Posts by ivan


log in
1) Message boards : Number crunching : Panic Mode On (91) Server Problems? (Message 1590111)
Posted 22 hours ago by Profile ivan
Summats up:-)

22/10/2014 11:19:36 | SETI@home | Scheduler request completed: got 107 new tasks

Got a fair stack of work including 3 APv7's

Swings & Roundabouts I guess.

Yeah, one of my new 20-core machines ran out and the other was on its last WU when the first got 98 new tasks and the second got 38.
22-Oct-2014 10:55:30 [SETI@home] Scheduler request completed: got 98 new tasks 22-Oct-2014 11:33:59 [SETI@home] Scheduler request completed: got 38 new tasks
2) Message boards : Number crunching : how many ways to fry a motherboard? (Message 1588558)
Posted 5 days ago by Profile ivan
Good to know. Thanks

The word we use in the states is usually Q-tip but I think we have other names for it too.

"Cotton bud" most places I've been.
As for spreading heat-sink compound, I keep all my old credit/debit cards and similar and use them to carefully smear the compound all across the surface of the CPU/GPU housing. (They are also handy in breaking apart pressed-together casings on all-in-one PCs, tablets, tc.)
3) Message boards : Number crunching : New PSU blows my mind. (Message 1588231)
Posted 5 days ago by Profile ivan
Ok, so now I have connected the 24 pin connector to the MB.

Next I know I need to connect an 8 pin ATX12V1 to the MB.

I have 2 cables that have 8 pin connections on each end - they have the label "CPU"

I think I have to connect one of these to that ATX12V1 on the MB

Correct.

and probably to the "6+2 PCIE & 4+4 CPU" group.

If you mean that as sockets on the power supply, yes. That "group" would be to supply extra 12 V to the ATX input and directly to PCIE GPUs, etc (some have 6-pin inputs, some have 8-pin).
[Edit] Ah, yes, found a picture on eBuyer. Definitely connect to that group. In fact, you can hardly go wrong -- if it's 8-pin it goes there, if it's 6-pin it goes in the peripheral group. Ignore the CLINK unless you have a second P/S... [/Edit]

I know of course that I first have to install the cpu and heatsink/fan but as far as the PSU set up is that all I need to start. That is the 24 pin and 8 pin connection? The 16GB of memory is already set up on the MB too.

I also need to confirm that I am setting up that 8 pin correctly.

That should be enough to get a bios display, assuming you have an on-board VGA/video output.
4) Message boards : Number crunching : Panic Mode On (90) Server Problems? (Message 1585052)
Posted 12 days ago by Profile ivan
4851...

Patience, Julie. I'm just now starting to see an uptick in my home machine and overall RAC. Perhaps the APv7 results are starting to have an effect. Or maybe it's just a statistical blip...
5) Message boards : Number crunching : AP V7 (Message 1584287)
Posted 13 days ago by Profile ivan
First one is complete, just awaiting my wingman.

I've had two complete and pending (3,900 secs each/400 secs CPU) and seven in progress on my "stock" Linux box.
6) Message boards : Number crunching : Mismatch in time elapsed values? (Message 1582727)
Posted 16 days ago by Profile ivan
...
I'm think to have that you must have Hypo Threading turned on . If you wish to speed things up Go into your BIOS and turn it off . That's not good running Seti . Or having it on with just a P4 .
...

OTOH, many users have reported a 25% or so productivity increase when using Intel Hyperthreading. That is, individual tasks take less than twice as long when running two per physical core.

It probably depends on various factors related to cache size, cache speed, main memory speed, etc. and the sensible way to determine whether to have it on or not is to actually see which way works best on the system. IOW, try each for long enough to see how many tasks get done per day.
Joe

Well, I've been running two identical machines 7371751 and 7371070 for more than a month now. Admittedly the one using hyperthreading has been crunching for one day longer than the other, but it has a 14-15% advantage over the non-HT machine in both total credit and RAC. Unfortunately the non-HT machine will have to be shut off tomorrow while an engineer investigates a small anomaly in its RAID controller, so it will slip behind a bit more. When we start using the HT machine in earnest, I'll have to turn off HT as we will then want the fastest individual processes, not the highest throughput.
7) Message boards : Number crunching : Panic Mode On (90) Server Problems? (Message 1581647)
Posted 19 days ago by Profile ivan
While my previous Front Page Mac is now in Full Free Fall;
AP Validation pending (491) · Valid (30)

All AstroPulse v6 tasks for computer 7042852
State: All (277) · In progress (90) · Validation pending (179) · Validation inconclusive (2) · Valid (6) · Invalid (0) · Error (0)
8) Message boards : Number crunching : Panic Mode On (90) Server Problems? (Message 1581398)
Posted 20 days ago by Profile ivan
They fixed the validator.

See:)

Sorry, Julie, but from where I sit it failed again after about 30 minutes. Waiting for validation rising again.

It looks like it hasn't completely gone OTL. Over the past hour my AP valid have gone from 130 to 147. That trickle could stop at any time I expect.

Yes, with more data this morning the slope of the graph is lower, so it may be still processing but at a lower rate than results are returned.
9) Message boards : Number crunching : Panic Mode On (90) Server Problems? (Message 1581231)
Posted 20 days ago by Profile ivan
They fixed the validator.

See:)

Sorry, Julie, but from where I sit it failed again after about 30 minutes. Waiting for validation rising again.
10) Message boards : Number crunching : Panic Mode On (90) Server Problems? (Message 1580980)
Posted 20 days ago by Profile ivan
Validators servers are back up and working but 293,358 now aproxx 2,000 more than 1:20 hrs ago so all not well in SETIland still no wonder i only got 7,000 so far should be 20,000 oh well time for bed then

The apparent only AP validator ap validate 4 has said running since yesterday, but the column on the left displaying the status is known to lie.

The Astropulse "awaiting validation" graphs still show a nearly-constant rate of increase, with no sign of anything reducing the pool.
11) Message boards : Number crunching : Panic Mode On (89) Server Problems? (Message 1576698)
Posted 29 days ago by Profile ivan
Could anyone with a heavily-active CPU check if they're getting an unusual number of VLARs, please? That's the only explanation I haven't felt sufficiently motivated to test.....

Quick check has 3 out of the last 20 -- over all machines -- as VLARs. That encompasses 20:11:55 UTC to 22:29:55 UTC.
12) Message boards : Number crunching : Power bill challenge (Message 1576691)
Posted 29 days ago by Profile ivan
I just used RAC for SETI (144,115,652) and divided down by my own machine's RAC which runs at probably around 500 W. Then used local energy costs and converted to USD.
I think the figure gives an indication of the massive effort and commitment people make and must feel about this project.

Well, to take one (hopefully average today) machine... My GTX 750 Ti at work tops out around 20k RAC when conditions are good. It uses less than 75 W for the GPU and ~90 W for the CPU. So say 160 W total or 1/6 kWh/h -> 4 kWh/day at a local (domestic) price of £GB0.14/kWh -> £GB0.56/day -> £GB16.8/mo. Multiplied by 7206 from your RAC figure above -> £GB121k/mo -- which is getting on for £GB1.5M/year!
13) Message boards : Number crunching : Panic Mode On (89) Server Problems? (Message 1576658)
Posted 29 days ago by Profile ivan
Forums seem a bit slow since we came back, but I think that's normal for right after the outrage, isn't it?

I'm having a lot of trouble reading my stats and communicating results/getting new work. I saw oscar (BOINC master database) was shown as down for a while but he's green again now; still getting time-outs when reporting, though.
14) Message boards : Number crunching : Max temp for getting the normal life out of a video card? (Message 1576626)
Posted 29 days ago by Profile ivan
Slightly happier bunny tonight -- I received a parcel from China today for my birthday present, a new fan for my Gigabyte GT 640 DDR5 card which was/is my secondary GPU in my home PC. It cost all of £GB1.78 with free posting! Re-assembled the card at lunchtime and replaced it tonight. It's now purring along on two AP tasks, with a temperature of 72 C at 80% fan according to nvidia-smi; the main Asus GTX 660 Ti is using 27% fan at 63 C (the 640 is in a single-width end slot with only 5 or 6 mm clearance between the fan and the bottom of the case).
When the original fan failed, the 640 would gradually rise to 102 C before shutting down...
15) Message boards : Number crunching : Computer Upgrades - normal or not? (Message 1571166)
Posted 12 Sep 2014 by Profile ivan
Thanks, actually I am having an issue with installing NVidia drivers in Linux.
I had no problems with the 210 card but the 'new' (eBay) 8800GTS is giving me problems. I'm a Win XP 'refugee' so need to 'have my hand held' with Linux (Mint 16 Petra)I've tried manual install through terminal but nothing has worked so far
Couple of people on Mint forum are helping out, posting scripts I can just cut and paste into terminal

a) Using Firefox/Chrome, go to www.nvidia.com, find their driver download area and download the latest qualified driver for your flavour (32/64-bit) Unix.
b) Make sure your system is up-to-date - sudo apt-get update; sudo apt-get upgrade.
c) reboot -- sudo reboot
d) If b) loaded new kernels, you may find error messages. Select the option to drop into a command-line terminal, or if (limited) graphics go there with Ctrl-Alt-F[1|2] (probably 2)
e) sudo telinit 2
f) sudo service stop mdm; sudo pkill -9 X -- (to be sure, to be sure)
g) cd to where you downloaded NVIDIA...run (insert proper filename here et seq.)
h) sudo chmod +x NVIDIA...run
i) sudo ./NVIDIA...run -- in general take default options
j) sudo reboot
k) report problems here in case my memory's faulty!
16) Message boards : Number crunching : NVIDIA Jetson TK1 (Message 1567807)
Posted 5 Sep 2014 by Profile ivan
GT 640 which had developed a faulty fan -- the third Gigabyte GPU that's done that to me now! :-( )..
Just ordered a replacement fan from China on eBay for about £1.50, so might be back in action by the end of the month. Otherwise I'll get the Asus GT640-1GD5-L as a replacement -- it has to fit in a single-width slot with only about 5 mm extra clearance.
17) Message boards : Number crunching : NVIDIA Jetson TK1 (Message 1567691)
Posted 5 Sep 2014 by Profile ivan
Any patches or recommendations for X-branch ? It's on idle while I address some complex Boinc issues, but I don't stop taking issues for the ToDo list :)

No, IIRC it just compiled as usual on the Jetson.
No real problems with the s@h, just the missing include I reported last January, and I had to edit the config file to remove the old compute capabilities that nvcc didn't like and put in 3.2 for the Tegra.
I had to add
#include <unistd.h>
to client/analyzeFuncs.h to bring in sleep() on my Mint system.
18) Message boards : Number crunching : NVIDIA Jetson TK1 (Message 1567589)
Posted 5 Sep 2014 by Profile ivan
Yeah, that's me. ... It runs about 1/10th the speed of my GTX 750 Ti, but takes perhaps 1/15th the power. I've got my wattmeter at work now so I'll try to get some power figures soon (got the chance to grab it when I had to shut down my home machine last night to remove the GTX 640 which had developed a faulty fan -- the third Gigabyte GPU that's done that to me now! :-( ).

OK, some figures. At idle, the wattmeter was showing 9 W at the socket (it was 4 W with the machine shut down, so that's about the inefficiency of the power supply). Running two CUDA jobs simultaneously shows 16 W, with occasional drops to 14 W and sometimes 11 W.
19) Message boards : Number crunching : NVIDIA Jetson TK1 (Message 1566730)
Posted 4 Sep 2014 by Profile ivan
14 W for 300 GFLOP/s sounds amazingly efficient. Would this work? A review of the board is here:
http://www.itpro.co.uk/desktop-hardware/22731/nvidia-jetson-tk1-review
Here is one actually running.
http://setiathome.berkeley.edu/show_host_detail.php?hostid=7354060
As I recall they had to compile the app for the hardware & there was quite a bit of effort to get it producing valid results.
Yeah, that's me. I had to add some ifdefs to the machine-code routines (someone else worked that out...) to get the floating-point working right. Note that the results it's producing are purely from the GPU. I've compiled the CPU code and it seems to run fine standalone but under BOINC itself it throws an exception. I haven't had time to try to debug this.
Also note that some CUDA code I have for reconstructing digital holograms compiled and ran without any code changes on the system -- I just had to change the location of the includes and libraries in the Makefile. It runs about 1/10th the speed of my GTX 750 Ti, but takes perhaps 1/15th the power. I've got my wattmeter at work now so I'll try to get some power figures soon (got the chance to grab it when I had to shut down my home machine last night to remove the GTX 640 which had developed a faulty fan -- the third Gigabyte GPU that's done that to me now! :-( ).

For the money I am sticking with Bay Trail-D. TheASRock Q1900-ITX I bought recently only cost around $80 US, or about £50 GB (with VAT I imagine more), & looks to be running around 3200-3500 for RAC. My system total is around 25w, but once optimized I am hoping to get closer to 15w at full load.
Mine (Acer Aspire XC-603) is running around 1250, but that's on Linux and without using the GPU. Cost £130.
20) Message boards : Number crunching : Show and tell your machine. Here's mine. (Message 1566075)
Posted 2 Sep 2014 by Profile ivan
... I turned hyperthreading off to see what the difference might amount to.

Let us know for what you find for the 'hyperthreading'.

For my own applications, I've been very underwhelmed with the throughput and I'm left wondering if the whole idea is a x2 Marketing ploy for a meagre x1.1 performance...

Happy fast crunchin',
Martin

When Intel first released HT I think their statement was something along the lines of 15-20% gains could be expected from the use of HT.

In the early days of HT, I did some extensive testing and the results were very underwhelming. I finally found that running HT off was more stable when OCing and ran cooler. I have not used HT since.

My leaning is not to run HT as these are research machines and we are more interested in single-thread efficiency than overall throughput; but, I'll run like this for some time if I can. It's not often I get to play with two identical machines simultaneously.


Next 20

Copyright © 2014 University of California