Ocean Modeling Discussion

jpringle

As coastal sea-levels rise, flooding is increasingly impacting coastal communities. The NSF funded EPSCOR project, "Community-Driven Coastal Climate Research & Solutions for the Resilience of New England Coastal Populations," seeks to help communities manage the increasing environmental risks caused ...

jpringle

I would still benchmark, but unless you need all those cores for other reasons, I would go with a higher clockspeed, lower core count chip. A dual CPU machine will have twice as many memory channels. The memory size, if it is large enough for your model to run, will not affect the run speed, as long ...

jpringle

Dear Enzo -- My first advice is to benchmark. Most server manufactures will allow you to bench mark systems remotely. How does your ROMS configuration scale with cores? My second advice is not to chase cores or threads. All my experience suggests that ROMS becomes quickly limited by bandwidth to ...

jpringle

Postdoctoral position at University of New Hampshire in the physics of sea level and modeling coastal sea-level change. As coastal sea-levels rise, flooding will increasingly impact coastal communities. The NSF funded EPSCOR project, the Community-Driven Coastal Climate Research & Solutions for the ...

jpringle

I remember meeting him at a conference at Rutgers, after which he invited everyone to his house. He was one of the first "big names" that I met, and realized that they were not just names on papers but actual people -- and idea that was still new to me, and a bit of a shock. He was very kind in ...

jpringle

Just a quick callout to a past post of mine https://www.myroms.org/forum/viewtopic.php?t=4665 on performance versus memory bandwidth. I still find this to be true with the latest AMD hardware for ROMS -- The 16 core AMD 5950x is a beast for everyday work, but with its two channels of memory I can't ...

jpringle

No problem. Note this is a straight translation from the code, accelerated via numba. Also note the many ways you can define Ertel's PV depending on how you define the conserved quantity... One note -- this code is accelerated with Numba; you need not do so, but it will be unbearably slow. If found ...

jpringle

I have a python code to compute these from history file that is based on the ROMS Fortran code; ask if interested.
Jamie

jpringle

The Department of Earth Sciences seeks a postdoctoral scholar hire in the field of Earth and Environmental Sciences. We will consider applicants from a broad range of disciplines in the geosciences (e.g., biogeochemistry, remote sensing, geochemistry, earth system modeling, surficial geology ...

jpringle

Thanks

jpringle

Hernan --

I agree with all that. All I am saying is that varinfo.dat should be changed to be consistent with the actual units written out.

Jamie

jpringle

Yes, I agree. All that is left is to change the text in varinfo.dat to reflect this.
Jamie

jpringle

Dear all -- I, and some Europeans doing particle tracking with ROMS output, are confused by what the units of omega are supposed to be in the output. From equation 12 of https://www.myroms.org/wiki/Terrain-Following_Coordinate_Transformation , the units of omega should be w/Hz or 1/time since Hz ...

jpringle

Dear all -- I think I have found a bug in how the potential vorticity calculation is computed. I was trying to make the output match my expectations for a motionless, stratified f-plane ocean, and found this (I think) error. In set_avg.F, the function that calculates the potential vorticity is ...

jpringle

Dear all -- Does anyone know of a package to calculate the potential vorticity flux J either inline while the model is running, or from the saved output? I would prefer python, but would be happy with anything. I would prefer not to have to re-invent the wheel, especially if that wheel involves ...

jpringle

Just to close this discussion. I ended up using Lars Roed's book, referenced above. I found it a very good fit to the class, and was very happy with it. It worked well with my approach of having students build a series of simple numerical models as various dynamics were introduced in Lars' book. The ...

jpringle

With the same version of Ubuntu, but updated kernels (nothing special, just the default updates), this no longer appears to be true. A reminder to test your tiling and MPI options every so often.

Jamie

jpringle

Lar's --

Thanks for bringing up your book. I like it very much.

Jamie

jpringle

Thanks everyone!
Jamie

jpringle

I have used windows subsytem with linux with Ubuntu 18.04, and it worked just like ubuntu on bare metal. have you tried your problem on regular linux box?

Jamie

jpringle

Dear modelers -- I am teaching an advanced graduate course in numerical ocean modeling in the spring, and thus must call it into existence. Students will have had fluids and PDE's and introductory physical oceanography. Most will have had GFD. I would love to see your syllabi if you have taught such ...

jpringle

A much less elegant solution, but one I use all the time, is XPRA -- it is a way to view X windows remotely that is MUCH MORE robust than forwarding a remote X11 connection via SSH. Essentially, it sets up a local X11 server, and then serves the windows that are created on that server via a screen ...

jpringle

Aryan -- I just want to amplify a point that Sasha made above, for it is important to understanding the dynamics of your case. An alongshore current in a periodic domain must be maintained by forcing; anything else is inconsistent. Why? what is an alongshore periodic domain? one in which there are ...

jpringle

Dear all -- I hope someone finds this usefull. I wanted to plot some iso-surfaces in 3D with ROMS data without re-gridding it to a rectangular grid or some such silliness. There are many heavy-weight environments that can do all sorts of cool things like that (paraview, vapor, yt) -- but getting ...

jpringle

In your sections, the bathymetry has severe stair-stepping (discontinuities). Is that real?

Also, is there any along-isobath flow which could be driving a bottom Ekman transport?

Jamie

jpringle

Dear all -- I hope some of you find this useful. I am running ROMS on a dual processor 32 core AMD EPYC machine. I noticed on the latest version of Ubuntu my smaller machines showed good improvement with ROMS runs with openMP parallelization. So I upgraded the big machine to Ubuntu 18.04, and my ...

jpringle

Dear All, The errors of the type Warning: distutils distribution has been initialized, it may be too late to add an extension _interp Warning: distutils distribution has been initialized, it may be too late to add an extension _obs_interp are a bit of a red herring. You can make the codes work by ...

jpringle

Thanks to John Wilkin, John Warner, Nirnimesh Kumar, the excellent Warner et al. 2005 Ocean Modeling paper on mixing schemes in ROMS and the excellent note by Malcolm Scully (https://www.myroms.org/forum/viewtopic.php?f=17&t=2310&p=8441&hilit=malcolm+scully#p8458 ), I have run this issue down. In ...

jpringle

Both in John Wilkin's reply and in some private emails, I have received some good hints related to minimum turbulence level parameters in the mixing scheme. I shall investigate and compare to the primary literature for this scheme in the next few days, and will post a summary here soon. Thanks for ...

jpringle

ALT_BAK is 1.0d-6 for both T and S, so much less than observed... ¯\_(ツ)_/¯

jpringle

I was asked offline why I expected the diffusion of temperature to be slower than ROMS's k-epsilon in the ocean -- why did I think the GOTM k-epsilon, ROMS MY25 and ROMS LMD was closer to the truth? In this stratified ocean, with no horizontal gradients of density and no forcing, there is no flow ...

jpringle

Dear all -- I think I have stumbled across evidence of a bug in the GLS vertical mixing scheme in ROMS, at least for the k-epsilon scheme. It remains possible that I am just doing something stupid. I find that under the k-epsilon scheme vertical stratification diffuses away much more quickly than ...

jpringle

I am not well versed in openMP programming -- but I think I found a bug where ana_psource initializes the tracer input. I was having problems with different runs of my code producing wildly different answers from run to run under openMP. It did not do this when run in a single thread and when run ...

jpringle

I think I found a bug in the ana_psource.h when the model is initialized with ana_initial.h. In this case, the analytical forcing files are invoked in analytical.F before the first time step of integration as part of initializing the u, v etc fields. When this is done, the variable iic(ng) is 0. In ...

jpringle

Mark --

Ah -- I see -- I had not defined "USE_MY_LIBS" and so it ignored the changes I made to NF_CONFIG and NETCDF_INCDIR in my build.bash. I had made the changes, and never tested if it worked without them.

Cheers,
Jamie

jpringle

I have recently compiled ROMS on a bunch of ubuntu machines for benchmarking and production use, with versions 16.04, 17.04 and 17.10 (I recommend skipping 17.04). In all cases it is trivial to get ROMS going. Just install the following packages (which include the MPI packages, and you can compile a ...

jpringle

Wayne -- A couple of things. To get the model to run on my Threadripper 1950x with only 8 threads, I used the environmental variable omp_num_threads. I suspect, based on my earlier post, that the speed of ROMS on this kind of system is limited by memory bandwidth (see Sasha's long thread on this ...

jpringle

Wayne-- This configuration seems reasonable -- but I have not experimented with the intel compilers yet. At some point I will have one of my students install the student version and let people know. If you would like to benchmark my threadripper system, let me know via email. On the 1920x (12 cores ...

jpringle

A naive question. For multi-threaded or multi-process programs like ROMS, is there any significant performance penalty for using something like docker?

Jamie

jpringle

Dear all -- I hope some of you find this useful; I have been researching purchasing a new modeling server, and the results should be interesting to those trying to optimize the performance on their own machines, or are thinking of purchasing new machines. There are a number of new architectures that ...

jpringle

Sacha and All-- A couple of things. First, the AMD Ryzen has a dual memory channels, so is has less memory bandwidth than the x99 Intel boards. Compared to older AMD processors, the L1 and L2 cache's are private to each core, but the L3 cache is shared amoung 4 cores. But see below for more on this ...

jpringle

Dear all -- IF YOU ARE INTERESTED IN THIS POST, PLEASE ALSO SEE: https://www.myroms.org/forum/viewtopic.php?f=29&t=4665 I hope some of you find this helpful. I needed a computer for a new graduate student to run models and do data analysis. For 1500$ I built a Ryzen 1800x box. Since this is a new ...

jpringle

Dear all -- I need to build/acquire a linux box for a new graduate student for process oriented ROMS modeling and ocean model data analysis, with a side of embarrassingly parallel ecological modeling. I have a budget of 1500 (excluding the massive pile of disks for data storage). I am wondering if ...

jpringle

I have funding available for graduate students at the University of New Hampshire to study the interaction of Western Boundary Currents and continental shelf flows. The applicant must posses strong quantiative skills, with a major in the sciences, mathematics or engineering. Applicants with either ...

jpringle

I do not know if this helps, but attached is a calculation of relative and potential vorticity that exactly parallels the code in Vorticity.F, but implemented in python. It calculates both 3D and shallow water vorticity. Please look at the function defineVorticity() for the calculation. I have ...

jpringle

It would be easier to debug if you printed out what the attribute name is. You could add an fprint by line 112 of nc_create, and print out what aname is. This might provide insight.

Cheers,
Jamie

jpringle

While waiting for some other runs to complete, I did some simple test cases with nested grids, and can confirm that what John said is true.

Jamie

jpringle

Dear all -- I am having some trouble with nesting and river inflows. I have justed started to implement rivers entering into my domain. Some rivers enter where the fine grid overlaps the coarse grid. When I run the model with nesting, it blows up quickly. When I run with rivers in just coarse grid ...

jpringle

Just to update -- the discrepancy in the area of grid cells between the fine and coarse grids was largely caused by an inconsistency between mat2roms_mw and coarse2fine. The former used sw_dist to compute distance between grid points, the later used gcircle. sw_dist uses the "plain sailing" method ...

jpringle

The area of the 9 rho cells of the fine grid is 0.144% greater than the area of the associated coarse grid rho cell, with a very weak dependency on latitude. This is of the same order of magnitude of the discrepancy of mass flux at the eastern boundary. I am investigating the origin of this issue. I ...

jpringle

Hernan -- I will compare the averaged metrics tomorrow, when I have time to code. A question and two points first. 1) It is a curvilinear spherical grids -- the delta-latitude and delta-longitudes are both constant, and the grid is north/south and east/west aligned. 2) There is no wind, so the wind ...

jpringle

Hernan -- I have posted the information you want in viewtopic.php?f=17&t=3957 ; I did not put it as a bug yet since I have not isolated the exact cause.

Jamie

jpringle

NEGLECT THIS MESSAGE -- THE PROBLEM WAS NOT WHERE I SUSPECTED IT WAS HERE. THERE IS SOME USEFUL INFORMATION BELOW ABOUT AREA CALCULATIONS WITH VARIOUS GRID PACKAGES, SO I AM NOT DELETING IT. I have been debugging on and off for several weeks what appears to be a bug (or my stupidity) in nesting in ...

jpringle

In check_massflux in nesting.F, the variable ng in # ifdef NESTING_DEBUG IF (DOMAIN(ng)%SouthWest_Test(tile)) THEN IF (Master) THEN WRITE (300,10) 'Western Boundary Mass Fluxes: ', & & cr, dg, rg, iif(rg), iic(rg), INT(time(rg)) END IF END IF ! # endif should be "ngf". "ng" is not defined in this ...

jpringle

In the latest ROMS, the model does not compile when NESTING is defined but MASKING is not. The error is minor; mask_hweights is always defined at the top of nesting.F even when MASKING is on. The fix is straightforward: *** nesting.F_old 2015-08-18 10:49:28.000000000 -0400 --- nesting.F 2015-08-18 ...

jpringle

My original edits to fine2coarse.m, and the "official" version on the Subversion repository, contain an error in which the curvilinear metrics dmde and dndx are not written to the coarse grid. Since those fields are defined in c_grid(), the grid file has fill values for those metrics. The fixed code ...

jpringle

Dear all -- I would like to create a ROMS grid file from a grid of h at longitude and latitude points. In the past this was possible with mat2roms_rps.m ( https://github.com/rsignell-usgs/seagrid/blob/master/seagrid/mat2roms_rps.m ) Unfortunately, the code I can find on the web for this uses Chuck ...

jpringle

Ah... I noticed in an email from John Wilkins that he told me We are taking this a step at a time. As you say, presently the Matlab tools have been written assuming the nest is wholly within the parent, but the ROMS design anticipates the day that the contact file can allow a nest to cross the ...

jpringle

Dear all -- I just want to document a bug in contact.m, and to ask if anyone has succeed in putting a refined grid next to a model boundary? I am using the latest version of the matlab tools, from SVN revision 722. I create a coarse resolution grid, which I have attached to this post. I then create ...

jpringle

My fine2coarse code does not set either the coarse_factor or refine_factor attributes of either grid; see https://www.myroms.org/forum/viewtopic.php?f=1&t=3698&p=14962#p14962 ; I am not sure fine2coarse is a good place to do so, and will not be able to do so until I have a better understanding of ...

jpringle

Hernan & Kate -- Kate -- to start to get things to work, I have had to add the refine_factor attributes by hand. My efforts have been interrupted by my vacation, but will pick up in two weeks or so. I am not sure if I will end up going fine2coarse or coarse2fine, then edit the bathymetry in the ...

jpringle

Attached is a corrected fine2coarse.m, a testing code, a file with grid information for it to read, and a little routine to plot grids. The testing harness expects the rest of the ROMS Matlab tools to be in the path. Please make sure you are running the provided fine2coarse.m, and not the one that ...

jpringle

There is a bug in the definition of lonp,latp,lonr,latr,lonu,latu and lonv,latv in ana_grid.h for the benchmark case. It does not affect the solution, since the metric definitions are correct. However, it can make interpreting plots difficult, and will cause errors if this analytical grid is then ...

jpringle

Before anyone else spends time on this, I am working on fixing this code. I will let people know when a working version exists and has been tested.

Jamie

jpringle

I am developing a new modeling setup with a simple nested grid configuration. Following Hernan's advice, I am starting from a full domain fine grid and extracting the coarse grid from it. However, the fine2coarse.m downloaded from the SVN repository as of this morning is completely broken (SVN ...

jpringle

Agree.

jpringle

John -- Thanks. You are right, the inclusion of the surface layer depth in the formulation is deeply problamatic. However, it is a science issue not a programming issue. In this code we prescribe the surface heat flux as a function of SST. Thus the time rate of change of temperature is set by the ...

jpringle

Dear Zhang -- You are correct. My code is correct, but the comments are wrong. The comments should be changed to ! !----------------------------------------------------------------------- ! Set surface heat flux sensitivity to SST (m/s ...

jpringle

Dear Hernan et al -- I think I have found a bug in ana_dqdsst.F. The stub code from the most recent model version on subversion reads: ! !----------------------------------------------------------------------- ! Set surface heat flux sensitivity to SST (m/s/degC ...

jpringle

Old thread, but I hope this helps someone. You can run ROMS on OS X/mac using macports to install all the libraries. But was noted above, the netcdf is a bit tricky. To get it to work, you must specify the variant of netcdf-fortran to install that is consistent with your fortran compiler. To do this ...

jpringle

Dear ROMS runners -- I am starting a ROMS project after a hiatus. Has anyone benchmarked compilers for Intel architectures recently (i.e. gfortran 4.9 or 5, and recent Intel compilers)? On other codes of mine, the gfortran compiler has become much faster. I wonder if the same is true for ROMS? It ...

jpringle

When you are testing for the effects of pressure gradient error and topography, I would set all the boundaries to closed. I am worried about how the currents are reacting to both the northern and southern boundaries. I would not be surprised if the currents were substantially less if the boundaries ...

jpringle

I have funding available for graduate students at the University of New Hampshire to study the interaction of Western Boundary Currents and continental shelf flows. The applicant must posses strong quantiative skills, with a major in the sciences, mathematics or engineering. Applicants with either ...

jpringle

I must be doing something silly, but it is escaping me. I have just turned on the LMD_* options to implement KPP mixing. I have ANA_STFLUX and ANA_SMFLUX defined, which should give me tracer fluxes and momentum fluxes. Temperature is the only tracer (there is no salinity). When I turned on the LMD ...

jpringle

As always, thanks Kate! I will look at tracmass and see how easy it is to incorporate behavior and vertical mixing. LTRANS will require some recoding to recreate w or omega from u and v ARIANE has a series of weird coordinates to specify time and inititial condition that hurt my brain. If anyone ...

jpringle

Colleagues -- I am trying to do some particle tracking in ROMS output; the model runs were not done by me, and were made with ROMS-AGRIF V3. I have several questions here; I am also asking them on the AGRIF forum. 1) Has anyone used LTRANS v2 with AGRIF? 2) Is the vertical stretching and transform ...

jpringle

This is the middle of the Christmas vacation season in most of Europe and the Americas -- perhaps reposting this in a month or two might get more of a response if you are interested in students from here...

cheers,
Jamie

jpringle

This comment is orthogonal to Sasha's comment -- and his certainly the more interesting of the two. However, it is worth noting that if you have stratification over a sloping bottom, in the presence of vertical mixing, you will have an adjustment of the density near the bottom. If the mixing were ...

jpringle

Dear Linda--

It appears that it passes the fortran tests, and fails the C++ tests. Since you only need the fortran libraries for ROMS, it seems like you should be good to go once you install it.

Cheers,
Jamie Pringle

jpringle

Dear Colleagues -- For the last 6 years, my ocean modeling needs have been well met by a 6 node cluster; each node a dual Opteron-250 with a single core for a total of 12 cores. This system has enough power to meet my modest process-oriented modeling needs; typical runs for me have a grid size of ...

jpringle

Kate, Sasha & Hernan--

Thanks for your replies, they have been very helpful.

Cheers,
Jamie

jpringle

Hi all -- I have a simple question; I fear perhaps the answer is not so simple. I am involved in a couple of efforts to read in ROMS history and grid files, and either plot them or compute other products from them (e.g. Lagrangian particle paths). I have several questions 1) What is the best way to ...

jpringle

Hi all- Several people at my university are trying to purchase a computer cluster with either IBM's Cell Processor (same as in the Sony Playstation) or with many GPUs to use as co-processors. Has anyone tried to modify the ROMS code to take advantage of these exotic (for now) architectures, and what ...

jpringle

Carl- The upwelling code is define to use a constant value of vertical mixing, as you can tell from this code in upwelling.h #if defined GLS_MIXING || defined MY25_MIXING # define KANTHA_CLAYSON # define N2S2_HORAVG #else # define ANA_VMIX #endif and by noting that neither GLS_MIXING or MY25_MIXING ...

jpringle

As evidenced by my silly answer above, I had not run into this problem with the simple domains of my application, so I had not ever worried how to solve this problem. I have thus never implemented a solution. When I have to, I will, but if someone beats me to it, I would be happy to incorporate ...

jpringle

I don't know if this is the issue, but when I was testing Pavel's gridgen, it occasionally threw up nan's if my domain was perfectly rectangular, but if I moved one of the corners by even an infinitesimal amount, the nan's went away. This was a flakey problem, that only occured for certain ...

jpringle

Roughly, the efficiency of the parallelization is reduced by the following * Slow interconnects *Small tiles, so that there is a lot of communications (which scales as the perimeter of tile) for each bit of internal computation in the tile (which scales as the number of gridpoints in the tile). Your ...

jpringle

Try putting the model run with a shell script, executing the shell script, and then logging out.

Our you can use the "screen" utility, which lets you disconnect from an active shell session, and reconnect to it later.

Cheers,
Jamie

jpringle

The efficiency of ROMS in parallel mode is a strong function of 1) the grid size 2) the interconnect speed 3) the configuration of MPI, and 4) the configuration of the model (parameters such as NDTFAST can make a big difference). It is hard to answer a question such as yours with no knowledge of the ...

jpringle

I have a matlab code that calls gridgen and allows you to specify multiple points along each edge, and to specify (roughly) a spatially variable resolution within the model domain. It works well for me, and is reasonably well documented. One caution, however -- if you have a very high-resolution ...

jpringle

Dmitry-

I would be happy to, but I cannot find your email address. You can find my contact info at my web page, http://oxbow.sr.unh.edu .

Cheers,
Jamie

jpringle

ROMS can handle multiple inflow points. This smells like a subtle coding error. My biggest errors in trying to specify point sources in ROMS have occurred because I calculated the positions in matlab, and did not properly take into account the fact that for array start in fortran at index 0 are ...

jpringle

Have you turned on the UV_PSOURCE, TS_PSOURCE and ANA_PSOURCE in the cppdefs.h file for your application?

Jamie

jpringle

Hi all- I have experimented with running ROMS 2.2 on a iMac 2Ghz Intel Core Duo processor, with 667 MHz DDR2 RAM. I used free compilers installed with fink. As you will see, I suspect that I would do better to use the Intel compiler, but I have not done so since for large runs I use my linux ...

jpringle

Craig (& others) I have gone through this on numerous systems. The main trick is figuring out how MPI-whatever runs its various sub-jobs on each system. Does it spawn a csh? a sh? Can you specify? Once you do, you can place the ulimit, etc commands in the appropriate .bashrc .cshrc or whatever. To ...

jpringle

Dear all- If you are using Pavel of CSIRO's gridgen, I have a little chunk of matlab code which allows you to specify the resolution of the grid along the edges of the model domain. If you are interested, mail me. I am not yet distributing it publicly because the rest of my evolving non-interactive ...

jpringle

Thanks a bunch yall. John Wilkin's code worked fine for my use, with minor modifications. It results in a cleaner initialization, and thus is easier for me to explain the initial evolution in my class.

Cheers,
Jamie

jpringle

I am starting a short, semi-idealized run with density features that are only 2-3 times larger than the radius of deformation. As part of the adjustment processes, gravity waves rattle around the domain, and bother the boundary condition. I could get away with a simpler model setup if I did not have ...

jpringle

Dear hive mind- Does anyone have a code that takes an initial density field on a ROMS grid (or any other grid) and a level of no motion and uses it to return a geostrophically balanced flow field? It would be nice if it delt with curved grids... It would not be hard to do, but I am hoping to avoid ...

jpringle

You can find scripts that allow you to experiment with the vertical grid parameters in part of the discussion thread "Stretching parameters - vertical coordinates" on this bulletin board. There is also some discussion of these parameters in the old manual for SCRUM, which can be found at http ...

jpringle

Hi all- I think Kate's problems are, indeed, due to her mexcdf install. Several other folks have used my code without an issue. I am not sure, however, what the issue is, which is less helpful than I would like to be. Also, Kate mentioned This works for ETOPO5, ETOPO2, and now GEBCO, .... If you've ...

jpringle

Hi everyone- A few weeks ago I had this problem, and I created a matlab code that uses Sakov's grid gen to make a matlab domain, useing Rich P's m_map routines and some code I got from Rich Signell to create ROMS grid files from matlab data. It is relatively primitive right now, but it is easy to ...

jpringle

Hi- I do not recognize your particular error message. However, it smells like a problem in the configuration of your mpi system. You should certainly be able to run one part of your job on each processor. However, if you are having troubles running the code, you should try getting MPI to work on ...

jpringle

John- You would be able to handle a freshwater wedge with a small vertical resolution in a layer model, like those from FSU, in which the depth of the layers can vary in time. However, in a model like ROMS where the level positions are fixed in time, you must have about six or more levels IN your ...

jpringle

Hi all-- I wondered if the varying results people get when they try to understand the relative importance of the interconnects could have to do with the relative importance of the 2D timestepping (lots of little messages) vrs. the 3D timesteps (fewer, larger messages). So I ran the benchmark1 test ...

jpringle

Hi all-- Courtesy of Western Scientific Inc, I benchmarked ROMS 2.2 on a dual processor, dual core Opteron 275 rig. These chips have two processing cores per chip, so a workstation with two processor chips will appear to Linux to have four processors. The rig I tested had the following specs: 1) 8GB ...

jpringle

Has anyone used the standard benchmark cases (for examples, those in Rich Signell's benchmarks above) to exam the speed of the dual core operteron processors that AMD has recently released? For the problem I have in mind, I plan to be running on a 5 or 6 node linux cluster, with each node haveing ...

jpringle

Has anyone used the standard benchmark cases (for examples, those in Rich Signell's benchmarks above) to exam the speed of the dual core operteron processors that AMD has recently released? For the problem I have in mind, I plan to be running on a 5 or 6 node linux cluster, with each node haveing ...

Search found 108 matches