Number of workers vs. number of CPUs - Page 2

retina · 2017-11-30, 01:12

Quote:

Originally Posted by daxmick

Which, from the above results output, appears to be 20 cores and 6 workers, yes? (Which happens to be the suggested number of workers when I first started the program.)

Nope. It looks to me as though 20 cores / 20 workers is better for you.

ctteg · 2018-02-22, 20:33

With apologies for jumping onto this thread. I just ran the test and got the following results for my i7 8700K, 6-cores. This indicates I should use the setting of 1 worker, yes? I have hyper-threading checked for trial factoring, but NOT for LL, P-1, ECM. For what it's worth, that's my default setting.

Timings for 2048K FFT length (6 cores, 1 worker): 1.74 ms. Throughput: 573.89 iter/sec.
Timings for 2048K FFT length (6 cores, 6 workers): 13.94, 14.11, 13.81, 13.88, 14.04, 14.19 ms. Throughput: 428.75 iter/sec.
Timings for 2048K FFT length (6 cores hyperthreaded, 1 worker): 1.81 ms. Throughput: 552.21 iter/sec.
Timings for 2048K FFT length (6 cores hyperthreaded, 6 workers): 14.76, 14.51, 14.41, 14.52, 14.96, 14.42 ms. Throughput: 411.06 iter/sec.
Timings for 2304K FFT length (6 cores, 1 worker): 2.16 ms. Throughput: 462.90 iter/sec.
Timings for 2304K FFT length (6 cores, 6 workers): 15.98, 15.58, 15.51, 15.32, 15.50, 15.83 ms. Throughput: 384.19 iter/sec.
Timings for 2304K FFT length (6 cores hyperthreaded, 1 worker): 2.30 ms. Throughput: 435.24 iter/sec.
Timings for 2304K FFT length (6 cores hyperthreaded, 6 workers): 16.72, 16.57, 16.55, 16.47, 17.16, 17.06 ms. Throughput: 358.20 iter/sec.
Timings for 2400K FFT length (6 cores, 1 worker): 2.18 ms. Throughput: 457.92 iter/sec.
Timings for 2400K FFT length (6 cores, 6 workers): 16.72, 16.50, 16.25, 16.09, 16.45, 16.61 ms. Throughput: 365.12 iter/sec.
Timings for 2400K FFT length (6 cores hyperthreaded, 1 worker): 2.58 ms. Throughput: 386.97 iter/sec.
Timings for 2400K FFT length (6 cores hyperthreaded, 6 workers): 18.28, 18.26, 18.98, 18.05, 18.80, 18.41 ms. Throughput: 325.06 iter/sec.
Timings for 2560K FFT length (6 cores, 1 worker): 2.44 ms. Throughput: 410.15 iter/sec.
Timings for 2560K FFT length (6 cores, 6 workers): 17.64, 17.54, 17.61, 17.53, 17.58, 17.63 ms. Throughput: 341.13 iter/sec.
Timings for 2560K FFT length (6 cores hyperthreaded, 1 worker): 2.58 ms. Throughput: 387.11 iter/sec.
Timings for 2560K FFT length (6 cores hyperthreaded, 6 workers): 18.41, 18.21, 17.93, 17.76, 18.89, 18.67 ms. Throughput: 327.82 iter/sec.
Timings for 2688K FFT length (6 cores, 1 worker): 2.58 ms. Throughput: 386.93 iter/sec.

Prime95 · 2018-02-22, 23:40

Quote:

Originally Posted by ctteg

With apologies for jumping onto this thread. I just ran the test and got the following results for my i7 8700K, 6-cores. This indicates I should use the setting of 1 worker, yes?

Yes

kladner · 2018-02-23, 01:27

"With apologies....."
Please. No need. Your post seems completely agreeable with the topic.

ctteg · 2018-02-23, 01:33

Thank you both. Much appreciated.

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
Change number of workers not interactively	Mcbsc	Software	1	2015-03-09 14:25
Number of CPUs to use	houding	Software	3	2015-02-26 19:56
Number of distinct prime factors of a Double Mersenne number	aketilander	Operazione Doppi Mersennes	1	2012-11-09 21:16
command line switch for the number of workers to start	roemer2201	Software	6	2012-02-16 07:47
Fermat number F6=18446744073709551617 is a composite number. Proof.	literka	Factoring	5	2012-01-30 12:28

2018-02-22, 20:33	#13
ctteg Feb 2018 Connecticut, USA 7 Posts	With apologies for jumping onto this thread. I just ran the test and got the following results for my i7 8700K, 6-cores. This indicates I should use the setting of 1 worker, yes? I have hyper-threading checked for trial factoring, but NOT for LL, P-1, ECM. For what it's worth, that's my default setting. Timings for 2048K FFT length (6 cores, 1 worker): 1.74 ms. Throughput: 573.89 iter/sec. Timings for 2048K FFT length (6 cores, 6 workers): 13.94, 14.11, 13.81, 13.88, 14.04, 14.19 ms. Throughput: 428.75 iter/sec. Timings for 2048K FFT length (6 cores hyperthreaded, 1 worker): 1.81 ms. Throughput: 552.21 iter/sec. Timings for 2048K FFT length (6 cores hyperthreaded, 6 workers): 14.76, 14.51, 14.41, 14.52, 14.96, 14.42 ms. Throughput: 411.06 iter/sec. Timings for 2304K FFT length (6 cores, 1 worker): 2.16 ms. Throughput: 462.90 iter/sec. Timings for 2304K FFT length (6 cores, 6 workers): 15.98, 15.58, 15.51, 15.32, 15.50, 15.83 ms. Throughput: 384.19 iter/sec. Timings for 2304K FFT length (6 cores hyperthreaded, 1 worker): 2.30 ms. Throughput: 435.24 iter/sec. Timings for 2304K FFT length (6 cores hyperthreaded, 6 workers): 16.72, 16.57, 16.55, 16.47, 17.16, 17.06 ms. Throughput: 358.20 iter/sec. Timings for 2400K FFT length (6 cores, 1 worker): 2.18 ms. Throughput: 457.92 iter/sec. Timings for 2400K FFT length (6 cores, 6 workers): 16.72, 16.50, 16.25, 16.09, 16.45, 16.61 ms. Throughput: 365.12 iter/sec. Timings for 2400K FFT length (6 cores hyperthreaded, 1 worker): 2.58 ms. Throughput: 386.97 iter/sec. Timings for 2400K FFT length (6 cores hyperthreaded, 6 workers): 18.28, 18.26, 18.98, 18.05, 18.80, 18.41 ms. Throughput: 325.06 iter/sec. Timings for 2560K FFT length (6 cores, 1 worker): 2.44 ms. Throughput: 410.15 iter/sec. Timings for 2560K FFT length (6 cores, 6 workers): 17.64, 17.54, 17.61, 17.53, 17.58, 17.63 ms. Throughput: 341.13 iter/sec. Timings for 2560K FFT length (6 cores hyperthreaded, 1 worker): 2.58 ms. Throughput: 387.11 iter/sec. Timings for 2560K FFT length (6 cores hyperthreaded, 6 workers): 18.41, 18.21, 17.93, 17.76, 18.89, 18.67 ms. Throughput: 327.82 iter/sec. Timings for 2688K FFT length (6 cores, 1 worker): 2.58 ms. Throughput: 386.93 iter/sec.

2018-02-23, 01:27	#15
kladner "Kieren" Jul 2011 In My Own Galaxy! 2×3×1,693 Posts	"With apologies....." Please. No need. Your post seems completely agreeable with the topic.

2018-02-23, 01:33	#16
ctteg Feb 2018 Connecticut, USA 7 Posts	Thank you both. Much appreciated.