I can finally announce releasing application for windows. I am glad that it is finally done and much more users can start crunching.

Radim Vančo (Kyong)

Thank you! This is well worth the wait! I am now off and running!

Yeah, I can finally start crunching for asteroids.

Have you considered to opensource your BOINC application? It allows custom builds of your application by volunteers on machines they have. It also allows potential optimization effort on your application. These two aspects can both raise the computational power you can get.

Cheers,
fwjmath.

Have you considered to opensource your BOINC application? It allows custom builds of your application by volunteers on machines they have. It also allows potential optimization effort on your application. These two aspects can both raise the computational power you can get.

It also allows jerks to create custom builds that do no work and return results that somehow manage to validate.They do it to earn credits for no work and it happens frequently. I'm not saying don't opensource, I'm advising the admin to make sure the validator can spot and reject bogus results else end up with bogus data in the database in spite of increased computational power.

I did get a task for my slow little Windows notebook. It's run 5 hours and shows 84 hours remaining. Glad to see the deadline is long enough to accomodate such slow machines.

Thank you, now lets crunch :-)

Brilliant...I've now a stack of cobblers to crunch for the project..

---

Remember...Always look on the bright side of life.

About releasing the sourcecode, I will manage first the appropriate validator to prevent custom "false" application as Dagorath says.

Thanks for the Windows application, and thanks also for allowing it it run on the old BOINC versions that I use :)

As soon as I've achieved my current tagets at WCG I'll put all of my faster machines onto Asteroids. Milestones and badges here I come ;)

Cheers,

Al.

Thank you very, very much - I am sure this project will now get loads more people producing valuable data.

Ray

Well done

Tasks seem to take about the same length of time on Windows as Linux (a good thing). If anything Windows might be slightly faster (haven't run enough to know for sure, and some seem slightly faster than others; there is variation).
I can still use the VM's for sim1...

---

.

Confirmed, Windows App seems to be slightly faster.
At least one nice thing about Windows.

On average I have windows7x64 being 23% faster than Dotschux in a VM (on the same system). A non-virtual machine might be slightly better?
Some people might also be interested in noting that an i7-2600K @4.2GHz is just as fast as an i7-3770K @4.2GHz. I've noticed this on several other projects too, and haven't seen a project on which the i7-3770K is faster.

---

.

Some people might also be interested in noting that an i7-2600K @4.2GHz is just as fast as an i7-3770K @4.2GHz. I've noticed this on several other projects too, and haven't seen a project on which the i7-3770K is faster.

That _is_ interesting as I've been contemplating an Ivy Bridge purchase. Seems the only thing to be gained by buying Ivy Bridge rather than Sandy Bridge would be PCI-E 3 which could have some benefit if running the new Nvidia GTX 600 series video cards but other than that it seems good ol' Sandy Bridge is good enough.

I am also interested in Bulldozer, AMD's latest technology. Ivy Bridge kicks Bulldozer butt in every test-review article I've read but they haven't tested and compared Ivy vs. Bulldozer on the test I am most interested in which is BOINC. See AMD's response to getting their butt kicked by Ivy is that the test suites used in the test-reviews don't mimic real world usage and that in the real world their B'dozer kicks Ivy butt. I believe they may have a point but the proof is in the pudding and I've not tasted or even smelled such a pudding so far.

AMD claims their 8 B'dozer cores shine best on heavily multi-threading applications and that none of the apps in the test-review suites actually do that. They may be right. Perhaps 1 instance of test app X does not use B'dozer the way it's meant to be used. I (we) run BOINC which spawns several apps that are known to push the core they run on to the max. That's far different from 1 app trying to push 8 cores. What's the skinny on Bulldozer performance on BOINC? Anybody heard? If it's comparable to Ivy then I'll be looking for a Bulldozer CPU and mobo at all the online Boxing Day blowouts because they are priced well below Ivy Bridge. Also, if they're not well received in the non-BOINC world then there may be retailers looking to cut losses and dump Bulldozer stock quick which means even lower pricing.

With more results (of the non-skewed variety) I can now say the Windows app is somewhere between 8 and 18% faster than running on Linux from within a VM. Some of my results were skewed by an mt app that caused more tasks to run than there were threads! So ignoring those, there seems to be quite a bit of variation in individual task performance, and it's likely that other tasks impact upon these to a few percent. Again, its probable that a native installation of Linux would outperform the VM for performance, reducing the real difference between Linux and Windows. I might test this theory at some stage.

I'm still seeing no significant performance difference between an i7-3770K@4.2GHz and an i7-2600K@4.2GHz (+/-1%). Disappointing, but no surprise as they are basically the same processors.
The notable exceptions when it comes to CPU computing are:
The 3rd generation processors have a 0.1GHz clock increase over the i7-2600K, but the i7-2700K matches this anyway and this is irrelevant as soon as you start to OC, which is the whole point of getting the K model.
The 22nm lithography, which coupled with a 77W TDP should offer reduced power consumption (though it's not a lot), but this is only better up to ~4.5GHz, after which it's worse.
25.6GB/s Max Memory Bandwidth, rather than 21GB/s is good for a few projects that benefit from higher memory bandwidth. Maybe 2 or 3 projects, by a few percent.

There are greater potential benefits to do with the GPU side of crunching:
The Intel® HD Graphics 4000, rather than the 3000, could in theory be used by a project to run OpenCl apps. I’ve been half expecting the emergence of a project to do just that, if not one that can span multiple resources (GPGPU/CPU).
The 3770K can support PCIE3.0 and it brings the controller onto the CPU, but this really only benefits people with PCIE3 capable GPU’s and arguably only those wishing to add a second GPU. Even then the benefits are disputable, probably quite small and limited to a very few projects; apps that continuously send over the PCIE are notoriously slow anyway. Fast apps simply avoid PCIE usage as much as possible.
If you want a new system to support two high end GPU’s then the 3770K or the i5-3570K would make sense.

For here, the i7-2600K/2700K/3770K and probably the 3820’s are all roughly on par. They do about 50% more work than an i5-2500K (and similar), and AMD’s 8-Core FX-8320 just about surpasses the i5-2500K (~8%).

i5-2500K (4 real cores, no HT) - Run Time 4,805.70, CPU Time 4,706.43, Credit 120.00
8-Core FX-8320 - Run Time 8,900.27, CPU Time 8,895.40, Credit 120.00

Even if the AMD 8-Core processors are relatively better when it comes to Multi-threaded applications such as SimOne@home (possibly the only existing mt Boinc project), I could only see it pulling slightly away from the i5’s and not eating enough into the i7’s lead to make it a good choice for crunching. Some crunchers have reported that AMD’s 6core predecessors actually outperform their 8 core processors, on some projects, and that's pitting 6 old cores against 8 new cores.

---

.

Don't buy Bulldozers!

I use one of the smaller Bullis (FX-4100) and tested it with A@H, Cosmology@home, CAS, Einstein, WCG...
It was always the same, the FX-4100 was awfully slow. Every other CPU i am using for BOINC, is much faster than my Bulli (I3-2120 f.e.).
Sometimes 2x or 3x faster!

Thanks for the advice regarding Bulldozer, guys. The i7-3770K may not be much better than the i7-2660K but they aren't that much more expensive either and I can't count the times I've later regretted not spending the extra few dollars to get that slightly better feature. It's nice to know the 2660K will be a formidable processor a good while more and I'm glad I own one.

My favorite online retailer just reduced i7-3770K pricing again, just a small drop but every little bit helps. I suspect they'll drop even further on Boxing Day or shortly thereafter, maybe Wrestling Day (Jan. 1) and that's when I'll pounce like a fat kid on a chocolate bar. Unless they reduce the 2660K to some ridiculously low price, low enough to allow for a GTX 690 or 680 in the same order though I am content to wait for pricing on those to drop too.

Thanks for the meaningful measures of how much slower apps-in-VM are compared to not-in VM. I can't say I am surprised. The numbers don't look good for the VM but if it's the only way to get the job done at the moment and you really need/want the job done and don't mind the setup work then it's nice to have the VM option until something better turns up.

ah very nice so there is no need to start the Ubuntu VM anymore ^^ Thx.

---

DSKAG Austria Research Team: http://www.research.dskag.at

Don't buy Bulldozers!

They're pretty good on the road grading apps. Seriously the X6 is still the fastest AMD for scientific work on most projects. In fact on at least one project they're the fastest of all CPUs. Also your assertion might be more helpful if you didn't hide your machines :-)

For some reason, I'm not seeing any credit for the Astroid Tasks my system has done since joining yesterday. (Dell Win7 x64, Core i7, SSD)

My Milkyway and Rosetta are reporting ok.