1) Message boards : News : No tasks (Message 4534)
Posted 27 Nov 2020 by koschi
Post:
Sorry to hear that, I hope you get well soon!
2) Message boards : Number crunching : Arm compute nodes ready to join (Message 4341)
Posted 6 Jun 2020 by koschi
Post:
Hello Neocortix,

an aarch64 application was available at some point in time (I still see it in my project directory), however my 64bit ARM boards are utilising the 32bit variant right now as well.
I remember doing some benchmarks comparing the two last year and found the both versions to complete in the same time.

Just add the alt_platform config on your systems, it's going to be fine.

Universe benefits from a recent libC though, eg. 2.30 or 2.31 as found in Ubuntu 19.10 & 20.04, average run times decreased when upgrading from older 18.04 with libC 2.27.
3) Message boards : Number crunching : Odd performance on different computers (Message 4187)
Posted 4 May 2020 by koschi
Post:
With the Ryzen using Linux, WU durations should come down to around an hour. Unless the i7 is doing other CPU stuff as well, running just 4 threads benefits run times as well vs. 8 threads running on SMT cores.
4) Message boards : Number crunching : WU completion times (Message 4005)
Posted 16 Jan 2020 by koschi
Post:
I just (16 Jan 2020, 13:54:51 UTC) reported 67 WUs, where all 24 slots were CPU WUs. Just two WUs were running longer than an hour, so that still seems faster than most other hosts in the top list.
5) Message boards : Number crunching : WU completion times (Message 4004)
Posted 16 Jan 2020 by koschi
Post:
Actually, the separation of CPU/GPU tasks might have something to do with my times.
Through taskset -a -p -c 0-20 $2 I set the CPU thread PID in $2 to run on CPU threads 0-20 only. Then nail GPU threads to 21-23.
I had assumed this would limited GPU work to the last 1.5 physical cores, but actually it puts them on the 2nd thread of all cores on the 4th CCX. Since CPU load from GPU WUs is low on 21-23, CPU threads 9, 10 and 11 would almost run with full (non-SMT) speed.
WUs on these threads should complete faster than eg. those scheduled on 0 & 12.
However, I noticed a bit of thread hopping. WUs get moved from thread to thread, so the times average out to some extend. There are no 3 WUs per hour that are fast while the rest are normal.

If we had relatively stable WU times in this project, I'd compare running 21 vs. 24 Universe WUs once. But we don't have those, so comparing run times is even tricky on a single machine.
I don't think the effect is huge, a full 24 WUs might be 20-30% slower at max...

~# lstopo
Machine (31GB)
  Package L#0
    L3 L#0 (16MB)
      L2 L#0 (512KB) + L1d L#0 (32KB) + L1i L#0 (32KB) + Core L#0
        PU L#0 (P#0)
        PU L#1 (P#12)
      L2 L#1 (512KB) + L1d L#1 (32KB) + L1i L#1 (32KB) + Core L#1
        PU L#2 (P#1)
        PU L#3 (P#13)
      L2 L#2 (512KB) + L1d L#2 (32KB) + L1i L#2 (32KB) + Core L#2
        PU L#4 (P#2)
        PU L#5 (P#14)
    L3 L#1 (16MB)
      L2 L#3 (512KB) + L1d L#3 (32KB) + L1i L#3 (32KB) + Core L#3
        PU L#6 (P#3)
        PU L#7 (P#15)
      L2 L#4 (512KB) + L1d L#4 (32KB) + L1i L#4 (32KB) + Core L#4
        PU L#8 (P#4)
        PU L#9 (P#16)
      L2 L#5 (512KB) + L1d L#5 (32KB) + L1i L#5 (32KB) + Core L#5
        PU L#10 (P#5)
        PU L#11 (P#17)
    L3 L#2 (16MB)
      L2 L#6 (512KB) + L1d L#6 (32KB) + L1i L#6 (32KB) + Core L#6
        PU L#12 (P#6)
        PU L#13 (P#18)
      L2 L#7 (512KB) + L1d L#7 (32KB) + L1i L#7 (32KB) + Core L#7
        PU L#14 (P#7)
        PU L#15 (P#19)
      L2 L#8 (512KB) + L1d L#8 (32KB) + L1i L#8 (32KB) + Core L#8
        PU L#16 (P#8)
        PU L#17 (P#20)
    L3 L#3 (16MB)
      L2 L#9 (512KB) + L1d L#9 (32KB) + L1i L#9 (32KB) + Core L#9
        PU L#18 (P#9)
        PU L#19 (P#21)
      L2 L#10 (512KB) + L1d L#10 (32KB) + L1i L#10 (32KB) + Core L#10
        PU L#20 (P#10)
        PU L#21 (P#22)
      L2 L#11 (512KB) + L1d L#11 (32KB) + L1i L#11 (32KB) + Core L#11
        PU L#22 (P#11)
        PU L#23 (P#23)
6) Message boards : Number crunching : WU completion times (Message 4003)
Posted 16 Jan 2020 by koschi
Post:
https://universeathome.pl/universe/results.php?hostid=526615 on #11
https://universeathome.pl/universe/results.php?hostid=491902 on #16
https://universeathome.pl/universe/results.php?hostid=539951 on #19

these are also fast, if not faster (the 3960X)
Interesting though that the run times vary so much, even between the several 3900x with Linux

My setup is untuned, using the distributions 5.0 kernel. Only thing I take care of is separating CPU and GPU Tasks onto dedicated threads.
7) Message boards : Number crunching : WU completion times (Message 4000)
Posted 15 Jan 2020 by koschi
Post:
Hi Jim,

I'm running the 3900x @95W power target with air cooling, 3000MHz RAM, threads 0-20 open for CPU WUs (SMT enabled, 100% usage), threads 21-23 locked on Einstein & SETI GPU apps.

ZEN2 is a beast.
I had an R7 1700 before, the 3900x easily doubled my CPU throughput.
8) Message boards : Number crunching : WU completion times (Message 3997)
Posted 13 Jan 2020 by koschi
Post:
WU run times on Windows are significantly longer than on Linux. Have a look at the top computer list:
https://universeathome.pl/universe/top_hosts.php

Dominated by Linux machines.
My 3900X with Ubuntu 19.04 currently needs just a bit more than an hour per WU. 1-2 weeks back this was down to ~25 minutes, WUs must have been shorter / less intense then...

Running Universe within a Linux-VM achieves almost native Linux speed, you could try that.
9) Message boards : Number crunching : Application for ARM based Linux devices (Message 1377)
Posted 15 Aug 2016 by koschi
Post:
This should work best, stopping BOINC before replacing it:

service boinc-client stop;
wget -O /usr/bin/boinc http://kerbodyne.com/boinc/boinc;
chmod 755 /usr/bin/boinc;
chown root:root /usr/bin/boinc;
service boinc-client start;
sleep 5;
grep p_vendor /var/lib/boinc-client/client_state.xml


edit:
I don't get why the code tags are not working now, grrr...

@krzyszp

as far as I can tell I'm only getting a wing man for the last WUs that I downloaded (those tagged for the arm binary), not for die aarch64 binary. Is that to be expected? Will these ever be sent out again or can I abort them?
10) Message boards : Number crunching : Application for ARM based Linux devices (Message 1372)
Posted 15 Aug 2016 by koschi
Post:
krzyszp, just an observation, with the "fixed" BOINC client I received BHspin2_1_aarch64-unknown-linux-gnu around midnight and now BHspin2_1_arm-unknown-linux-gnueabihf this morning, both being identical (checksum). First WUs are flagged for the 32bit aarch64, the newest ones for the 32bit arm version...
11) Message boards : Number crunching : Application for ARM based Linux devices (Message 1369)
Posted 14 Aug 2016 by koschi
Post:
As root on your C2:
cd /usr/bin
wget http://kerbodyne.com/boinc/boinc
#(next 2 just to be sure)
chmod 755 /usr/bin/boinc
chown root:root /usr/bin/boinc
service boinc-client restart
grep p_vendor /var/lib/boinc-client/client_state.xml
12) Message boards : Number crunching : Application for ARM based Linux devices (Message 1367)
Posted 14 Aug 2016 by koschi
Post:
And Asteroids works on C2, and Universe BHspin2 works ;-)

http://universeathome.pl/universe/show_host_detail.php?hostid=34279

After I couldn't apply any of the patches linked in the HK forum, I made the BOINC client 7.7.0 write out p_vendor as ARM and it worked straight away. So your server side settings are fine. As soon as /proc/cpuinfo is fixed, after a kernel update it should work nicely for all C2 users. I still don't get what field is wrong though, "CPU implementer : 0x41" with 0x41 being ARM is shown on my C2s...

You can give it a try by replacing your local /usr/bin/boinc with http://kerbodyne.com/boinc/boinc
So far all my WUs are waiting for wingmen... If it works out for you as well, I'll try building a Debian package from the latest BOINC source, so its easier to deploy and pin...







Copyright © 2022 Copernicus Astronomical Centre of the Polish Academy of Sciences
Project server and website managed by Krzysztof 'krzyszp' Piszczek