log in |
1)
Message boards :
Number crunching :
mfaktc.exe --perftest for RTX3080/90 cards
(Message 7427)
Posted 13 Mar 2021 by Wailing Angus Beef Is an app_config file running? It did have an app_config.xml. I deleted it, restarted the client and now I'm getting work. Thanks for the help! |
2)
Message boards :
Number crunching :
mfaktc.exe --perftest for RTX3080/90 cards
(Message 7425)
Posted 13 Mar 2021 by Wailing Angus Beef Do you have enabled AMD and NVidia in pref? Yes mfaktc v0.21 (64bit built) Compiletime options THREADS_PER_BLOCK 256 SIEVE_SIZE_LIMIT 32kiB SIEVE_SIZE 193154bits SIEVE_SPLIT 250 MORE_CLASSES enabled Runtime options SievePrimes 25000 SievePrimesAdjust 1 SievePrimesMin 5000 SievePrimesMax 100000 NumStreams 3 CPUStreams 3 GridSize 3 GPU Sieving enabled GPUSievePrimes 82486 WARNING: Read GPUSieveSize=2047 from mfaktc.ini, using max value (128) GPUSieveSize 128Mi bits GPUSieveProcessSize 32Ki bits Checkpoints enabled CheckpointDelay 120s WorkFileAddDelay disabled Stages enabled StopAfterFactor class PrintMode full V5UserID (none) ComputerID (none) AllowSleep no TimeStampInResults no CUDA version info binary compiled for CUDA 11.20 CUDA runtime version 11.20 CUDA driver version 11.20 CUDA device info name GeForce RTX 3090 compute capability 8.6 max threads per block 1024 max shared memory per MP 102400 byte number of multiprocessors 82 clock rate (CUDA cores) 1695MHz memory clock rate: 9751MHz memory bus width: 384 bit Automatic parameters threads per grid 671744 GPUSievePrimes (adjusted) 82486 GPUsieve minimum exponent 1055144 running a simple selftest... Selftest statistics number of tests 107 successfull tests 107 selftest PASSED! ERROR: get_next_assignment(): no valid assignment found in "worktodo.txt" |
3)
Message boards :
Number crunching :
mfaktc.exe --perftest for RTX3080/90 cards
(Message 7423)
Posted 13 Mar 2021 by Wailing Angus Beef It won't give me any work. All I get is this... (GPU info) 13-Mar-2021 16:59:08 [---] CUDA: NVIDIA GPU 0: GeForce RTX 3090 (driver version 461.72, CUDA version 11.2, compute capability 8.6, 4096MB, 3440MB available, 17791 GFLOPS peak) 13-Mar-2021 16:59:08 [---] OpenCL: NVIDIA GPU 0: GeForce RTX 3090 (driver version 461.72, device version OpenCL 1.2 CUDA, 24576MB, 3440MB available, 17791 GFLOPS peak) 13-Mar-2021 17:02:28 [SRBase] update requested by user 13-Mar-2021 17:02:29 [SRBase] Sending scheduler request: Requested by user. 13-Mar-2021 17:02:29 [SRBase] Not requesting tasks: don't need (CPU: ; NVIDIA GPU: ) 13-Mar-2021 17:02:32 [SRBase] Scheduler request completed Nothing other than WUProp is running on this host. https://srbase.my-firewall.org/sr5/show_host_detail.php?hostid=209342 |
4)
Message boards :
Number crunching :
mfaktc.exe --perftest for RTX3080/90 cards
(Message 7421)
Posted 13 Mar 2021 by Wailing Angus Beef Should RTX 3090 systems be able to download and run TF using Ampere GPUs now or are you still testing? I successfully ran the test app. Do you need the output? |
5)
Message boards :
Number crunching :
FMA3 vs AVX
(Message 3373)
Posted 1 Apr 2017 by Wailing Angus Beef Do you see all cores clocking at 4.2Ghz when SRBase is running? Some CPUs automatically downclock when running AVX even thought temps are fine. I have a Xeon Broadwell-EP ES system that will clock at 2.8Ghz running non-optimized apps but downclocks to 2.3Ghz when running SRBase or project apps which use AVX/AVX2. And the i7-6700K only supports 2 memory channels. Are you using 2x 8GB or 4x 4GB sticks? And what speed is yours and Rebs? Reb, what system are you running with 6 memory channels? |
6)
Message boards :
Number crunching :
LLR Version 3.8.20 released
(Message 3336)
Posted 24 Mar 2017 by Wailing Angus Beef If a WU for a particular app typically takes 12 hours using 1 core, then you earn 12 hours on WUProp. If you now use 12 cores to crunch that 1 WU and lets say it takes 1 hour using 12 cores, then will you earn 12 hours work on WUProp or 1 hour? |
7)
Message boards :
Number crunching :
LLR Version 3.8.20 released
(Message 3324)
Posted 22 Mar 2017 by Wailing Angus Beef Will WUProp record all cpu time on the multi-thread WUs? Most do, some don't. |