log in |
21)
Message boards :
Number crunching :
LLR Version 3.8.20 released
(Message 3317)
Posted 19 Mar 2017 by Thalus From srbase3 to srbase 12 the tag <app> is missing in your config. |
22)
Message boards :
Number crunching :
llr.ini
(Message 3310)
Posted 19 Mar 2017 by Thalus Thats what i meant. Change the content (the ini-File) in the zip-archive. |
23)
Message boards :
Number crunching :
llr.ini
(Message 3308)
Posted 19 Mar 2017 by Thalus But the ini-file is inside the zip-archive. Should be enough to modifiy it there, shouldnt it? |
24)
Message boards :
Number crunching :
llr.ini
(Message 3305)
Posted 19 Mar 2017 by Thalus Am I allowed to edit the llr.ini for (e.g.) reduce the iterations output? Or is there a check so all WUs will fail? |
25)
Message boards :
Cafe :
Solve a base
(Message 3302)
Posted 18 Mar 2017 by Thalus Just wondering how to "Solve a Base"? When/How is a base solved? Is there only 1 solution for each base or could there be multiple? |
26)
Message boards :
Number crunching :
Hyperthreading
(Message 3299)
Posted 18 Mar 2017 by Thalus Hi, I had some spare time the last few days and was wondering if I can increase the performance of my 6700k without OC, so I tried different combinations of HT on/off and useage of a different amount of cores. Therefore I tested each combination for around 3 hours (computer was not used during the tests) with Sierpinski / Riesel Base v0.18. I know that the test duration is not too long but I guess for a short analysis it's good enough. Setup: - Windows 10 Home x64 - Intel i7 6700k (4.2GHz each core) - 16 GB DDR4 RAM 3000MHz Here are my results: HT off, 4 cores: CPU Time: 69-70.8s (avg. 70.9s) Runtime: 79.3-81.8 (avg. 80.1s) Avg. WUs per hour: 179.77 HT on, 4 cores: CPU Time: 79.9-80.7s (avg. 80.3s) Runtime: 83.5-85.6s (avg 84.1s) Avg. WUs per hour: 171.22 HT on, 5 cores: CPU Time: 89.8-90.4s (avg. 90.1s) Runtime: 98.1-101.1s (avg. 99.0s) Avg. WUs per hour: 181.82 HT on, 6 cores: CPU Time: 100.0s-101.6s (avg. 100.9s) Runtime: 109.4s-111.1s (avg. 110.2s) Avg. WUs per hour: 196,0 HT on, 7 cores: CPU Time: 110.6s-110.8s (avg. 110.7s) Runtime: 117.4s-119.9s (avg. 118.2s) Avg. WUs per hour: 213.20 HT on, 8 cores: CPU Time: 121.6s-122.2s (avg. 122.0s) Runtime: 129.8s-131.6s (avg. 130.9s) Avg. WUs per hour: 220.02 Avg. WUs per hour are calculated by: 1/(avg. time) * cores * 3600[/b] |
27)
Message boards :
Number crunching :
Result invalid?
(Message 3298)
Posted 16 Mar 2017 by Thalus Hmm... wont think about that too much since 99.999% of the results are valid. Dont know what happened there. |
28)
Message boards :
Number crunching :
Result invalid?
(Message 3296)
Posted 16 Mar 2017 by Thalus Strange then since I am running everything at stock speed. And didn't change a thing before and after that happened... |
29)
Message boards :
Number crunching :
Result invalid?
(Message 3294)
Posted 16 Mar 2017 by Thalus http://srbase.my-firewall.org/sr5/result.php?resultid=210974124 Why is this one invalid? |
30)
Message boards :
Number crunching :
FMA3 vs AVX
(Message 3293)
Posted 15 Mar 2017 by Thalus Hmm... so I should think about using a RAM-Disk then... By the way, hopefully the new 3.8.20 gets optimized a bit more. Did some testing with single core 3.8.18/3.8.20 and multicore 3.8.20... 3.8.18: 129897*68^129897+1 - 228.383s 3.8.20: 129897*68^129897+1 - 229.175s 3.8.20 8 threads (this is only using ~90% of CPU): 129897*68^129897+1 - 103.033s Strange results... |
31)
Message boards :
Number crunching :
FMA3 vs AVX
(Message 3291)
Posted 15 Mar 2017 by Thalus Hmm... definitly no Temp-Issue, running @4.2GHz each core without throtteling at 1.15V at around 56-65 degrees core. CPU itself has around 58 degrees (at least thats what PECI tells me). But i compared to other i7 6700k and my current times for e.g. Riesel shorts are nearly the same. But i have no clue why your CPU is faster than mine. Is it stock speed or oc? Definitly looking forward to llr 3.8.10 and multicore useage! |
32)
Message boards :
Number crunching :
FMA3 vs AVX
(Message 3289)
Posted 15 Mar 2017 by Thalus I do use HT. But if I disable it my throughput will get ~50% of what I can do now ;-) |
33)
Message boards :
Number crunching :
FMA3 vs AVX
(Message 3287)
Posted 14 Mar 2017 by Thalus I guess the current apps are not optimized for FMA3? The difference is around 5-10% as far as i can see. |
34)
Message boards :
Number crunching :
FMA3 vs AVX
(Message 3283)
Posted 14 Mar 2017 by Thalus Hi, I got some questions concerning Sierpinski / Riesel Base - short: I observed, that my i7 6700k is using zero-padded FMA3 FFT (WU 206102871) while (for example) the i7 of rebirther is using zero-padded AVX FFT (WU 206108473). Is there an advantage of using FMA3 FFTs instead of AVX FFTs concerning runtime? Or are there no differences at all? Thalus |