PrimeGrid
Please visit donation page to help the project cover running costs for this month

Toggle Menu

Join PrimeGrid

Returning Participants

Community

Leader Boards

Results

Other

drummers-lowrise
11) Message boards : Project Staging Area : Can you multi-thread PRPNet apps? (Message 118198)
Posted 1057 days ago by 288larssonProject donor
Ok here is what I did:

1. I downloaded the updated console llr windows app from here - http://jpenne.free.fr/index2.html as you suggested. The app that I downloaded b4 was ancient apparently. So was a needed updated.

2. Created a batch file in my prpclient-1 directory for the 1 instance I will be running. the batch file is called cllr.bat and only has one line: "@cllr64.exe -t2 %*" no quotes.

3. Edited the prpclient.ini file with the line for the llr.exe app. It now reads - "llrexe.exe=cllr64.bat" (again no quotes).


So now when I run the prpclient.exe (or the single start batch file), it uses that cllr64 batch file to start the cllr main app with the number of threads I'd like to use. -t2 for 2, -t4 for 4, -t8 for 8, etc. just change the batch file for the number of threads.


Very nice. Will leave this running once my SOB task finishes and see how it does.


Thanks for the help with those links.

Hi The bold text should be the same
12) Message boards : Generalized Fermat Prime Search : GTX 1080 anomaly / Genefer 3.3.2 (Message 107244)
Posted 1453 days ago by 288larssonProject donor
Hi can not get HD7970 to run. on Win10-64bit

A new Windows binary "3.3.2-4-dev" containing a fix is available: https://app.assembla.com/spaces/genefer/subversion/source/HEAD/trunk/bin

Tell me if it's OK.

Hi it's OK.:)

device number: 0
Running on platform 'AMD Accelerated Parallel Processing', device 'Tahiti', vendor 'Advanced Micro Devices, Inc.', version 'OpenCL 1.2 AMD-APP (2264.11)' and driver '2264.11'.
32 computeUnits @ 925MHz, memSize=3072MB, cacheSize=16kB, cacheLineSize=64B, localMemSize=32kB, maxWorkGroupSize=256.
High priority change succeeded.
Generalized Fermat Prime Search benchmarks
50000000^32768+1 252280 digits OCL2 Estimated time: 0:03:19
25000000^65536+1 484832 digits OCL2 Estimated time: 0:07:26
8000000^131072+1 904802 digits OCL3 Estimated time: 0:14:40
46000000^131072+1 1004373 digits OCL2 Estimated time: 0:22:20
2800000^262144+1 1690084 digits OCL4 Estimated time: 0:42:20
1500000^524288+1 3238051 digits OCL4 Estimated time: 2:09:00
900000^1048576+1 6243476 digits OCL4 Estimated time: 7:44:00
130000^2097152+1 10724717 digits OCL Estimated time: 17:30:00
100000^4194304+1 20971520 digits OCL Estimated time: 67:40:00
Low priority change succeeded.
13) Message boards : Generalized Fermat Prime Search : GTX 1080 anomaly / Genefer 3.3.2 (Message 107219)
Posted 1453 days ago by 288larssonProject donor
Hi can not get HD7970 to run. on Win10-64bit

C:\folding\prpnet\genefer-329>geneferocl_windows332-3 -q "2178956^131072+1"
geneferocl 3.3.2-3 (Windows/OpenCL/32-bit)

Copyright 2001-2017, Yves Gallot
Copyright 2009, Mark Rodenkirch, David Underbakke
Copyright 2010-2012, Shoichiro Yamada, Ken Brazier
Copyright 2011-2014, Michael Goetz, Ronald Schneider
Copyright 2011-2017, Iain Bethune
Genefer is free source code, under the MIT license.

Command line: geneferocl_windows332-3 -q 2178956^131072+1

Low priority change succeeded.

Testing 2178956^131072+1...
Using OCL5 transform
Running on platform 'AMD Accelerated Parallel Processing', device 'Tahiti', vendor 'Advanced Micro Devices, Inc.', version 'OpenCL 1.2 AMD-APP (2264.11)' and driver '2264.11'.
32 computeUnits @ 925MHz, memSize=3072MB, cacheSize=16kB, cacheLineSize=64B, localMemSize=32kB, maxWorkGroupSize=256.
Error: build program failed.
"C:\Users\pip\AppData\Local\Temp\OCL9108T2.cl", line 232: error: work group
size exceeds the maximum default value for the selected device
__kernel __attribute__((reqd_work_group_size(B_256 * CHUNK256, 1, 1)))
^

"C:\Users\pip\AppData\Local\Temp\OCL9108T2.cl", line 245: error: work group
size exceeds the maximum default value for the selected device
__kernel __attribute__((reqd_work_group_size(B_256 * CHUNK256, 1, 1)))
^

"C:\Users\pip\AppData\Local\Temp\OCL9108T2.cl", line 262: error: work group
size exceeds the maximum default value for the selected device
__kernel __attribute__((reqd_work_group_size(B_1024 * CHUNK1024, 1, 1)))
^

"C:\Users\pip\AppData\Local\Temp\OCL9108T2.cl", line 277: error: work group
size exceeds the maximum default value for the selected device
__kernel __attribute__((reqd_work_group_size(B_1024 * CHUNK1024, 1, 1)))
^

"C:\Users\pip\AppData\Local\Temp\OCL9108T2.cl", line 468: error: work group
size exceeds the maximum default value for the selected device
__kernel __attribute__((reqd_work_group_size(2048 / 4, 1, 1)))
^

"C:\Users\pip\AppData\Local\Temp\OCL9108T2.cl", line 499: error: work group
size exceeds the maximum default value for the selected device
__kernel __attribute__((reqd_work_group_size(4096 / 4, 1, 1)))
^

6 errors detected in the compilation of "C:\Users\pip\AppData\Local\Temp\OCL9108T2.cl".
Frontend phase failed compilation.

Error: OpenCL error detected: CL_BUILD_PROGRAM_FAILURE.
Errors occurred for all available transform implementations
14) Message boards : Number crunching : LLR 3.8.20 testing (Message 105693)
Posted 1502 days ago by 288larssonProject donor

Boinc test win64 avx
Host http://dev.primegrid.com/show_host_detail.php?hostid=455138
sob http://dev.primegrid.com/result.php?resultid=1774
sob-prp http://dev.primegrid.com/result.php?resultid=663


Just checking, you really have you BOINC prefs set to checkpoint every 11 minutes??

- Iain

Hi yes correct
15) Message boards : Number crunching : LLR Version 3.8.20 released (Message 104753)
Posted 1529 days ago by 288larssonProject donor
Hi This works for me
<app_info> <app> <name>llrSR5</name> <user_friendly_name>Sierpinski/Riesel Base 5 Problem (LLR)</user_friendly_name> <fraction_done_exact/> </app> <file_info> <name>primegrid_llr_wrapper_7.06_windows_x86_64.exe</name> <status>1</status> <executable/> </file_info> <file_info> <name>cllr64.3.8.18.exe</name> <status>1</status> <executable/> </file_info> <file_info> <name>llr.ini.6.07</name> <status>1</status> </file_info> <app_version> <app_name>llrSR5</app_name> <version_num>705</version_num> <platform>windows_x86_64</platform> <avg_ncpus>1.000000</avg_ncpus> <max_ncpus>1.000000</max_ncpus> <api_version>6.11.7</api_version> <file_ref> <file_name>primegrid_llr_wrapper_7.06_windows_x86_64.exe</file_name> <main_program/> </file_ref> <file_ref> <file_name>cllr64.3.8.18.exe</file_name> <open_name>primegrid_cllr.exe</open_name> <copy_file/> </file_ref> <file_ref> <file_name>llr.ini.6.07</file_name> <open_name>llr.ini</open_name> <copy_file/> </file_ref> </app_version> </app_info>
16) Message boards : Generalized Fermat Prime Search : Running more than one GFN per GPU? (Message 104036)
Posted 1545 days ago by 288larssonProject donor
hi
<app_config> <app> <name>genefer16</name> <gpu_versions> <gpu_usage>0.5</gpu_usage> <cpu_usage>0.5</cpu_usage> </gpu_versions> <fraction_done_exact/> </app> </app_config>

it is not faster for me
17) Message boards : Number crunching : Badges II (Message 103406)
Posted 1557 days ago by 288larssonProject donor
18) Message boards : AP26 - AP27 Search : App testing (Message 97861)
Posted 1701 days ago by 288larssonProject donor
Linux avx2 http://dev.primegrid.com/result.php?resultid=735426354

Linux ATI GPU http://dev.primegrid.com/result.php?resultid=735426352

Linux Nvidia GPU http://dev.primegrid.com/result.php?resultid=735427348
19) Message boards : AP26 - AP27 Search : App testing (Message 97845)
Posted 1701 days ago by 288larssonProject donor
Linux Nvidia GPU, GTX 980ti, GPU tests passed.
Linux ATI GPU, AMD Hawaii, GPU tests passed
20) Message boards : Number crunching : Did anyone get a 1080 today? (Message 97293)
Posted 1724 days ago by 288larssonProject donor
Do I have to run an app_config.xml ?
Can someone post an example for GFN and PPS, Thanks

Hi yes
<app_config> <app> <name>genefer15</name> <gpu_versions> <gpu_usage>0.5</gpu_usage> <cpu_usage>0.5</cpu_usage> </gpu_versions> <fraction_done_exact/> </app> <app> <name>pps_sr2sieve</name> <gpu_versions> <gpu_usage>0.5</gpu_usage> <cpu_usage>0.5</cpu_usage> </gpu_versions> <fraction_done_exact/> </app> </app_config>

it is not faster for me, but you can try


Next 10 posts
[Return to PrimeGrid main page]
DNS Powered by DNSEXIT.COM
Copyright © 2005 - 2021 Rytis Slatkevičius (contact) and PrimeGrid community. Server load 4.76, 4.28, 3.99
Generated 17 Apr 2021 | 6:05:56 UTC