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

Advanced search

Message boards : Number crunching : Assigning cores to increase speed

Author Message
Bur
Send message
Joined: 25 Feb 20
Posts: 190
ID: 1241833
Credit: 11,745,120
RAC: 137,971
321 LLR Silver: Earned 100,000 credits (426,285)Cullen LLR Gold: Earned 500,000 credits (624,600)ESP LLR Gold: Earned 500,000 credits (636,842)PPS LLR Gold: Earned 500,000 credits (684,350)PSP LLR Bronze: Earned 10,000 credits (35,042)SR5 LLR Gold: Earned 500,000 credits (531,229)SGS LLR Amethyst: Earned 1,000,000 credits (1,008,695)TRP LLR Gold: Earned 500,000 credits (561,429)Woodall LLR Gold: Earned 500,000 credits (781,741)321 Sieve Ruby: Earned 2,000,000 credits (2,107,153)PPS Sieve Amethyst: Earned 1,000,000 credits (1,045,010)AP 26/27 Ruby: Earned 2,000,000 credits (2,470,273)GFN Gold: Earned 500,000 credits (825,613)PSA Bronze: Earned 10,000 credits (10,909)
Message 143100 - Posted: 6 Sep 2020 | 6:35:35 UTC
Last modified: 6 Sep 2020 | 6:40:05 UTC

Thanks to a comment by mackerel I assigned cores to the processes via taskmanager.

So far I tested PPSE and SGS (i7-4... and i3-2110) and both saw an increase in speed of about 15%. It's very similar ratio interestingly, average time with affinity is 0.85 for all three cases.

The i7 is now back to WOO, let's see if it does something for these as well.

You can assign cores via taskmanager, details tab. Right click boinc.exe, "set affinity" and select as many cores as the number of physical cores you have. Mackerel suggested choosing every second (e.g. 0+2 or 0+2+4+6), I don't know if that's important. The affinity is inherited by the processes boinc runs.
____________
Primes: 1281979 & 12+8+1979 & 1+2+8+1+9+7+9 & 1^2+2^2+8^2+1^2+9^2+7^2+9^2 & 12*8+19*79 & 12^8-1979 & 1281979 + 4 (cousin prime)

Profile j.sheridanProject donor
Send message
Joined: 21 Mar 11
Posts: 643
ID: 91622
Credit: 1,093,473,970
RAC: 2,831,607
321 LLR Turquoise: Earned 5,000,000 credits (5,019,701)Cullen LLR Ruby: Earned 2,000,000 credits (4,582,271)ESP LLR Ruby: Earned 2,000,000 credits (4,124,420)Generalized Cullen/Woodall LLR Ruby: Earned 2,000,000 credits (3,666,820)PPS LLR Turquoise: Earned 5,000,000 credits (7,764,560)PSP LLR Turquoise: Earned 5,000,000 credits (5,500,951)SoB LLR Turquoise: Earned 5,000,000 credits (8,511,507)SR5 LLR Ruby: Earned 2,000,000 credits (2,987,619)SGS LLR Turquoise: Earned 5,000,000 credits (5,138,926)TRP LLR Turquoise: Earned 5,000,000 credits (9,717,538)Woodall LLR Ruby: Earned 2,000,000 credits (4,084,622)321 Sieve Sapphire: Earned 20,000,000 credits (20,019,388)Cullen/Woodall Sieve (suspended) Double Silver: Earned 200,000,000 credits (265,102,350)PPS Sieve Double Gold: Earned 500,000,000 credits (513,092,849)TRP Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,801,812)AP 26/27 Emerald: Earned 50,000,000 credits (50,881,155)GFN Double Bronze: Earned 100,000,000 credits (177,481,625)
Message 143105 - Posted: 6 Sep 2020 | 8:42:22 UTC - in response to Message 143100.
Last modified: 6 Sep 2020 | 8:47:16 UTC

Assigning whole cores works too - I've got mine set to assign tasks to (0+1), (2+3) etc - although I've not checked yet whether that's better or worse when you're doing other things on the pc at the same time.
Also, for anyone using ryzen who hasn't seen the previous discussion, note that you need to keep your multithreaded tasks within a ccx/ccd to get the best performance.

mackerelProject donor
Volunteer tester
Avatar
Send message
Joined: 2 Oct 08
Posts: 2410
ID: 29980
Credit: 416,013,940
RAC: 119,133
Discovered 2 mega primesEliminated 1 conjecture "k"Found 3 primes in the 2018 Tour de PrimesFound 1 mega prime in the 2018 Tour de PrimesFound 5 primes in the 2019 Tour de PrimesFound 6 primes in the 2020 Tour de Primes321 LLR Turquoise: Earned 5,000,000 credits (8,774,878)Cullen LLR Turquoise: Earned 5,000,000 credits (5,149,818)ESP LLR Turquoise: Earned 5,000,000 credits (6,454,573)Generalized Cullen/Woodall LLR Turquoise: Earned 5,000,000 credits (5,122,074)PPS LLR Emerald: Earned 50,000,000 credits (75,018,135)PSP LLR Jade: Earned 10,000,000 credits (15,223,714)SoB LLR Jade: Earned 10,000,000 credits (17,319,914)SR5 LLR Sapphire: Earned 20,000,000 credits (23,996,561)SGS LLR Turquoise: Earned 5,000,000 credits (7,342,780)TPS LLR (retired) Bronze: Earned 10,000 credits (34,130)TRP LLR Jade: Earned 10,000,000 credits (18,602,519)Woodall LLR Turquoise: Earned 5,000,000 credits (5,715,464)321 Sieve Sapphire: Earned 20,000,000 credits (20,236,219)Cullen/Woodall Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,383,853)Generalized Cullen/Woodall Sieve (suspended) Sapphire: Earned 20,000,000 credits (20,626,419)PPS Sieve Emerald: Earned 50,000,000 credits (76,969,144)Sierpinski (ESP/PSP/SoB) Sieve (suspended) Ruby: Earned 2,000,000 credits (2,293,882)TRP Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,012,757)AP 26/27 Sapphire: Earned 20,000,000 credits (21,918,894)GFN Emerald: Earned 50,000,000 credits (71,887,807)PSA Ruby: Earned 2,000,000 credits (2,939,755)
Message 143106 - Posted: 6 Sep 2020 | 9:24:37 UTC - in response to Message 143100.

If you run Woo multi-thread, then I don't expect it to have a difference. My past observations only show an improvement for single thread tasks. I would be interested to hear if this is confirmed.

15% improvement is bigger than I saw, which was in the ball park of 10%, but that testing was done a long time ago and things may have changed since then.

Bur
Send message
Joined: 25 Feb 20
Posts: 190
ID: 1241833
Credit: 11,745,120
RAC: 137,971
321 LLR Silver: Earned 100,000 credits (426,285)Cullen LLR Gold: Earned 500,000 credits (624,600)ESP LLR Gold: Earned 500,000 credits (636,842)PPS LLR Gold: Earned 500,000 credits (684,350)PSP LLR Bronze: Earned 10,000 credits (35,042)SR5 LLR Gold: Earned 500,000 credits (531,229)SGS LLR Amethyst: Earned 1,000,000 credits (1,008,695)TRP LLR Gold: Earned 500,000 credits (561,429)Woodall LLR Gold: Earned 500,000 credits (781,741)321 Sieve Ruby: Earned 2,000,000 credits (2,107,153)PPS Sieve Amethyst: Earned 1,000,000 credits (1,045,010)AP 26/27 Ruby: Earned 2,000,000 credits (2,470,273)GFN Gold: Earned 500,000 credits (825,613)PSA Bronze: Earned 10,000 credits (10,909)
Message 143165 - Posted: 9 Sep 2020 | 6:29:39 UTC

Three WOOs done with assigning cores and average went from 304000 s CPU time to 296000 or about 3% increase. It's not much and just based on three tasks each, but it only takes a few mouse clicks, so why not.
____________
Primes: 1281979 & 12+8+1979 & 1+2+8+1+9+7+9 & 1^2+2^2+8^2+1^2+9^2+7^2+9^2 & 12*8+19*79 & 12^8-1979 & 1281979 + 4 (cousin prime)

Profile composite
Volunteer tester
Send message
Joined: 16 Feb 10
Posts: 763
ID: 55391
Credit: 687,657,790
RAC: 108,034
Discovered 2 mega primesFound 1 prime in the 2018 Tour de Primes321 LLR Turquoise: Earned 5,000,000 credits (5,477,467)Cullen LLR Gold: Earned 500,000 credits (776,297)ESP LLR Ruby: Earned 2,000,000 credits (3,120,351)Generalized Cullen/Woodall LLR Ruby: Earned 2,000,000 credits (2,056,207)PPS LLR Jade: Earned 10,000,000 credits (17,757,940)PSP LLR Turquoise: Earned 5,000,000 credits (5,027,818)SoB LLR Sapphire: Earned 20,000,000 credits (24,671,131)SR5 LLR Turquoise: Earned 5,000,000 credits (6,110,877)SGS LLR Ruby: Earned 2,000,000 credits (3,477,744)TRP LLR Turquoise: Earned 5,000,000 credits (7,025,303)Woodall LLR Amethyst: Earned 1,000,000 credits (1,693,614)321 Sieve Emerald: Earned 50,000,000 credits (50,256,050)Cullen/Woodall Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,571,178)Generalized Cullen/Woodall Sieve (suspended) Emerald: Earned 50,000,000 credits (50,009,610)PPS Sieve Double Silver: Earned 200,000,000 credits (312,256,351)Sierpinski (ESP/PSP/SoB) Sieve (suspended) Jade: Earned 10,000,000 credits (10,165,888)TRP Sieve (suspended) Sapphire: Earned 20,000,000 credits (20,071,454)AP 26/27 Turquoise: Earned 5,000,000 credits (6,616,128)GFN Emerald: Earned 50,000,000 credits (52,755,348)PSA Double Bronze: Earned 100,000,000 credits (102,762,384)
Message 143259 - Posted: 13 Sep 2020 | 5:18:13 UTC

Paired logical CPUs (hyperthreads in the same physical core) are numbered adjacently in Windows (CPU 0+1, 2+3, ...) and offset by half the total count of logical CPUs in Linux (CPU 0+4, 1+5, 2+6, 3+7 for 4 physical cores).

Post to thread

Message boards : Number crunching : Assigning cores to increase speed

[Return to PrimeGrid main page]
DNS Powered by DNSEXIT.COM
Copyright © 2005 - 2020 Rytis Slatkevičius (contact) and PrimeGrid community. Server load 0.55, 0.60, 0.70
Generated 21 Oct 2020 | 23:14:07 UTC