Author |
Message |
|
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)
|
|
|
rebirtherVolunteer moderator Project administrator Project developer Project tester Project scientist
 Send message
Joined: 2 Jan 13 Posts: 7720 Credit: 44,264,218 RAC: 0
|
We need to check the code.
Update:
we need a new plan_class and an app for cuda12.8 + cc10 for 50xx. The old plan_class was changed to avoid to send out work for 50xx |
|
|
rebirtherVolunteer moderator Project administrator Project developer Project tester Project scientist
 Send message
Joined: 2 Jan 13 Posts: 7720 Credit: 44,264,218 RAC: 0
|
Pls test it with this file
1. extract the zip in separate folder
2. run mfaktc-win-64.exe -st |
|
|
|
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. |
|
|
rebirtherVolunteer moderator Project administrator Project developer Project tester Project scientist
 Send message
Joined: 2 Jan 13 Posts: 7720 Credit: 44,264,218 RAC: 0
|
Thx for testing, new apps for cuda12.8 support added
Try to get some work so we can be sure all our config is working. |
|
|
|
My host keeps getting the cuda120 apps not the cuda128. I tried resetting the project and restarting BOINC. |
|
|
rebirtherVolunteer moderator Project administrator Project developer Project tester Project scientist
 Send message
Joined: 2 Jan 13 Posts: 7720 Credit: 44,264,218 RAC: 0
|
My host keeps getting the cuda120 apps not the cuda128. I tried resetting the project and restarting BOINC.
That is odd, can you send me the sched_request_srbase.my-firewall.org_sr5.xml? |
|
|