BOINC, Burp, and Benchmarks......Oh My!

[CarcinogenX]

So, I’ve read up on BOINC and optimizing a little but it appears that I am still doing something wrong.
First, I understand that this is an alpha project, but others are having a much better go at it than me. Looking at my results, it’s clear that I am getting shafted most of the time. I spend hours on a project, claim say, 200 credits, but am granted far, far less. While the other guy and his 300mhz Celeron fart out 20 minutes of cpu time, claims 5 credits and get 100. It’s a bit of an exaggeration but what gives??
I noticed that Loki has a somewhat similar CPU to mine and looking at his results, he generally receives what he is granted and sometimes far more. I’m running just plain old BOINC 10? Should I be doing something else?
One more thing I don’t get. My system is circa 2005/6 and when I run a benchmark, I get higher numbers than most computers out there. Why is that happening?
My current results are:
2885
5223
Xpod has a C2D E6850 that gets lower benchmarks than me. I know that cannot be correct. Should I be setting my multiplier to 1x before running a benchmark on a project?

Any help would be much appreciated.

[mitchellds]

I feel your pain. I have the same problems. Here is one of my pc's showing credit claimed and granted. I could only find one result that they gave me more credit that I asked for. I'd say that 95% of the credit returns less than 30% of was was claimed. I wonder what causes this poor estimation? Is it the project applications, or the way boinc estimates wu completion/credit?

Maybe someone can post to the project admin for answers?

240.69 122.79
247.98 70.04
218.91 83.36
144.40 37.34
259.17 70.73
163.14 33.53
227.19 51.81
126.60 50.24
217.80 48.95
167.25 66.53
155.29 41.32
240.69 122.79
230.46 74.59
207.77 121.93

0.94 1.01

[NeoGen]

Burp grants the middle claim out of the first three that arrive for each workunit.
Say for instance three people return a result for a workunit, and the first claims 5, the second claims 10, and the third claims 15. Actually, it's independent from the order by which those three arrive, everyone is given 10 as soon as the third result comes in.
This is for protection against people with optimized boincs that make huge claims, but since that sometimes new benchmark values are achieved with different (stock) boinc versions on the same machine, it is indeed annoying to not get what we claim.

Guess it's time for them to revise their credits strategy...


P.S. - Also... Welcome to the forums CarcinogenX :icon_wink:

[Strongbow]

In addition and one that I really have a gripe about is regarding the average work done rating! ...I can be crunching their day+ WUs and my average drops off pretty much immediately, hence the reason why it is hard to actually get a realistic figure to the amount of daily points you gain!

[Bender10]

This is an often debated problem in BOINC projects. I may not be able to nail this down for you, as my information comes from the "www.apsathome.org" site (which seems to be down). If the site comes back up, check there. Bear with me during my short blurb.

Also, Alpha stage projects (and the credit for WU's) tend to be a little quirky for the testers... The designer for BURP is hopefully working on what they call 'Equalizing' the amount of credit awarded, or how is is awarded.

Remember, you are in the mystery world of 'Opimized Clients', which through smoke and majik, provide higher point per WU's than normal clients (most times). When 'Optimized Clients' don't werk, I like to think the project designer did a good job designing his points algorithm. :)

And BURP uses a 'Qorum of 3' to award points. For that, They send the WU to 3 computers and wait for the results.

EDIT: Ooops. They try to get 3 cpu's to agree on a score. If that does not happen, the WU keeps getting sent out. Then they filter for errors/totals/successful results. Kinda complicated. see below.

application Blender
created 23 May 2007 16:33:33 UTC
name 450in0.zip__ses0000000450_frm0000000209_prt00025.w u
minimum quorum 3
initial replication 4
max # of error/total/success results 25, 35, 20

Click on a "Workunit ID" number, and you will see the above information. This will tell you the critiera being used to find 'successful' matching results.

Then they normally throw out the high and the low and award all computers the middle value (in a nutshell).... So yes, a slow machine can get more points than they have claimed for a specific WU. Kinda squirrely...

(most crunchers don't like Qorums anyway...).

Any comments? or corrections?

Back to werk I go....:icon_rolleyes:

[Lagu]

CarinogenX!

Welcome to our forum! I hope you can got an answer on your dilemma. I´m nor the right person for your problem bat I´m glad se a new "face" into our forum. Are you crunching for AMDusers?

Lagu:)

[CarcinogenX]

CarinogenX!

Welcome to our forum! I hope you can got an answer on your dilemma. I´m nor the right person for your problem bat I´m glad se a new "face" into our forum. Are you crunching for AMDusers?

Lagu:)


Thanks Lagu,

I'm providing whatever help I can with the Burp "race" for the AMDusers team.
I'm still need a little clarification though.
I get an 8hour WU that, through a nasty vortex of space/time takes maybe 12+ hours to complete.
The "other" guy and his 300mhz Celeron must be getting a considerably smaller WU than me, because it is completed in the same or less time than me.
So I don't get the connection that I and the Celeron guy have that should grant us the same credit.
And I'm not here to bitch or complain, I am curious and just want to understand the process better.
Also, someone else mentioned it too that the long WU's kill your RAC. It seems like it's based on a very short time frame, shorter than other projects.
Nobody mentioned anything about benchmarks either. I don't know how much of a role they play and why mine are so high. I read that some optimizers will beef up your benchmarks, but I am only using the latest version of BOINC.

[CarcinogenX]

I think the real answer is for all of us to switch to really old Sempron's :icon_wink:

[Lagu]

I too run BURP on my Intel Core 2 Duo 6600, 2,4 GHz and I earn relatively good points. I began crunch July 7 and have now 4,000 points.

Here is my Boinc Benchmark:
2007-07-25 01:59:20|| Number of CPUs: 2
2007-07-25 01:59:20|| 2240 floating point MIPS (Whetstone) per CPU
2007-07-25 01:59:20|| 4691 integer MIPS (Dhrystone) per CPU

I have noticed BURP has his own Benchmark as chows here:

Measured floating point speed: 2,244,75 million ops/sec
Measured Integer speed: 2,992,23 million ops/sec

That is strange. What is valid? BURP or Boinc or both? On other project Boinc benchmark is the same on the projects page but not here?

Example of CPU-sec, Claimed and Granted credit:
34792, 139,89, 117,19
27718, 84,0, 84,0
27800, 84,25, 113,85
27784, 91,61, 126,04

I received mostly WU´s as takes between 4,5 to 6 hours. I also only receive 2 WU´s per time, crunch them and get 2 new the whole time.

On my 3 other computers I run MoneyBee. Have you an older Intel PII you can run MoneyBee on this computer.

I haven’t owe clocked any of my computers because we have summer in Sweden and the computer room gets too hot. :)

[CarcinogenX]

100.98 - 23.14
137.63 - 34.76
43.31 - 23.07
156.27 - 61.92
157.94 - 81.10
124.96 - 58.45

It’s like a giant BURP credit tax
This is really out of hand.

We are going to need a lot more people to get ahead of Xpod. We are still 2000 RAC behind Xpod.

There is a lot of dissention among the ranks here with BURP and I don’t think people will stay long without a change. I’m all for BOINC, I think the idea behind it is great, but like many others have said here, without credits, without something to show for your work, it’s just not that appealing.
What’s been the best project for an AMD anyway?

[Nflight]

There is a lot of dissention among the ranks here with BURP and I don’t think people will stay long without a change. I’m all for BOINC, I think the idea behind it is great, but like many others have said here, without credits, without something to show for your work, it’s just not that appealing.
What’s been the best project for an AMD anyway?

CarcinogenX It has been nice to see you take such an effort in an alpha project, these are the worst Projects to delve into without knowing whats out there in the rest of the 60 or so projects Boinc has to offer. The BEST BOINC project to become involved in for the AMD's is really any project that is out of Alpha Status and Beta Status as well. There are even some Permanent Testing Status ones you find.
Here is a list of Beta. Alpha and Permanent Testing Platforms any others not mentioned here are in Full active projects.

Beta Projects: QMC@Home, MalariaControl.net, Nano-Hive@Home, Spinhenge@home, RieselSieve, Proteins@home, Rectilinear Crossing Number, Project Neuron, Lattice Project, PS3GRID, Superlink@Technion

Alpha Projects: PrimeGrid, uFluids, TANPAKU, Leiden Classical, XtremLab, Docking@Home, Chess960@Home, BURP, Cosmology@Home, DepSpid, HashClash, Distributed Rainbow Table Generator, vtu@home, APS@Home, WEP-M+2 Project, Zivis Superordenador Ciudadano, RenderFarm@Home, Gerasim@home, Belgian Beer@Home, SciLINC

Permanent Testing Projects: SETI@Home Beta, Rosetta@Home Alpha (RALPH), BOINC Alpha, ABC@home Beta, Pirates@Home, LHC@Home Alpha

Everything else is considered open season for crunching.

As for AMD preferred projects let someone else assist you with determining that factor of crunching, say NeoGen or AMDave are experts in that realm.

[AMDave]

Excellent post there Nflight!

I don't see much BURP dissent. There are some firm opinions from those who prefer more stable projects which is understandable as BURP is an Alpha project, but allowing for the rough edges of an Alpha project, BURP does alright in the grande scheme of things.

As far as AMD advantage goes, I still cannot go past Riesel Sieve Classic (Unless you have a Mac-G5 using JoeO's custom compiled client)

As far as BOINC goes I have found the current BURP credit awards to be comparable with some other projects for my middle-of-the-market CPUs on closer inspection some CPUs do seem to be disadvantaged on BURP currently . Otherwise RieselBOINC is giving some decent credit and uFluids is on the kinder side as well.

It simply depends on your CPU type and available RAM. If you have and AMD64 based CPU (either single core or SMP) then you want to head for the BOINC projects that have specially compiled clients for AMD64 rather than those projects that simply allow the server to send a 32-bit client to an AMD64 CPU.

Augustine has been following (and championing) this 32-bit to 64-bit adoption and you can follow his updates on the BOINCstats forum here
http://www.boincstats.com/forum/forum_thread.php?id=1774

I will not run a system under 2GB RAM anymore so I don't tend to hit any RAM issues very often although I run a lot of services on my box that I run linux on so every once in a while it rejects a WU that needs more RAM than what is available, but the other boxen just plod along now.

[AMDave]

Welcome to the forum CarcinogenX and thanks for getting in with the questions up front.

Now is a great time to explain my previous comments from a programmers' point of view in something like laymans terms...I hope I do it justice.

Firstly, each project contains a weights table that evens out the credit distribution across CPU platforms.

Whilst a project is going through development those weights may be altered to help balance out points allocation.

Some CPUs finish certain types of functions faster than others and that can directly affect the amount of credit that gets claimed for a work unit.

When a project's core client is modified (the bit of code that does the real work - not the BOINC client itself) a chunk of code that gets used often may get changed from being Integer to Float dependent or SSE to SSE2 optimized (for example) and that may change the CPU platform that best suits it.

In Alpha and Beta projects, core clients may get recompiled often so it is hard for the project-lead to keep the weights table updated (more so in the case of an Alpha project).

During this development stage it is the focus of the project team to get the project core-client to perform it's task as well as possible. Later on in Beta they are able to focus more on the BOINC platform balance that will keep most members happy and coming back for more work to do to further the cause.

As the project becomes more stable and the client updates become less frequent, the weights table may be more accurately assessed and updated.

Many of us have (or have had) fairly "interesting" investments in hardware that we have dedicated to our Distributed Computing commitments. Some more than others. Hence it is to be expected that those with the greatest investment will be drawn towards the projects that are past Beta or are at least fairly well advanced in their Beta stages so that the amount of human time and computer time is used to the greatest advantage and an absolute minimum of effort is lost. (Note that - Efficiency does not always equal effectiveness)

Committing to Alpha projects does pose risks to the aim of "recorded" contribution as from time to time mistakes happen and points can be cleared or simply "lost" due to process / hardware / software configuration failure. It happens. Some of us have lost 50K, 100K or more credits in the quest to help test and develop these projects, but doing so knowingly of those risks. Like I said - it happens.

So, when choosing projects, if you have expectations of stability, you should always do a bit of reading first before selecting and jumping onto a project. That way you are less likely to be disappointed.

For me, I like DC'ing on the edge and contributing in the early stages of a project. That's just the way I am.

Well, I guess this is mostly opinion rather than information, but I hope it helps you to achieve your expectations in the DC-quest.

Once again, welcome to the AMD Users forum.
We look forward to getting to know you.

[PoorBoy]

I don't see much BURP dissent. There are some firm opinions from those who prefer more stable projects which is understandable as BURP is an Alpha project, but allowing for the rough edges of an Alpha project, BURP does alright in the grande scheme of things

Dave, BURP has been Online now for over 2 years, yet Janus is still using the Prehistoric Credit Granting Method of using the middle of 3 or out with the High & Low. That Method is so Passé anymore, BURP may be the only Project that even uses that Method anymore.

Heck anymore any of the new Projects Developers can be talked into within a few weeks of going to Fixed or Sliding way of Granting Credit yet Janus still plods along with some 18'th Century way of Granting the Credit after over 2 years.

I don't know, I guess my Quads have spoiled me in some way, I used to think if I could do 3000 Credits a day I was doing great, now if I can't hit 30,000 Per day or close to it it's been a bad day ... :icon_lol:

[CarcinogenX]

Thanks for the reply guys. It’s a lot to soak up. I guess it just seems kind of unfair in a way but, that is life. And I did see someone else here ( I forget who) who was consistently getting even less credit per WU than me. I vented, and now I am better.

I kind of worry that I one night I will wake up to a mushroom cloud of what was once was my “work” computer. Probably not the smartest thing to run it 24/7 @ 100% for weeks straight. I just want to get the max throughput I can while it is still alive. I’m thinking I should probably build another unit and use this one a little less. At work I use 4 computers (all non AMD) and I used them for BOINC…….that is, until the company tattle-tale found out. Before that he made a grand scale attempt to get me fired for using a MAC to transfer an album to an employees Ipod. He is a real interesting character.

My devotion to BURP is simply because we are banding together to come from behind and overtake the Intel team. That’s enough for me to stay. And BOINC gives me one more thing to ponder in my car, where I spend a lot of time.

The photo was taken on a Saturday afternoon. No accidents, no construction, just lots of people.

I’m thinking of buying a ThinkPad T61 with a C2D. Does this make me a bad person?

[Strongbow]

80

I feel much better now that your steering wheel is on the 'right' side! :icon_wink::icon_lol:

[Nflight]

Strongbow you have left our merry men of Burp crunchers, I suppose you had enough of the turmoil of running a project that has a major maladjustment! I am going to tolerate it just a little bit longer, and go back and visit an old friend I left many many months ago! :sad5:

[Strongbow]

I have! ...got bored with it, I don't normally bother too much with points but I do like to see a fair RAC rating and they just haven't tuned it yet so got out after a few weeks stint with them to see what I've been missing.

[liuqyn]

I just shut down on burp again for awhile, one of my other projects is coming to a close soon and I'm trying to chase down 1st place (in the team anyway) before then. I'll be back.

[Strongbow]

CarcinogenX, apologies but I didn't even say hello to you as a new joiner!

Hello and a big welcome to the team! :icon_mrgreen:



I’m thinking of buying a ThinkPad T61 with a C2D. Does this make me a bad person?

Errr, possibly, depends what you're gonna do with it! :icon_wink: ...I've always thought the ThinkPad's were well made but a bit over priced and under spec'd! will it be for personal use or work?

[CarcinogenX]

Oh Crap!!

Sorry Strongbow, I replied to this but in the confusion of an alcoholic haze, I might not have hit the "post" button. Nice to meet you and everyone else.

So, about Thinkpads.....I looked at all of others offerings of the "Santa Rosa" platform and you are right, Lenovo is the most expensive and Dell is the cheapest, but Dell's, you know, they are just so......Dell. And Asus has blinking lights and other features I don't want. Frankly, it looks like sh*t, as do all the other models I saw. But the Lenovo I saw a T60 at the local Micro Center, that was a perfect match. It took 3 security guards to drag me away from it. I'm going to get it one way or another.

[mitchellds]

well if you want to 30-50% more credits for your efforts than this project, join us on the Cosmo project.

[CarcinogenX]

I think I'll do that. I already reached 10k with RS.

Update: They are not accepting new accounts :(

[PoorBoy]

I think I'll do that. I already reached 10k with RS.

Update: They are not accepting new accounts :(

Check your PM's, I sent you the Info to get in unless Scott has turned off new Accounts all together ...

[CarcinogenX]

Thanks Poorboy,

I'm in and crunching as we speak.

[PoorBoy]

Thanks Poorboy,

I'm in and crunching as we speak.

Great, the more pressure we can put on the French Team the more likely they will not try to keep pace with use as they are into other Projects quite heavy at the moment too ... :)

[King-xPOD]

the picture pretty much says it all ;)

http://img91.imageshack.us/img91/8860/xpodruleswa8.jpg

[Frederic Brillouet]

the picture pretty much says it all ;)

http://img91.imageshack.us/img91/8860/xpodruleswa8.jpg
praise yourself lucky for as long as it lasts :icon_lol:

[Nflight]

the picture pretty much says it all ;)

Yes it does: but, the signature really tells a better story! Great Job there X-Pod ! You have got a great output, are you interested in participating in our up and coming Race this weekend? Its a Medical Project which looks like one of your major focuses is doing some research for the good of mankind. Care to share some CPU cycles for the good of the Project?

A little competition always brings out the hardware bugs we never knew existed yet shows the world your willingness to help depending on the cause. Care to ruffle some feathers and show off a little! :icon_razz: