Posts by NucularLuc

1) Message boards : News : new TF app testing started (Message 10639)
Posted 23 Apr 2025 by NucularLuc

Sorry for the late reply and thank you for your help in the other thread. I am getting run times of 222 to 240 seconds for Bit 75-76 in the 251M to 303M range

2) Message boards : Number crunching : TF App: No kernel image error for RTX 5080 (Message 10620)
Posted 12 Apr 2025 by NucularLuc

My host keeps getting the cuda120 apps not the cuda128. I tried resetting the project and restarting BOINC.

3) Message boards : Number crunching : TF App: No kernel image error for RTX 5080 (Message 10613)
Posted 11 Apr 2025 by NucularLuc

Pls test it with this file

1. extract the zip in separate folder
2. run mfaktc-win-64.exe -st

The .exe successfully ran. Here is the end of the output:

Selftest statistics
number of tests 26192
successfull tests 26192

kernel | success | fail
-------------------+---------+-------
UNKNOWN kernel | 0 | 0
71bit_mul24 | 2586 | 0
75bit_mul32 | 2682 | 0
95bit_mul32 | 2867 | 0
barrett76_mul32 | 1096 | 0
barrett77_mul32 | 1114 | 0
barrett79_mul32 | 1153 | 0
barrett87_mul32 | 1066 | 0
barrett88_mul32 | 1069 | 0
barrett92_mul32 | 1084 | 0
75bit_mul32_gs | 2420 | 0
95bit_mul32_gs | 2597 | 0
barrett76_mul32_gs | 1079 | 0
barrett77_mul32_gs | 1096 | 0
barrett79_mul32_gs | 1130 | 0
barrett87_mul32_gs | 1044 | 0
barrett88_mul32_gs | 1047 | 0
barrett92_mul32_gs | 1062 | 0

Let me know if you need anything else.

4) Message boards : Number crunching : TF App: No kernel image error for RTX 5080 (Message 10610)
Posted 11 Apr 2025 by NucularLuc

I recently got a RTX 5080, but I am getting computation errors. Here is part of the Stderr output of a workunit:

CUDA version info
binary compiled for CUDA 12.0
CUDA runtime version 12.0
CUDA driver version 12.80

CUDA device info
name NVIDIA GeForce RTX 5080
compute capability 12.0
max threads per block 1024
max shared memory per MP 102400 byte
number of multiprocessors 84
clock rate (CUDA cores) 2700MHz
memory clock rate: 15001MHz
memory bus width: 256 bit

Automatic parameters
threads per grid 688128
GPUSievePrimes (adjusted) 82486
GPUsieve minimum exponent 1055144

running a simple selftest...
ERROR: cudaGetLastError() returned 209: no kernel image is available for execution on the device
2025-04-05 17:07:18 (59080): mfaktc-win-64.exe exited; CPU time 0.015625
2025-04-05 17:07:18 (59080): app exit status: 0x1
2025-04-05 17:07:18 (59080): called boinc_finish(195)

5) Message boards : News : new TF app testing started (Message 10601)
Posted 6 Apr 2025 by NucularLuc

If you are a lucky owner of a 5080/90 post your runtimes here.

I recently got a RTX 5080, but I am getting computation errors. Here is part of the Std Out of a workunit:

CUDA version info
binary compiled for CUDA 12.0
CUDA runtime version 12.0
CUDA driver version 12.80

CUDA device info
name NVIDIA GeForce RTX 5080
compute capability 12.0
max threads per block 1024
max shared memory per MP 102400 byte
number of multiprocessors 84
clock rate (CUDA cores) 2700MHz
memory clock rate: 15001MHz
memory bus width: 256 bit

Automatic parameters
threads per grid 688128
GPUSievePrimes (adjusted) 82486
GPUsieve minimum exponent 1055144

running a simple selftest...
ERROR: cudaGetLastError() returned 209: no kernel image is available for execution on the device
2025-04-05 17:07:18 (59080): mfaktc-win-64.exe exited; CPU time 0.015625
2025-04-05 17:07:18 (59080): app exit status: 0x1
2025-04-05 17:07:18 (59080): called boinc_finish(195)

I suspect there's an issue with compiling mfaktc-win-64. But no rush; I can work on other projects in the meantime.

6) Message boards : Number crunching : Calculation error Intel arc gpu (Message 10596)
Posted 6 Apr 2025 by NucularLuc

Does just depend on the specific project or is there a rule of thumb?

7) Message boards : News : project update (Message 9950)
Posted 2 May 2024 by NucularLuc

I'm glad you're back and hoping for a full recovery.

8) Message boards : Number crunching : Too many workunits to finish. (Message 8157)
Posted 28 Mar 2022 by NucularLuc

Because World Community Gird is offline, I have a host doing mostly SRBase. So, I have an app_config file to set the number of threads and concurrent tasks for each of the apps.

However, BOINC keeps too many tasks to finish by the deadline. I have set the BOINC client and my SRBase preferences for this host not to store any additional work, but the problem persists. I was hoping it would sort itself out. Am I missing something?