There was in the PCI/PCI-X era -- sometimes you had to downclock the
not to mention the fact that PCI/PCI-X is often an actual bus,
ie, multidrop. PCI-E is always point-to-point, so avoid some
of the worst challenges of buses. PCI-E also has a per-transfer CRC...
On Mon, 2009-02-23 at 12:39 -0500, Mark Hahn wrote:
> > When gfortran is used, then we get
> > "segmentation fault" in the middle/during the
> > parameter setting stage of the computation.
> > I would be grateful if you
> > have any idea on how to treat this problem.
>
> compile with gfortran and
On Mon, Feb 23, 2009 at 08:30:24AM -0800, Lucas Sheehan wrote:
> Is there really that much effect from a riser or other connector?
There was in the PCI/PCI-X era -- sometimes you had to downclock the
bus (a BIOS option) to get it to work reliably. And it was very
important to use a riser which wa
Mark Hahn wrote
> > When gfortran is used, then we get
> > "segmentation fault" in the middle/during the
> > parameter setting stage of the computation.
> > I would be grateful if you
> > have any idea on how to treat this problem.
>
> compile with gfortran and add -g. then run inside gdb.
> w
On Mon, Feb 23, 2009 at 08:30:24AM -0800, Lucas Sheehan wrote:
> On Sun, Feb 22, 2009 at 11:53 PM, Nifty Tom Mitchell
> wrote:
> >
> > In general a landed on motherboard chip set solution can be less expensive
> > than a MB+card solution. The lack of a PCIe connector and riser can
> > improve PC
On Mon, Feb 23, 2009 at 12:39:33PM -0500, Mark Hahn wrote:
>> When gfortran is used, then we get
>> "segmentation fault" in the middle/during the
>> parameter setting stage of the computation.
>> I would be grateful if you
>> have any idea on how to treat this problem.
>
> compile with gfortran and
On Mon, Feb 23, 2009 at 5:27 AM, Mark Hahn wrote:
> AMD Opteron "Shangai" 6MB L3 : 90% of peak
>> Intel "Nehalem" Core i7 : 95.2% of peak
>> Intel Itanium 2 : 95.6% of peak
>>
>
> interesting numbers, and Goto's efforts are always respected.
> it would be valuable to understand why, though. I us
On Mon, 23 Feb 2009, f.cos...@cs.man.ac.uk wrote:
Dear All,
This is not directly relate to parallel computing
but I may be able to get your skills/knowledge.
We have developed a fortran code and
we can compile it with bot intel-fortran and
gfortran without any error message.
When we run it, t
Dear Fumie,
does the code read anything from a file?
Note, there are many non-standard features in intel fortran, so that the
code that works
correctly under ifort might behave differently when compiled under a
different compiler.
Among these features are
- support for lines longer than 132 chara
On Sun, Feb 22, 2009 at 11:53 PM, Nifty Tom Mitchell
wrote:
>
> In general a landed on motherboard chip set solution can be less expensive
> than a MB+card solution. The lack of a PCIe connector and riser can
> improve PCIe signal quality. The IB chip set is close to the 4x connector
> which i
>
>
> . HP MPI works pretty well also, though it (and
> other binary only stacks) tend to be hard linked against (older)
> particular Infiniband stacks ... makes support ... well ... challenging.
>
We have not found that to be the case with HP-MPI, the latest HP-MPI 2.3
release supports up throu
On Tuesday 17 February 2009, Bogdan Costescu wrote:
> On Mon, 16 Feb 2009, Tiago Marques wrote:
> > I must ask, doesn't anybody on this list run like 16 cores on two
> > nodes well, for a code and job that completes like in a week?
>
> For GROMACS and other MD programs, the way a job runs depends o
When gfortran is used, then we get
"segmentation fault" in the middle/during the
parameter setting stage of the computation.
I would be grateful if you
have any idea on how to treat this problem.
compile with gfortran and add -g. then run inside gdb.
when compiled, are there any warning message
Dear All,
This is not directly relate to parallel computing
but I may be able to get your skills/knowledge.
We have developed a fortran code and
we can compile it with bot intel-fortran and
gfortran without any error message.
When we run it, the code runs when intel-fortran
ifort was used for th
On Fri, 2009-02-20 at 16:10 +, John Hearns wrote:
> It is a tad lame to repeat articles from HPCwire here, but I can't help it.
> New. Shiny. http://www.supermicro.com/products/nfo/2UTwin2.cfm
>
> The nice thing is that the motherboards are hot-swap from the rear -
> so these things
> offer th
On Sat, Feb 21, 2009 at 07:46:57AM -0500, Andrew Piskorski wrote:
> On Fri, Feb 20, 2009 at 04:10:33PM +, John Hearns wrote:
> > It is a tad lame to repeat articles from HPCwire here, but I can't help it.
> > New. Shiny. http://www.supermicro.com/products/nfo/2UTwin2.cfm
>
> So it gets to use
16 matches
Mail list logo
