Are both the IB HCA and the ethernet interfaces on the same physical
bus?
If they're not, the need for multiplexing them is diminished (but, of
course, it depends on what you're trying to do -- if everything is
using huge memory transfers, then your bottleneck will be RAM, not
the bus tha
Hi,
Some of our clusters uses Gigabit Ethernet and Infiniband.
So we are trying to multiplex them.
Thanks and Regards
Pooja
> On Thu, Apr 19, 2007 at 06:58:37PM -0400, po...@cc.gatech.edu wrote:
>
>> I am Pooja working with chaitali on this project.
>> The idea behind this is while running a pa
On Thu, Apr 19, 2007 at 06:58:37PM -0400, po...@cc.gatech.edu wrote:
> I am Pooja working with chaitali on this project.
> The idea behind this is while running a parallelized code ,if a huge
> chunks of serial computation is encountered at that time underlying
> network infrastructure can be used
Hi,
I am Pooja working with chaitali on this project.
The idea behind this is while running a parallelized code ,if a huge
chunks of serial computation is encountered at that time underlying
network infrastructure can be used for some other data transfer.
This increases the network utilization.
But
On Sun, Apr 15, 2007 at 10:25:06PM -0400, chaitali dherange wrote:
>schedule MPI and non MPI calls... giving more priority to the MPI calls
>over the non
>MPI ones.
What is the idea behind this and what advantages are expected?
Christian Leber
--
http://rettetdieti.vde-uni-mannhei
On Apr 15, 2007, at 10:25 PM, chaitali dherange wrote:
To make things simple, we are making this scheduling static to some
extent... by static I mean.. we know that our clusters use
Infiniband for MPI ( from our study of the openmpi source code this
precisely uses the 'mca_btl_openib_send()
Hi!!!
I am Pooja ,I am working with chaitali on this project.
What we meant by Btl_Tcp is a call to btl_send that our program will give
directly on the higher levels.In short we want to call BTL transport at
the higher levels and so we have configure openmpi using all development
header
files.(So
Hi
I am Pooja.I am working with chaitali on this project.
We want to shift BTL transport to the higher levels.
So we are configuring MPi using all development header file .
This will enable us to call btl /Bml functions directly at the higher level.
So we will send a normal file across the net
On Sun, Apr 15, 2007 at 10:25:06PM -0400, chaitali dherange wrote:
> Hi,
Hi!
> giving more priority to the MPI calls over the non MPI ones.
> static I mean.. we know that our clusters use Infiniband for MPI ...
> so all the non MPI communication can be assumed to be TCP
> communication using th
Hi,
Pooja and I are actually working on this course project where we our main
aim is
schedule MPI and non MPI calls... giving more priority to the MPI calls over
the non
MPI ones.
To make things simple, we are making this scheduling static to some
extent... by
static I mean.. we know that our c
10 matches
Mail list logo
