, I'm trying to determine which parts of the IMB results are most
importan
> Offload, usually implemented by RDMA offload, or the ability
> for a NIC to autonomously send and/or receive data from/to
> memory is certainly a nice feature to tout. If one considers
> RDMA at an interface level (without looking at the
> registration calls required on some interconnects)
We have a dedicated cluster room, email server room, and networking room
that have slowly evolved over the years. Due to budget constraints in
the past no one has ever done an analysis of our electricity and AC.
(We've had the facilities people in, but their analysis wasn't any
better than our own
> obviously, there are
> many applications which have absolutely no use for bandwidth
> greater than even plain old gigabit.
> equally obvious, there are others which are sensitive to
> small-packet latency, which is not affected by DDR or dual-rail.
Yes, there are application that don't uti
>
> The next slide shows a graph of the LS-Dyna results recently
> submitted to topcrunch.org, showing that InfiniPath SDR beats
> Mellanox DDR on the neon_refined_revised problem, both
> running on 3.0 Ghz Woodcrest dual/dual nodes.
This is yet another example of "fair" comparison. Unlike Q
15 matches
Mail list logo
