Posts by cyrusNGC_224@P3D

1) (Message 5720)
Posted 8 Mar 2018 by cyrusNGC_224@P3D
Post:
Again out of work!
2) (Message 5071)
Posted 30 Nov 2016 by cyrusNGC_224@P3D
Post:
But why one CPU core?
This app utilise only few seconds per task.
3) (Message 4831)
Posted 21 Mar 2016 by cyrusNGC_224@P3D
Post:
It's a fake.
4) (Message 4260)
Posted 26 Mar 2015 by cyrusNGC_224@P3D
Post:
Look at: http://asteroidsathome.net/boinc/server_status.php
5) (Message 4193)
Posted 21 Mar 2015 by cyrusNGC_224@P3D
Post:
Yes nearly 99,9999999% fealure rate.

Equal script for linux:
#!/bin/sh
#time in minutes m
SLEEP=2m

while true
do
        sleep $SLEEP
        boinccmd --project http://asteroidsathome.net/boinc/ update
done
6) (Message 3604)
Posted 12 Sep 2014 by cyrusNGC_224@P3D
Post:
Asteroids has no constant wu's anymore.
7) (Message 3598)
Posted 6 Sep 2014 by cyrusNGC_224@P3D
Post:
Wrong!
These long wu's are the normal running times at asteroids.

Look at your older results: http://asteroidsathome.net/boinc/workunit.php?wuid=19533687
8) (Message 3582)
Posted 24 Aug 2014 by cyrusNGC_224@P3D
Post:
Your machines receive CUDA work!?
http://asteroidsathome.net/boinc/host_app_versions.php?hostid=82538
9) (Message 3464)
Posted 4 Aug 2014 by cyrusNGC_224@P3D
Post:
Yes, and I have any wu's that run out on 5.8.
10) (Message 3463)
Posted 4 Aug 2014 by cyrusNGC_224@P3D
Post:
Yes, and I have any wu's that run out on 5.8.
11) (Message 3422)
Posted 23 Jul 2014 by cyrusNGC_224@P3D
Post:
In my computer list there is an pentium4 m and pentium3 tualatin. The p4 ist faster, because of sse2!

But on the whole the old computer are too inefficient. Compared to modern cpus as amds kabini or intel pentium.
12) (Message 3395)
Posted 21 Jul 2014 by cyrusNGC_224@P3D
Post:
You should first use the forum search, or look to see if there is something about it.

http://asteroidsathome.net/boinc/forum_thread.php?id=336
http://asteroidsathome.net/boinc/forum_thread.php?id=337
13) (Message 3392)
Posted 21 Jul 2014 by cyrusNGC_224@P3D
Post:
Look at this: http://asteroidsathome.net/boinc/forum_thread.php?id=336&postid=3379
14) (Message 3380)
Posted 21 Jul 2014 by cyrusNGC_224@P3D
Post:

A lot (if not all) of the finished results that I still have here on my hosts are not "in progress" in the server result lists anymore so reporting must have worked.

So currently nothing gets lost, I cannot receive more work though.
Exactly the same here!

With different client- and os versions.
But some run out of work soon.
15) (Message 3299)
Posted 3 Jul 2014 by cyrusNGC_224@P3D
Post:
As was to be expected the deadline was 1.6. 214h wasted. :(
16) (Message 3250)
Posted 28 Jun 2014 by cyrusNGC_224@P3D
Post:
can any one tell me how to get use out of the gpu on these devices , I'm a noob trying to learn this stuff - any answers thanks!
By you look here [1], you see that there are currently only cuda apps.

[1] http://asteroidsathome.net/boinc/apps.php
17) (Message 3155)
Posted 6 Jun 2014 by cyrusNGC_224@P3D
Post:
But all in all there seems to be something wrong with the cuda code; the gpu app should be much faster than a cpu wu.
Obviously, it is very dependent on the algorithms. Most benefits does indeed MW@H. But other projects like Einstein or SETI use the GPU not so good too.


The cuda app takes almost no CPU load. So it's not necessary to free a core for A@h cuda GPU app (so far).
18) (Message 2862)
Posted 21 Mar 2014 by cyrusNGC_224@P3D
Post:
I have a AMD processor, which supported FMA4 and does not clock down.
19) (Message 2705)
Posted 12 Mar 2014 by cyrusNGC_224@P3D
Post:
My new AMD A10-7850K with Steamroller cores seems to be so far a little faster with the AVX version. Unfortunately, he gets currently only SSE2 WUs.
Perhaps this will change when the whole pending jobs are valid.
SSE2/3: ~ 9300 s
AVX: ~ 8900 s
20) (Message 2703)
Posted 12 Mar 2014 by cyrusNGC_224@P3D
Post:
WOW, the CUDA code of Asteroids is very well commented and readable!
I can understand it. 99 of it without looking into CUDA API reference! This is COOL.
Re-write this into OpenCL will be a toy :).

Hmm, will need the latest version of it soon.............. :)

Because you develop it for OpenCL?
That would be nice if it is making progress!


Next 20