Hi Brice,
Thank you for your response. Yes, possibly hardwiring everything would
be easier. I was thinking I could use OpenMPI for the signaling between
the cores on an OS that doesn't support multi-processing, using the
shmem approach. The executable is the same for each CPU image, but the
initial conditions will be different and have to be communicated from
the master CPU, which will also be responsible for aggregating the
results into a data and image file.
Here's the hardware:
https://shop.udoo.org/other/x86/udoo-x86-advanced-plus.html
The OS running on CPU0 would have control of I/O and partition the
memory. In testing to this point 1GB is sufficient to run the OS and
executable. In fact, currently I do not free any memory so likely the
footprint is much, much smaller. Not freeing the memory until execution
is completed has avoided some malloc complaints. The OS does not have
paging or segmentation, so fragmentation can be an issue. Performance
is very good.
Is is possible to use a shared memory approach and run an AMP set up,
with hwloc? Would there be any benefit to doing so instead of the
hardwiring approach you mention?
tim
Brice Goglin wrote:
Hello
I am available for off-line discussion for the hwloc side of things. But
things look complicated here from your summary below. I guess there's no
need for binding on such a system. And topology is quite simple, so it
might be easier to hardwire everything.
Brice
Le 20/03/2018 à 08:36, Tim Kelly a écrit :
Hello Everyone,
I'm inquiring to find someone that can answer some multi-part questions
about hwloc, OpenMPI and an alternative OS and toolchain. I have a
project as part of my PhD work, and it's not a simple, one-part
question. For brevity, I am omitting details about the OS and
toolchain, other than that neither are supported. If forced to choose
between OpenMPI and the OS/toolchain, I am likely to choose the
OS/toolchain and pursue other avenues for parallelization. That's part
of what I am trying to determine with my inquiry, and not a reflection
on OpenMPI.
To summarize some of the question areas:
1) The OS I am working with does not support MP
2) nor does it support pthreads
3) the hardware is quad-core x86 SoC with an integrated memory controller
4) I'd like to see if it possible to utilize hwloc and shmem to build an
asymmetric multi-processing system where only one core has I/O but the
other three can run the executable
This is a fairly dedicated system to be used for analyzing ODEs (disease
models). The hardware is cheap ($200) and uses very little power (can
run off a 12v battery), and the toolchain and OS are all BSD-licensed
(and everything will be published under that license).
If someone is available for off-line discussion (to minimize unnecessary
traffic to the list), I'd be more than willing to summarize the
conversation and contribute it to the online documentation.
Thank you,
tim
_______________________________________________
users mailing list
users@lists.open-mpi.org
https://lists.open-mpi.org/mailman/listinfo/users
--
Every chord has a key, every note a consequence
_______________________________________________
users mailing list
users@lists.open-mpi.org
https://lists.open-mpi.org/mailman/listinfo/users
