Posts by petri33
1)
Posted 14 Mar 2024 by petri33 Post: I just blew through 80 or so apparently badly formatted gpu work units on five different hosts. Not seen this type of error before on any of my hosts. Seems similar to the type mentioned in the OP. Good job. Bad smell is from me. It has been fixed. Breathe easy. Petri |
2)
(Message 8255)
Posted 6 Feb 2024 by petri33 Post: RTS 0 |
3)
(Message 8232)
Posted 21 Jan 2024 by petri33 Post: And again. |
4)
(Message 8203)
Posted 14 Jan 2024 by petri33 Post: RTS 0 Again |
5)
(Message 8166)
Posted 7 Dec 2023 by petri33 Post: Solved: My app had made errors and its quota had been reduced. |
6)
(Message 8165)
Posted 6 Dec 2023 by petri33 Post: Hi, I get a message in boincmanager saying: Asteroids@home: Notice from server Your app_info.xml file doesn't have a usable version of Period Search Application. Thu 07 Dec 2023 12:54:16 AM EET I saw this yesterday and again tonight. During the day everything worked just fine. cat projects/asteroidsathome.net_boinc/app_info.xml <app_info> <app> <name>period_search</name> <user_friendly_name>Asteroids</user_friendly_name> <non_cpu_intensive>0</non_cpu_intensive> </app> <file> <name>period_search_10216_x86_64-pc-linux-gnu__cuda118_linux</name> <executable/> </file> <app_version> <app_name>period_search</app_name> <version_num>10213</version_num> <avg_ncpus>1.00</avg_ncpus> <max_ncpus>1.00</max_ncpus> <plan_class>cuda118_win10</plan_class> <file_ref> <file_name>period_search_10216_x86_64-pc-linux-gnu__cuda118_linux</file_name> <main_program/> </file_ref> <coproc> <type>NVIDIA</type> <count>0.125</count> </coproc> <gpu_ram>786432000.000000</gpu_ram> </app_version> <app_version> <app_name>period_search</app_name> <version_num>10217</version_num> <avg_ncpus>1.00</avg_ncpus> <max_ncpus>1.00</max_ncpus> <plan_class>cuda118_win10</plan_class> <file_ref> <file_name>period_search_10216_x86_64-pc-linux-gnu__cuda118_linux</file_name> <main_program/> </file_ref> <coproc> <type>NVIDIA</type> <count>0.125</count> </coproc> <gpu_ram>786432000.000000</gpu_ram> </app_version> <app_version> <app_name>period_search</app_name> <version_num>10218</version_num> <avg_ncpus>1.00</avg_ncpus> <max_ncpus>1.00</max_ncpus> <plan_class>cuda118_linux</plan_class> <file_ref> <file_name>period_search_10216_x86_64-pc-linux-gnu__cuda118_linux</file_name> <main_program/> </file_ref> <coproc> <type>NVIDIA</type> <count>0.125</count> </coproc> <gpu_ram>786432000.000000</gpu_ram> </app_version> <app_version> <app_name>period_search</app_name> <version_num>10215</version_num> <avg_ncpus>1.00</avg_ncpus> <max_ncpus>1.00</max_ncpus> <plan_class>cuda118_linux</plan_class> <file_ref> <file_name>period_search_10216_x86_64-pc-linux-gnu__cuda118_linux</file_name> <main_program/> </file_ref> <coproc> <type>NVIDIA</type> <count>0.125</count> </coproc> <gpu_ram>786432000.000000</gpu_ram> </app_version> </app_info> |
7)
(Message 8155)
Posted 28 Nov 2023 by petri33 Post: RTS 0 |
8)
(Message 8119)
Posted 23 Oct 2023 by petri33 Post: Good mornig, we are out of work again. Petri |
9)
(Message 8106)
Posted 10 Oct 2023 by petri33 Post: ... and again. 0 tasks ready to send. |
10)
(Message 8087)
Posted 29 Sep 2023 by petri33 Post: Hi, it is that time of the month again: Computing status Work Tasks ready to send 0 Thanks! |
11)
(Message 7881)
Posted 30 Aug 2023 by petri33 Post: And again. And again :) -- petri33 |
12)
Posted 30 Aug 2023 by petri33 Post: Hi! Some progress, but not so much. Tweaking every day. Just wait and do other projects in the mean time if you wish. Petri |
13)
(Message 7822)
Posted 19 Jun 2023 by petri33 Post: And again. Last time it was fixed quickly. |
14)
(Message 7816)
Posted 2 Jun 2023 by petri33 Post: Again! I Hope someone notices. |
15)
(Message 7814)
Posted 24 May 2023 by petri33 Post: Work units are available again |
16)
(Message 7813)
Posted 24 May 2023 by petri33 Post: We're out of tasks -- petri33 |
17)
(Message 7794)
Posted 27 Mar 2023 by petri33 Post: Now there is work here to be found. Thanks! |
18)
(Message 7793)
Posted 26 Mar 2023 by petri33 Post: Hi! We seem to be out of work. Computing status Work Tasks ready to send 0 -- Petri |
19)
Posted 17 Feb 2023 by petri33 Post: https://asteroidsathome.net/boinc/workunit.php?wuid=155519775 3090 vs 3 x 2080 Ti Or what? I'm still developing. |
20)
Posted 16 Jan 2023 by petri33 Post: Hi Keith! For now I'm concentrating in memory access patterns. My Titan V (double master) does not do any better than a GTX 2080 Ti. That implies there are problems like strided access, i.e. consecutive threads access non consecutive memory locations. This is BAD: T1 T1 T1 T1 .. (50 x T1) .. T1 T2 T2 T2 .. (50 x T2) .. T2 T3 T3 T3 .. (50 x T3) .. T3 ... A good access pattern would be: T1 T2 T3 T4 ... TN-1 TN T1 T2 T3 T4 ... TN-1 TN T1 T2 T3 ... The bad one achieves only about 0.25% of mem throughput. I tried with float, but accuracy is lost. Results do not validate. -- Petri |
Next 20