Posts by ivan


log in
1) Message boards : Number crunching : Windows 10 may put SETI@home in Danger (Message 1655378)
Posted 6 days ago by Profile ivan
Miss the screensaver myself...

I do too.

Provided it blanks after 5 minutes to avoid wasting CPU cycles.

Indeed. I had a cow-orker once who used the "random" screensaver in RHEL4. He was often out of the room, screensaver running but (LCD) screen blank(!). From time to time I'd hear his CPU fan spin up and kick into high gear, and if I went over and wiggled his mouse one particular screensaver would be running -- Pipes IIRC.
What a waste of CPU cycles!
2) Message boards : Number crunching : Nvidia Titan X (Message 1655376)
Posted 6 days ago by Profile ivan
X it is then. Awesome, it's cheap!

(relatively speaking and for what it is...)

Cheap? In the US maybe ($999). Over here it's coming in around £900 ($US1,350).
http://www.ebuyer.com/store/Components/cat/Graphics-Cards-Nvidia/subcat/NVIDIA-GTX-TITAN
3) Message boards : Number crunching : Some sad news I need to pass on... (Message 1655372)
Posted 6 days ago by Profile ivan
Condolences to you and your family, Richard. Everything else has been said, probably better than I could myself.
4) Message boards : Number crunching : Banana Pi (Message 1653249)
Posted 12 days ago by Profile ivan
My Jetson build seems to be running OK!
http://setiathome.berkeley.edu/results.php?hostid=7354060&offset=0&show_names=0&state=4&appid=
5) Message boards : Number crunching : CPU Power Usage Varies Significantly With RAM Frequency (Message 1652837)
Posted 13 days ago by Profile ivan
To program a GPU efficiently one must do just that right now in his/hers mind.

Yes, GPU programming is a whole new mindset -- two talented programmers before me failed to get our analysis software running on a FPS vector-processor (TRIUMF, 1984) before I tried and succeeded. Looking today at the theoretical and S@H-reported performance of my Tegra GPU -- 327 GFLOPS and 14.5 GFLOPS respectively (double the S@H figure as I run two jobs at once) -- it does appear that there is some way to go in extracting ultimate performance. In my experience, this may need new algorithms.
Mind you, the same is true of complex CPU software, as this 2007 report on my current project's software shows -- I doubt programmers or compilers have gotten significantly more proficient in the interim.
6) Message boards : Number crunching : Banana Pi (Message 1652829)
Posted 13 days ago by Profile ivan
BOINC doesn't seem to be reliably able to determine the number of CPU cores -- sometimes it thinks 1, sometimes 2, finally settled on 4. I've never worked out how to use the fifth core in Ubuntu ...

You have to be able to use <ncpus>N</ncpus> in cc_config.xml to force/tell BOINC you have N CPUs (cores)

Yeah, thanks, I guess that'll solve it!
<test>
14-Mar-2015 12:03:03 [---] CUDA: NVIDIA GPU 0: GK20A (driver version unknown, CUDA version 6.0, compute capability 3.2, 1746MB, 808MB available, 327 GFLOPS peak) 14-Mar-2015 12:03:03 [SETI@home] Found app_info.xml; using anonymous platform 14-Mar-2015 12:03:03 [---] Host name: tegra-ubuntu 14-Mar-2015 12:03:03 [---] Processor: 4 ARM ARMv7 Processor rev 3 (v7l) 14-Mar-2015 12:03:03 [---] Processor features: swp half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt 14-Mar-2015 12:03:03 [---] OS: Linux: 3.10.24-g6a2d13a 14-Mar-2015 12:03:03 [---] Memory: 1.71 GB physical, 0 bytes virtual 14-Mar-2015 12:03:03 [---] Disk: 58.55 GB total, 53.88 GB free 14-Mar-2015 12:03:03 [---] Local time is UTC +0 hours 14-Mar-2015 12:03:03 [---] Config: simulate 4 CPUs 14-Mar-2015 12:03:03 [---] Config: use all coprocessors

top - 12:06:11 up 4 days, 1:54, 5 users, load average: 5.15, 4.68, 4.86 Tasks: 209 total, 6 running, 202 sleeping, 0 stopped, 1 zombie %Cpu(s): 0.2 us, 10.4 sy, 89.1 ni, 0.2 id, 0.0 wa, 0.0 hi, 0.0 si, 0.0 st KiB Mem: 1788136 total, 1697140 used, 90996 free, 47592 buffers KiB Swap: 0 total, 0 used, 0 free. 123656 cached Mem PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 10604 ubuntu 39 19 73156 70636 1780 R 93.4 4.0 2:33.12 setiathome-7.28 10605 ubuntu 39 19 73300 70868 1772 R 89.4 4.0 2:31.85 setiathome-7.28 10607 ubuntu 39 19 70684 68452 1776 R 73.7 3.8 2:32.95 setiathome-7.28 10606 ubuntu 39 19 73220 70700 1788 R 72.3 4.0 2:31.89 setiathome-7.28 10608 ubuntu 30 10 403984 99964 17072 S 25.3 5.6 0:49.50 setiathome_x41z 10609 ubuntu 30 10 406208 102680 17376 R 24.7 5.7 0:48.96 setiathome_x41z

Sofa so good...
</test>
Cheers!
7) Message boards : Technical News : Results (Mar 11 2015) (Message 1652671)
Posted 13 days ago by Profile ivan
Oh now it looks like georgem is crashing too with the same NFS errors. Ha ha. Happy Friday afternoon...

- Matt

Ouch, everything bad happens on Friday near quitting time. :(

In my extensive experience as an experimental physicist at various institutes around the world, everything bad happens on a Friday afternoon after the technicians have left, but before the scientists start knocking off for the weekend.
8) Message boards : Number crunching : Banana Pi (Message 1652549)
Posted 14 days ago by Profile ivan
One Note, If when compiling the app, If it fails with an error, check the client sub-directory anyway for the compiled app, there are two Bugs with compiling seti_boinc from head,

If you use a more minimal configure, it fails with the following, but the app is still compiled:

In file included from <command-line>:0:0:
//home/stephen/boinc/lib/../config.h:732:0: note: this is the location of the previous definition
#define VERSION "7.5.0"
^
readwu.cpp:47:20: fatal error: export.h: No such file or directory
#include "export.h"

^
compilation terminated.
make[2]: *** [readwu_so-readwu.o] Error 1
make[2]: Leaving directory `/home/stephen/seti_boinc/tools'
make[1]: *** [all-recursive] Error 1
make[1]: Leaving directory `/home/stephen/seti_boinc'
make: *** [all] Error 2


Claggy

You're right, the executable was there. Running now, tho' BOINC doesn't seem to be reliably able to determine the number of CPU cores -- sometimes it thinks 1, sometimes 2, finally settled on 4. I've never worked out how to use the fifth core in Ubuntu, but since it's less powerful and the "real" CPUs look like they'll take about 100,000 seconds per WU I doubt that it would bring me much anyhow.
9) Message boards : Number crunching : Banana Pi (Message 1651809)
Posted 15 days ago by Profile ivan
Thanks for your answer!
In the meantime I installed the most Boinc packages, include boinc-dev. I think this is what you mean. Nothing happend, still "boinc not found".

You need to tell the ./configure where your BOINC headers are located. E.g.
[tegra-ubuntu:seti_boinc] > head -50 config.log This file contains any messages produced by compilers while running configure, to aid debugging if configure makes a mistake. It was created by setiathome_v7 configure 7.28, which was generated by GNU Autoconf 2.69. Invocation command line was $ ./configure BOINCDIR=../boinc --enable-fast-math --disable-graphics ## --------- ## ## Platform. ## ## --------- ## hostname = tegra-ubuntu uname -m = armv7l uname -r = 3.10.24-g6a2d13a uname -s = Linux uname -v = #1 SMP PREEMPT Fri Apr 18 15:56:45 PDT 2014
10) Message boards : Number crunching : thinking about upgrading GPU's (Message 1651807)
Posted 15 days ago by Profile ivan
Okay i have been running GTX 570 in SLI for a few years now. I was thinking about moving up to the GTx 980 but one at time (might do SLI again later in the year).

so the Q: is the 980 that much better than the old 570's i have now.

http://en.wikipedia.org/wiki/List_of_Nvidia_graphics_processing_units:
SP GFlOpS Power (W) GFlOpS/W GTX 570 1405.4 219 6.41 GTX 980 4612 165 28.0
11) Message boards : Number crunching : Win 10 will be a FREE Upgrade to Win 7 & 8 Users!!! (Message 1651129)
Posted 17 days ago by Profile ivan
Oops, I forgot, is anyone crunching on Windows 10 yet?

Yes. :-)
12) Message boards : Number crunching : NVIDIA SHIELD! I can't wait to run SETI on it! (Message 1649410)
Posted 22 days ago by Profile ivan
Multibeam support (at least) for that could be relatively quick, since it should I guess run Cuda natively (taking the specs at face value). Should manage OpenCL too, though I haven't read the Tegra SDK details on that. For My Nexus 9, I'm having to look at the viability of a Renderscript port as well, because Google decided to go with their own language instead of using Cuda and/or OpenCL.

Guess it's time to ask (again) if anyone's managed to get MB CPU tasks running on a Tegra TK1 Jetson. I got the CUDA version running relatively easily, and my digital hologram reconstruction, but when I tried the CPU version -- it runs fine manually, but crashes when run as a BOINC task. I should really look at it again but at the moment I'm up in my all in assigators trying to bridge the gap between xxxx IT and yyy scientists to get yyy@Home running for volunteer computing. (Of course, most of you know what xxxx and yyy are, but I'd better be circumspect.) With a little bit of luck, we'll have things ready for the public in late autumn; with a lot of luck, earlier!
13) Message boards : Number crunching : Panic Mode On (96) Server Problems? (Message 1649157)
Posted 23 days ago by Profile ivan
I'm sure it will all be fine, in time for the next outage :-)
No tasks left to do now though. Fans are going at very low speed.

My temperatures at work have dropped from 75-80 C to 30 C. Apparently the CPU fan liked being warm, it's now making so much noise that I called the IT guy over and asked for a replacement!
14) Message boards : Number crunching : Panic Mode On (95) Server Problems? (Message 1648173)
Posted 26 days ago by Profile ivan
It's working just fine.

No, it's not.
If it were we would have had a full Ready-to-send buffer by the end of the day of the weekly outage.

Grant, for the sake of your blood pressure -- don't look at the cricket graphs just now! :-/
15) Message boards : Number crunching : TCP Settings (Message 1647903)
Posted 27 days ago by Profile ivan
They've just finished a lot of NBN work in Darwin and I'm wondering if they've pinched some of the bandwidth allocation from Alice Springs to boost the speeds up there.

Network speeds still suck up here.

I was shocked at the speeds my brother was getting in Byron Bay until I looked at his modem and found it was quoting over 10 Mbps achievable, but an actual rate of 1.5 Mbps. Seems that that is the plan he could afford years ago and he hasn't updated since. (And his ISP apparently hasn't told him that faster plans are now available.) Also his monthly limit of 3 GB peak and 5 GB off-peak would drive me doolally -- and I'm only getting 6 Mbps here (but unlimited data), I should change to fibre because it's strung to the telephone cabinet embedded in my front hedge!
16) Message boards : Number crunching : Any thoughts upon this one? (Message 1644682)
Posted 20 Feb 2015 by Profile ivan
I've learned over the years to "NEVER" let Microsoft upgrade your video drivers. Most other drivers update fine but I've always had problems with their graphics drivers. Check and see if there are in your recent Microsoft update history.

+1
17) Message boards : Number crunching : SETI/BOINC Milestones [ v2.0 ] - XXVIII (Message 1644490)
Posted 20 Feb 2015 by Profile ivan
Just slipped past Questor to become the top cruncher in the UK. :-)

That was nice -- I had a PM from Questor congratulating me on overtaking him. Thanks!
18) Message boards : Number crunching : Panic Mode On (95) Server Problems? (Message 1643501)
Posted 18 Feb 2015 by Profile ivan
Never seen these messages before, interesting ...
2015-02-17 6:18:59 PM | SETI@home | Fetching scheduler list
2015-02-17 6:19:00 PM | SETI@home | Master file download succeeded
AFAIK, if BOINC want contact to the server, and get 5 or 6 times no well answer back, then master file will be downloaded. (for to download the 'new' server URLs).
Just to be clear "master file" is master_setiathome.berkeley.edu.xml:
<scheduler>http://setiboinc.ssl.berkeley.edu/sah_cgi/cgi</scheduler> <link rel="boinc_scheduler" href="http://setiboinc.ssl.berkeley.edu/sah_cgi/cgi">
19) Message boards : Number crunching : Panic Mode On (95) Server Problems? (Message 1642433)
Posted 15 Feb 2015 by Profile ivan
ivan wrote:
Well, as of 2042 UTC, all my machines have their full quota of MB tasks, except for my Celeron J1900 which I switched from Linux to Windows 10 on Monday. It's not done enough GPU jobs yet to have its performance quantified (currently its GPU is running at 70 or 80% of a single CPU core, but the CPU is reportedly running at 2.4 GHz, for a 2 GHz part!).

Intel® Celeron® Processor J1900
Burst Frequency 2.41 GHz

Ah, thanks. I thought it might have been something like that, but I hadn't got around to go looking for it.
20) Message boards : Number crunching : Haswell-EX get up to 18 cores!! (Message 1641148)
Posted 13 Feb 2015 by Profile ivan
About time they got around to releasing the v3 for the E7's. All we had to drool over before were the E5's with their 18, 16, & 14 cores on 2 sockets. Now we can have 18c/36t with 8 sockets @ 2.5GHz

I must contact Boston/Viglen -- the in-socket Xeon Phi should be imminent. I couldn't see how to make the co-processor version do S@H but once it has access to all system memory...


Next 20

Copyright © 2015 University of California