[halimedia]

Originally Posted by Todd Madson

I wonder how you would set it up so that 2 or 4 processors would divide the workflow. Would it create a measureable speedup?

The worker would have to be multi-threaded insead of single-threaded. Individual threads of the computation would then automatically be distributed to all processing cores by the kernel. There are a number of reasons why the SETI-workers have never been multi-threaded:

- Multi-threaded coding is far more labor intensive
- The end result (i.e. RAC) of one machine wouldn't be any better (rather a touch worse, most likely)
- You couldn't allocate just a fraction of the cores to BOINC, which is an important feature of BOINC in high-availability server environments.

HTH,

Ron

[Knightrider]

I came across this web site, which deals with Parallel computing and clustering.

It occurred to me that this type of system (Clustering) may allow BOINC to be able to process very large work units by using two or more remote computers to process different parts of the same wu and assemble the results either on one machine acting as a surrogate server and it reports, or onto a server proper collecting and unifying the separate results.

It may also be a way of improving the work rate for multiple cpu machines by treating each wu in a cluster style and portioning it out to the available cpu's.

it was just a thought.

K.

[halimedia]

Since the BOINC infrastructure is a distributed computing platform by itself, the whole SETI-crunching community already represents an enormous distributed cluster (what an oxymoron!). Additional clustering solutions would therefore be of very limited advantage...

[BTBlomberg]

Originally Posted by alexkan

v5 prints its identifying information to stderr every time it starts. If you pause computation (and BOINC is set up to not keep suspended applications in memory), the application will print its information again once computation resumes. Crunch3r's app used to do this as well, I think, but the problem is exacerbated by the fact that your G4 500 takes a long time to crunch in the first place and winds up being interrupted quite a few times.

I got you. Since this is a PowerBook and I move it around during the day (unplug, move, plugin) that makes total sense. It was not problem, just an oddity I was pointing out. All other machines are desktops so unless a restart is needed mid WU I guess most people would not see this. Also, as you say a faster Laptop with shorter times would likely have fewer interruptions per WU. Always learn something new. Adds to teh point that I have known for a while that I need a new laptop.

Thanks!

[beadman]

Originally Posted by BTBlomberg

I got you. Since this is a PowerBook and I move it around during the day (unplug, move, plugin) that makes total sense. It was not problem, just an oddity I was pointing out. All other machines are desktops so unless a restart is needed mid WU I guess most people would not see this. Also, as you say a faster Laptop with shorter times would likely have fewer interruptions per WU. Always learn something new. Adds to teh point that I have known for a while that I need a new laptop.

Thanks!

My iBook is only a year and a half old, but I'm already trying to figure out how to justify to my wife my need for a new MacBook Core Duo. I'll probably have to wait until next spring when I get my tax refund. Maybe I can offer to send the iBook to our son and daughter-in-law, since they're stuck with an iMac G3 333Mhz and OS 9.

beadman

[Gecko_r7]

Originally Posted by beadman

My iBook is only a year and a half old, but I'm already trying to figure out how to justify to my wife my need for a new MacBook Core Duo. I'll probably have to wait until next spring when I get my tax refund. Maybe I can offer to send the iBook to our son and daughter-in-law, since they're stuck with an iMac G3 333Mhz and OS 9.

beadman

Doesn't she realize that the laptop is really for her?
Ilife 06' and other goodies that make pictures and vid clips so fun.

My wife can't wait for hers...now.
And Seti will be happily crunching away in the background as a service.........

Worked for me.
Good luck!

[BTBlomberg]

Latest v5 result on the old PB G4 500. It is in the 30 point range and I have some others to compare it to from v4.

THis finished in 32,009.92 sec. (8:53 hours) and claimed 32.34 but got 21.25 because somehow some PC users chrunched it on "core_client_version-4.13" for 9.90 and core_client_version-4.45 for 21.25. the other user was on 5.13 so they got 32.33 which is what ti should have been. Looks to me that this was a Old WU for these old clients that are horribly calibrated (4.xx) and becasue of it they bring down the whole quarum. Sux. I thought they no longer were getting WUs. Maybe they were reissues of failed WUs.

Anyway, I have this to compare to 3 v4 WUs:
33,763.41 sec. (9:23 hours) claimed 29.10 Received credits 29.09
35,207.26 sec. (9:47 hours) claimed 29.95 Received credits 29.95
33,553.58 sec. (9:19 hours) claimed 29.14 Received credits 29.13

Average:
34,174.75 sec. (9:30 hours) Received credits 29.39

So there was some improvement there, about 40 mins. Not sure if they old Seti WUs, but the size and credits are right. I really thought old cleints could not used anymore though.

[beadman]

BTBlomberg:
Here's a comparison for you. My iBook 1.33 GHz with v.5, last six valid results

Secs Claimed Granted
8429 12.94 12.94
17831 32.4 32.4
17911 30.68 30.68
17984 30.64 30.64
20242 34.53 34.53
22396 48.36 61.53

The average of this is 554 seconds/credit. It looks to me like the principal difference between yours and mine is clock speed, which implies to me that we're both about where we should be. As an aside, I checked this afternoon on my einstein output for this same computer and using Bernd's 4.56 client and got an average of 396 seconds/credit. Inverting these numbers, that's 40% greater credit per cpu second crunching einstein.... I switched my iBook from 75% SETI/25% Einstein to 80% Einstein/20%SETI.

beadman

[fran]

I had the same problem with this one, and this was with the standard (5.4.9) client and worker on my windows machine.

http://setiathome.berkeley.edu/worku...?wuid=80775341
My machine 57561 seconds, claimed 61.42, granted, 47.80
One intel machine with "core_client_version>4.45<" claimed 47.80
One intel machine with "core_client_version>5.2.2<" claimed 39.25

Compare it to this one:
http://setiathome.berkeley.edu/worku...?wuid=80870239
58010 seconds, claimed 60.89, granted 60.89 (which is normal for this machine)
The other two machines (windows and power mac) both claimed and granted the same amount, using 5.2.13

Erik

[mac1896]

Originally Posted by Todd Madson

But it typically hasn't worked like that - in the present case of my machine, both
processors work on a separate work unit at the same time.

On a quad, it works on four at the same time.

I wonder how you would set it up so that 2 or 4 processors would divide the
workflow. Would it create a measureable speedup?

I don't know how it would work either, but I DO notice on my DA 1.8GHz duallie, that I CAN make BOTH PROCESSORS work on only ONE WU.

The above statement depends on the accuracy of Activity Monitor.

I have never run the WU all the way through to see if it will validate or not.

Strange thing is, that the processors only run at about 50% capacity each, so that there is no gain in time on the given WU.

I'm wondering if this is something that can be further exploited (not like exploited in a cheating way).

[BTBlomberg]

What's the Difference. One WU done in a little over half the time (due to managment overhead) or two WUs done at regular time. Basically in the same time you get two WUs finished. You may report a WU back faster, but it still takes time on two CPUs so it's the same or greater time. I say greater becasue when you do something like that one prosessor still needs to manage the other one so that should slow down the overall process. One at a time on two is better. 1 CPU will allways complete a little faster in real time because one processor will get tied up with OS activities more so they will diverge in processing position, but each will still produce about the same # of WUs with the first getting hit with any other activity on the machine.

Overall two CPUs for Two WUs is really better.

[liebsmaschine]

Originally Posted by Gecko_r7

And Seti will be happily crunching away in the background as a service.........!

"Oh, honey, you don't need to take the iBook with you today...no, don't put it to sleep...just leave it on the desk open...in fact, just leave it open on the desk every day..."

When I first got back into running SETI/BOINC three or so months ago, I vowed that I would NOT LET it determine how I used my computer and whether I took my computer (and let it sleep all day) in my bag.

In the last month, it's been running 24/7 on my nightstand, and I'm hesitant to run iTunes, leave apps open, or even to activate Dashboard.

Oh, well, it's all about the science, isn't it?

[Gecko_r7]

Originally Posted by jackal

In the last month, it's been running 24/7 on my nightstand, and I'm hesitant to run iTunes, leave apps open, or even to activate Dashboard.

Jackal, I almost fell out of my chair laughing so hard!!!
The G4's been 24/7 on Seti since 03. I never leave aps open.
Since installing on my laptop, poor IBM has been running 24/7 for 2 years (with shutdown/reboots every 3-5 days since Windows gets more unstable the longer it's up).
I don't take it with me on bus. trips unless I KNOW I'll have to use it, and it irks me when I have to actually miss 4-6 hours on a plane flight. (battery is only good for 2 at full speed).
Pretty darn ridiculous. We may have to start a support group and meet at the YMCA every Wed. night.

On topic, v5 has been flawless w/ 30 WUs crunched. No invalid WUs, no errors specific to the G4. Smooth sailing!

[alexkan]

As the author of the optimized client, let me definitively put a rest to the questions about processing work units in parallel--the current client doesn't do it, and it's more efficient at this point for each worker to be independent. Think of it this way: the cores on your machines are still dividing up the SETI work among themselves, just with much larger granularity, and without any need for the cores to synchronize with (read: wait for) each other.

If it looks like your cores are working on the same work unit, they're probably duplicating a lot of work. You don't want this to happen.

Speaking of specific to the G4, I've posted the G4-specific compile athttp://tbp.berkeley.edu/~alexkan/set...-ppc-v5-g4.zip. The difference in speed only amounts to about 5%. It's less than I was hoping, but G4s need all the speed that they can get. Don't forget to generate your wisdom if you want an extra edge!

[wrhowell]

I see the v5 worker has 3 threads. Only 1 for the computational work. I assume the other 2 are for graphics. I've seen that there is a -nographics option for the worker, but how do you get the CLI boinc client (5.4.9) to start each worker with the -nographics option, and does it have any impact on run time compared to not specifying any options?

[fran]

Originally Posted by alexkan

Speaking of specific to the G4, I've posted the G4-specific compile athttp://tbp.berkeley.edu/~alexkan/set...-ppc-v5-g4.zip. The difference in speed only amounts to about 5%. It's less than I was hoping, but G4s need all the speed that they can get. Don't forget to generate your wisdom if you want an extra edge!

THANKS!! Already installed on both my G4s. What's this about "generate your wisdom"? I've seen this file referenced in several threads, but have no idea what it all means. What's a wisdom file, and how do I generate it?

Thanks again,
Erik

[liebsmaschine]

Originally Posted by alexkan

Speaking of specific to the G4, I've posted the G4-specific compile athttp://tbp.berkeley.edu/~alexkan/set...-ppc-v5-g4.zip. The difference in speed only amounts to about 5%. It's less than I was hoping, but G4s need all the speed that they can get. Don't forget to generate your wisdom if you want an extra edge!

Is that 5% better than the G5 v5 compile or 5% better than the G4 v4 compile? (Say that 5 times fast...)

[alexkan]

Originally Posted by jackal

Is that 5% better than the G5 v5 compile or 5% better than the G4 v4 compile? (Say that 5 times fast...)

It's 5% faster than the G5 v5 compile. v5 creams v4 on G4 regardless of which compile you're using.

[liebsmaschine]

Originally Posted by zombie67

THANKS!! Already installed on both my G4s. What's this about "generate your wisdom"? I've seen this file referenced in several threads, but have no idea what it all means. What's a wisdom file, and how do I generate it?

Thanks again,
Erik

Try <a href="http://forums.macnn.com/showthread.php?p=2994256&highlight=wisdom#post2994 256">this post</a> for alex's original instructions and the 300,000 posts that follow for help with issues when running it.

Basically, you'll download the zip file linked in that post (oh, all right, <a href="http://tbp.berkeley.edu/~alexkan/seti/fft_test3.zip">here's the link</a>), unzip it, run it with ./fft_test3 (or whatever the unzipped filename is--I forget) in Terminal, and when it's done, look for the wisdom.sah file (it should be in whatever directory you ran fft_test3 in) and copy that to /Library/Application Support/BOINC Data/projects/setiathome.berkeley.edu/. You may end up replacing a wisdom.sah file that's already there, but that's OK (and better).

HTH.

[fran]

Originally Posted by jackal

Try <a href="http://forums.macnn.com/showthread.php?p=2994256&highlight=wisdom#post2994 256">this post</a> for alex's original instructions and the 300,000 posts that follow for help with issues when running it.

Basically, you'll download the zip file linked in that post (oh, all right, <a href="http://tbp.berkeley.edu/~alexkan/seti/fft_test3.zip">here's the link</a>), unzip it, run it with ./fft_test3 (or whatever the unzipped filename is--I forget) in Terminal, and when it's done, look for the wisdom.sah file (it should be in whatever directory you ran fft_test3 in) and copy that to /Library/Application Support/BOINC Data/projects/setiathome.berkeley.edu/. You may end up replacing a wisdom.sah file that's already there, but that's OK (and better).

HTH.

Thanks for the exact pointer. It drives me nuts when people just point you at threads miles long, and hours to read. And then half the time it doesn't really answer the question.

It seems that Alex is saying that this wisdom file can be used to benefit, with any client or worker. True? Even Intel macs using the standard BOINC Manager and worker?

Thanks,
Erik

[alexkan]

Originally Posted by zombie67

Thanks for the exact pointer. It drives me nuts when people just point you at threads miles long, and hours to read. And then half the time it doesn't really answer the question.

It seems that Alex is saying that this wisdom file can be used to benefit, with any client or worker. True? Even Intel macs using the standard BOINC Manager and worker?

fft_test3 isn't Universal, so it may not generate good wisdom for Intel Macs. I could probably roll a i386 or Universal binary later on, though. It's just that I would be flying blind without Intel Macs of my own to test compiles on.

[fran]

Here's another bizarre one caused by "<core_client_version>4.45<"

http://setiathome.berkeley.edu/worku...?wuid=81177321

my ibook spend 22399 sec. and claimed 60.65, which is consistant with other WU taking ~22k sec.

This other guy spent 51141 sec, and claimed 110 (!).

[BTBlomberg]

I wonder if this is someone that has a Stock BOINC 4.45 setup that update the SETI Cleint to Stock SETI_Enhanced and somehow the OLD BOINC does it's botched up calibration on the WU. If this is the case BOINC should kill use of 4.xx versions of BOINC and force users to upgrade becasue they are messing things up for the rest of us, especially with the lower claimed credits. I don't think we mind the higher ones though. It will go the next highest one from the first 3 reported and that is more likely to be on target. it may not be that big of a deal but I hate crunching for that long and getting robbed of credits because of someone elses bad WU Claims.

[brysonda]

I finally had a moment to check the forum yesterday and discover all of the optimized enhanced worker goodness. So I've switched over my collection of machines (to v5) and will hopefully be crunching my way back up in the rankings. (My eyes are fixed on you, halimedia )

In this line of thought, I figured I'd throw in another example of how awesome Alex's client really is:
http://setiathome.berkeley.edu/worku...?wuid=81123887

This workunit has the great example of pitting my Quad versus another dual core powermac running the standard worker (I'm guessing a 2.3 GHz).


Thanks much for all the hard work Alex. It is really appreciated.

[Todd Madson]

I suspect there's a lot of machines out there still running the old Boinc manager.

[tony.escobar]

Originally Posted by BTBlomberg

I wonder if this is someone that has a Stock BOINC 4.45 setup that update the SETI Cleint to Stock SETI_Enhanced and somehow the OLD BOINC does it's botched up calibration on the WU. If this is the case BOINC should kill use of 4.xx versions of BOINC and force users to upgrade becasue they are messing things up for the rest of us, especially with the lower claimed credits. I don't think we mind the higher ones though. It will go the next highest one from the first 3 reported and that is more likely to be on target. it may not be that big of a deal but I hate crunching for that long and getting robbed of credits because of someone elses bad WU Claims.

The real variability here is in versions prior to v5.2.6. The newer versions count FPOPS (Floating Point OPerationS), while the earlier versions use benchmarking. There's a wide range of credits claimed.

Take a look at the unit that Zombie referred to. His G4 iBook took 22,400 seconds and claimed 60.65. Both of the other machines used v4.45. One is a 1.7GHz Celeron running WinXP SP2 that took 45,643 seconds and claimed 65.45. The second machine is a 2.4GHz P4 running Win2k SP4 and took 51,141 seconds and claimed 110.28. Side Note: A G4 iBook beating those PCs by 51% and 56%? Nice work, Alex!!

For this WU, zombie got 5 extra credits. But depending on what other computers and versions are involved, it could have been a lot lower or a lot higher.

I've been tracking many of my WUs since starting Enhanced. I have about 30 WUs where a pre-5.2.6 version was involved. In one example, I recevied 22 "points" more than I claimed; in the other examples, 12 and 15 less. I have several examples where my WU was completed by two other users using pre-5.2.6 versions. They claimed credits ranging from half to 2.5 times greater. Good thing I was there to keep it fair!

QS

[arkayn]

Here is one where I got 93.64 instead of 58.84 that I claimed, both of the high claimers were using 4.45.

http://setiathome.berkeley.edu/worku...?wuid=81214491

[fran]

Originally Posted by arkayn

Here is one where I got 93.64 instead of 58.84 that I claimed, both of the high claimers were using 4.45.

http://setiathome.berkeley.edu/worku...?wuid=81214491

Claimed credits:
58.69
58.84
93.68
111.61

Interesting. I thought the granted was supposed to be the middle claim, or if there are more than 3 returned, the average of the middle claims. Do I misunderstand (again)?

[Gecko_r7]

For G4 lovers out there.
The latest Ref WU times for Alex's v5-G4 compile on 03' MDD w/ Giga DP 1.33
BTW, all runs are w/ latest wisdom.sah

AlexKan v5-G4 (Test5 6.9.06)
real 258m57.563s ( = 15537.563s)
user 258m24.204s
sys 0m31.797s
wu_cpu_time = 15298.139857

v5-G4 vs.v5

real: +7% faster!

Stock 5.13 Worker (Test1 5.24.06)
real 499m12.054s ( = 29952.054s)
user 498m11.342s
sys 0m57.878s
wu_cpu_time = 29915.352618

v5-G4 vs. Stock 5.13 worker

real: +93% faster
wu_cpu_time: +96% faster!!!

Holy Smokes!!! 2x as fast as stock!
Me thinks my lowly, antiquated, "good as dead" G4 is going to be kicking some x86 butt!

Alex: You are THE MAN!
Thanks a bunch!

[arkayn]

I'm not complaining on that issue, of course it was not processed on my Mac but on my Dell Laptop.

[BTBlomberg]

Originally Posted by alexkan

Speaking of specific to the G4, I've posted the G4-specific compile athttp://tbp.berkeley.edu/~alexkan/set...-ppc-v5-g4.zip. The difference in speed only amounts to about 5%. It's less than I was hoping, but G4s need all the speed that they can get. Don't forget to generate your wisdom if you want an extra edge!

Shoot, once again I go a day or so missing a post like this. Thanks for the bump. I am switching now.

[amrad9]

Alex

Is there a way to tell the worker to use the wisdom file that has been generated locally and not create one on its own. Only having it create one if one is not found. It has got to take some time for the worker to create that file. Time that could be used crunching the wu. I don't know how much of a code rewrite or speed improvement there might be. It's just a thought.

Jon P. (amrad9)

[RandC]

Hi Alex,

Got the following information message (which I assume is no big deal but would report it) on a validated WU using your seti_enhanced-ppc-v5 worker: "Number of results detected exceed storage space allocated". Result ID is http://setiathome.berkeley.edu/resul...ltid=339759391

By the way, thanks so much for your work on both seti and set_enhanced ALTIVEC clients for the G5. Your efforts are much appreciated by myself and the Mac community.

Rand

[halimedia]

Watch out for quad-killer!!

There's a 32-core Linux box screaming up the ranks

http://setiweb.ssl.berkeley.edu/show...hostid=2426798

Not much we can to to beat that fellow, I'm afraid

[fran]

Originally Posted by halimedia

Watch out for quad-killer!!

There's a 32-core Linux box screaming up the ranks

http://setiweb.ssl.berkeley.edu/show...hostid=2426798

Not much we can to to beat that fellow, I'm afraid

Well, the good news is that, per WU, it's only about as fast as my iBook, with v5 & wisdom; or about 1/2 has fast as my MPB 2.16. So it's not really that fast on a per-CPU basis. (I'm assuming that, like my MBP, it is doing one WU per CPU.)

In other words, it's the same 32 G4 iBooks, or 16 MBPs.

Any guesses about what machine it is? It's actually 32 individual intel chips, right? Intel doesn't have any multi-core chips running at 3ghz, right?

Erik

[fran]

I notice on my intel MBP, I have both these files in the seti project folder:

setiathome_4.18_i686-apple-darwin
setiathome_5.13_i686-apple-darwin

I have only ever installed the stock 5.4.9 Boinc Manager in this machine. Any idea why both would be there, and is there any harm having the older version? Or should I delete it?

Also, there is no wisdom file. I thought they were generated automatically, and that we are running fft_test_shell (on PPC machines only for now) to replace it with a better version. Obviously I am misunderstanding the way this works. Little help?

Thanks,
Erik

[liebsmaschine]

Originally Posted by zombie67

Well, the good news is that, per WU, it's only about as fast as my iBook, with v5 & wisdom; or about 1/2 has fast as my MPB 2.16. So it's not really that fast on a per-CPU basis. (I'm assuming that, like my MBP, it is doing one WU per CPU.)

In other words, it's the same 32 G4 iBooks, or 16 MBPs.

Any guesses about what machine it is? It's actually 32 individual intel chips, right? Intel doesn't have any multi-core chips running at 3ghz, right?

Erik

S@H provides a ranking for computers according to RAC; with the advent of multi-processor and multi-core machines, perhaps they should also provide a ranking according to WU completion time. Of course anyone can rise to the top of the top computers list by building a machine like this guy did (he's anonymous). The question is, who actually makes the fastest processor and who has the best-optimized client? On a WU-completion basis, my PB 1.67 is faster than many Intel 3.0 machines out there (well, the ones who weren't running Crunch3r's client, anyway).

Originally Posted by zombie67

I notice on my intel MBP, I have both these files in the seti project folder:

setiathome_4.18_i686-apple-darwin
setiathome_5.13_i686-apple-darwin

I have only ever installed the stock 5.4.9 Boinc Manager in this machine. Any idea why both would be there, and is there any harm having the older version? Or should I delete it?

The BOINC Manager version makes no difference as to the worker application that's downloaded to actually process the work. When you're running the stock workers (i.e. no custom optimized apps), the worker app version you get and use is dependent on the what the work unit's needs are. (BOINC will download whichever worker the WU needs if you don't already have it.) If you downloaded and installed BOINC before S@H had completely switched over to the new SETI Enhanced project, S@H might have distributed an old, non-enhanced work unit to your machine, which would have caused your BOINC installation to download the 4.18 worker app.

With the enhanced clients, I've noticed that when I update (or replace) my app_info.xml file to refer to the new client, BOINC automatically deletes the old worker when it starts up, even though I specifically left it there when copying the new worker into the directory (presumably because the new app_info.xml file doesn't refer to the old worker). Perhaps when using the stock workers (i.e. no app_info.xml file), BOINC doesn't delete the old clients--and I seem to remember this being the case in my installation before I found the Alex's client.

I'd say that as long as the older version isn't being actively used by BOINC (you can check it by surveying your old results or by checking Activity Monitor, top, or the ps -ax | grep seti Terminal command I described earlier), it's safe to delete. Don't take my word for it, though.

Originally Posted by zombie67

Also, there is no wisdom file. I thought they were generated automatically, and that we are running fft_test_shell (on PPC machines only for now) to replace it with a better version. Obviously I am misunderstanding the way this works. Little help?

Perhaps Intel processors don't use/need wisdom files? Perhaps it's only a PPC thing? I'm totally speculating here--this is a question that a real programmer (and probably one familiar with Intel processors) should answer.

There are two alternate places that wisdom.sah files are stored. <a href="http://forums.macnn.com/showthread.php?p=2994473&highlight=slots#post29944 73">Alex</a> and <a href="http://forums.macnn.com/showthread.php?p=3007396&highlight=slots#post30073 96">Knightrider</a> said that the worker-generated wisdom files are placed there. Check /Library/Application Support/BOINC Data/slots/* (I show 0-7, presumably one for each project I run) for wisdom.sah files.

Speaking of which, Alex or Knightrider or someone, my slots folder for my S@H project does indeed clean up after itself, but the wisdom.sah file in there is not the same as the custom-created one I put in the projects/setiathome.berkeley.edu/ directory. The first line reads:

<i>(fftw-3.1.1 fftwf_wisdom</i>

which is the same as the worker-created wisdom file I had earlier (the custom one reads "(fftw-3.1-beta2 fftwf_wisdom"). Can you confirm that the v5 worker does NOT use the one in the slots folder? Are you sure, especially because the slots folder also has the v5 worker in it? Should I replace the one in the slots folder, too?

[arkayn]

I can confirm that neither of my 2 Dells has a wisdom file.

[Knightrider]

Originally Posted by jackal

Can you confirm that the v5 worker does NOT use the one in the slots folder? Are you sure, especially because the slots folder also has the v5 worker in it? Should I replace the one in the slots folder, too?

Rick will have to confirm about the V5 use of the wisdom file in the slots folder. I noticed it was there and apparently the sah stock worker creates and use one 'on the fly'. Because it was there I copied the wisdom file I had made with the fft_test_shell into the sah slots as well as the project folder, just in case it was needed. ( btw, If you drop the fft_test_shell into the applications folder and click on it should auto start and run)

also btw, slot folders are created and used for each wu run. If wu's are suspended so that another wu with a shorter time priority can run, folders are created however many times this occurs across all the projects you may be running. If you quit a project the empty folder is still there.

K.

[liebsmaschine]

My first result purely with v5/G4 (I think the one preceding it was a hybrid with v4 and v5):

http://setiathome.berkeley.edu/resul...ltid=339998424

Looks like I'm the fastest one (http://setiathome.berkeley.edu/worku...?wuid=81441195).

On the <a href="http://setiathome.berkeley.edu/result.php?resultid=340249602">next WU</a> after this, I'm almost tied with...a 1.1GHz Pentium. Wonder whose client he's using...or if his CPU is lying about the speed...

[BTBlomberg]

jackal,

Those Pentium M chips are very nice. They are more like a P3 than a P4 and that is good. Also they are running Boinc 5.2.13 rather than 5.4.9 so it could be someones Optimized client and the SETI appears to be version 5.15 rather than 5.13 so it may be a dev build that is faster than 5.13 becasue of fixes.

Zombie,

As for the wisdom, it looks like the apps will rewrite the wisdom as it goes along and that may reorganize it or hopefully enhance it as it may get better feedback on processes. I put my wisdom in the Projects/Seti... folder and it was automatically copied over to the slots/0 folder. Sine then it gets updated all the time.

[BTBlomberg]

As for PCs and wisdom files, I just checked mine and on my IBM P3 550 I found a file libfftw3....dll and woner if it's the equivelent but for intel only??. I found it in my Projects folder. This file seams fixed and not rewritten like our wisdoms.

On my AMD 1700+ XP machine there was no wisdom and no DLL. Then on my OpenSUSE gateway P2 266 I found no wisdom either.

My iMac G3 333 does have a wisdom however and I did run the fftw test nto make a custom one, for whatever good that did.

[Gecko_r7]

Originally Posted by BTBlomberg

jackal,

Those Pentium M chips are very nice. They are more like a P3 than a P4 and that is good.

Yes, the M gives great performance and is highly efficient at Seti, especially the lastest Dothan-based variety. Been very happy w/ my Banias and it's been fun to compare the performance between it and the G4 with the various optimizing updates. G4 despite obvious disadvantages, hangs right in there!

M-1.6 (Banias)
BOINC 5.5.0/Crunch3r 5.12
WU: http://setiathome.berkeley.edu/worku...?wuid=81182739
AR: .4265
CPU Time: 16911 Secs

G4 MDD Giga DP 1.33
BOINC 5.4.9/Alex Kan v5.13 v5-G4
WU: http://setiathome.berkeley.edu/worku...?wuid=81410497
AR: .4265
CPU Time: 19758 Secs

M-1.6 is only +17% faster, despite +266mhz clock advantage, 1MB L2 (9 cycle latency) & 400FSB.
By comparison, G4 7455 has only 256K L2 (11 cycle latency, +2MB L3 at 1/6 cpu clock) & 167FSB.
I'd imagine this 17% performance advantage would disappear completely at the same 1.3ghz clock. Though, would run much cooler than my desktop "office furnace".

M has HUGE advantages over G4 for such a small performance difference.
Alex's v5 really shows the massive power of ALTIVEC when the ap is specifically optimized to exploit the feature.

ALTIVEC, I hate to see you go.......

[arkayn]

My Dell with the 1.6 Pentium M is my current champ at processing, but my 2.53 Celeron is closing in.

[BTBlomberg]

Maybe Apple can get the Altivec Licensed to Intel

I have used my Dad's new Dell Laptop with 1.8 Pentium M for a few weeks when they visit and with old SETI the RAC was 800ish alone with 3 weeks of crunching. He uses it as a real laptop so he does not have it runing plugged in all the time and tends to turn it off when he's busy with tasks.

[Gecko_r7]

Originally Posted by BTBlomberg

Maybe Apple can get the Altivec Licensed to Intel

I have used my Dad's new Dell Laptop with 1.8 Pentium M for a few weeks when they visit and with old SETI the RAC was 800ish alone with 3 weeks of crunching. He uses it as a real laptop so he does not have it runing plugged in all the time and tends to turn it off when he's busy with tasks.

Wouldn't mind seeing someone introduce a PC or server blade w/ the Freescale 8641D. http://www.freescale.com/files/32bit...C8641DFACT.pdf
Was hoping Giga Designs would try to make an upgrade processor board w/ this, or even a dual 7448 board (167/200 FSB-based) Low volume production by Freescale, means a likely $1,000.00 upgrade, so not a practical solution vs. just getting a new Mac-tel. Oh, well. Based on my 24/7 operation, I might have 2-3 years left in the old soldier (if I'm lucky).

What is Seti C in your signature? Beta?

[arkayn]

My guess would be SETI classic, 11000 units completed before it was shut down.

[alexkan]

Here's the story on wisdom:

Only SETI workers that use the FFTW libraries to compute FFTs read and write wisdom.sah files. Stock SETI clients should all do this. Crunch3r's clients use the Intel-tuned FFTs in the IPP libraries, so they don't need wisdom.sah.

Once wisdom is generated, it is simply read from the file, and isn't superseded by later wisdom. This is because all FFTW wisdom is generated during a separate planning phase, not when the FFTs are being performed. Basically, if it looks like the client is speeding up, it's probably your imagination.

I've updated fft_test3. I actually mistakenly linked my old fft_test3 with a slightly older version of FFTW (the same one that I used for fft_test2), rather than the newest version that the optimized workers are linked with. You may or may not wish to regenerate your wisdom to take care of the new version. If you do, make sure you don't have a wisdom.sah file already in that directory, or no new wisdom will be generated. The fixed compile is also Universal now, so those of you running Intel Macs can now generate optimized wisdom as well (and post your scores).

[Todd Madson]

Alex: I've generated wisdom from fft test 2 - the best way then to convert over is:

-stop seti
-delete old wisdom (or move out of directory)
-generate new wisdom file from fft test 3
-install file in projects / seti folder
-restart?

Is that it or? You indicate if there is a file already there it won't generate
new wisdom.

[Knightrider]

Originally Posted by Todd Madson

Alex: I've generated wisdom from fft test 2 - the best way then to convert over is:

-stop seti
-delete old wisdom (or move out of directory)
-generate new wisdom file from fft test 3
-install file in projects / seti folder
-restart?

Is that it or? You indicate if there is a file already there it won't generate
new wisdom.

I generated a wisdom file for fft_test3 by droping the test3 into my apps folder. Click on it and it runs auto and writes the wisdom file to the documents folder. I already had an old one there so I deleted that and had to run it again. ( I have the time, though on the quad it wasn't that long) It wrote to the docs folder and is now in use.

K.