mersenneforum.org  

Go Back   mersenneforum.org > Great Internet Mersenne Prime Search > Hardware

Reply
 
Thread Tools
Old 2020-10-09, 12:55   #23
henryzz
Just call me Henry
 
henryzz's Avatar
 
"David"
Sep 2007
Liverpool (GMT/BST)

3·23·89 Posts
Default

Quote:
Originally Posted by axn View Post
Unlikely that 560K result has anything to do with memory. The i9 is a 20MB L3 part so the whole FFT should be running entirely from L3 and shouldn't be hitting RAM at all. Probably just seeing multi-threading overhead (particularly since it is such a small FFT size).

Upto 20/8 = 2.5M FFT (or slight smaller to account for other overheads) should run entirely within L3.
Is it possible the L3 bandwidth limit is being hit?
henryzz is offline   Reply With Quote
Old 2020-10-09, 14:34   #24
axn
 
axn's Avatar
 
Jun 2003

155816 Posts
Default

Quote:
Originally Posted by henryzz View Post
Is it possible the L3 bandwidth limit is being hit?
Quite possible, now that you mention it.
axn is offline   Reply With Quote
Old 2020-10-14, 14:01   #25
Xyzzy
 
Xyzzy's Avatar
 
Aug 2002

207238 Posts
Default

Here is a chart of timings for a 6144K FFT on the i5-10600K.

The orange is 3200 14-14-14-34 memory and the yellow is 4000 18-19-19-39 memory.

We also tested the 560K FFT but as expected it was the same for both memory configurations.

We have already sold the i9 so we are unable to test it with the faster memory.
Attached Thumbnails
Click image for larger version

Name:	6144.PNG
Views:	229
Size:	13.4 KB
ID:	23541  
Xyzzy is offline   Reply With Quote
Old 2020-10-14, 14:16   #26
henryzz
Just call me Henry
 
henryzz's Avatar
 
"David"
Sep 2007
Liverpool (GMT/BST)

3·23·89 Posts
Default

Quote:
Originally Posted by Xyzzy View Post
Here is a chart of timings for a 6144K FFT on the i5-10600K.

The orange is 3200 14-14-14-34 memory and the yellow is 4000 18-19-19-39 memory.

We also tested the 560K FFT but as expected it was the same for both memory configurations.

We have already sold the i9 so we are unable to test it with the faster memory.
It would be interesting to see how many cores and at what speed provide the maximum efficiency(lowest TDP limit) at the minimum clock speed that reaches 130 iter/sec
henryzz is offline   Reply With Quote
Old 2020-11-17, 15:30   #27
Xyzzy
 
Xyzzy's Avatar
 
Aug 2002

100001110100112 Posts
Default

We have the 10600K from this thread for sale. $225 shipped (US) seems like a fair price. PM us for more info!

Xyzzy is offline   Reply With Quote
Old 2022-02-08, 00:55   #28
Xyzzy
 
Xyzzy's Avatar
 
Aug 2002

7·1,237 Posts
Default

This benchmark is from a 12400F set to 65W and DDR5 4800 (40-40-40-76) memory on a B660 motherboard.

Just for fun compare these timings with the 10900K and 10600K earlier in this thread.

Code:
Timings for 6144K FFT length (1 core, 1 worker): 15.32 ms.  Throughput: 65.29 iter/sec.
Timings for 6144K FFT length (2 cores, 1 worker):  8.95 ms.  Throughput: 111.74 iter/sec.
Timings for 6144K FFT length (3 cores, 1 worker):  5.71 ms.  Throughput: 175.28 iter/sec.
Timings for 6144K FFT length (4 cores, 1 worker):  4.70 ms.  Throughput: 212.91 iter/sec.
Timings for 6144K FFT length (5 cores, 1 worker):  4.12 ms.  Throughput: 242.86 iter/sec.
Timings for 6144K FFT length (6 cores, 1 worker):  3.71 ms.  Throughput: 269.43 iter/sec.
Code:
CPU: 1 × Intel Core i5-12400F 2.5 GHz 6-Core Processor
CPU Cooler: 1 × Noctua NH-C14S 82.52 CFM CPU Cooler
Motherboard: 1 × Asus ROG STRIX B660-I GAMING WIFI Mini ITX LGA1700 Motherboard
Memory: 1 × Corsair Vengeance 32 GB (2 x 16 GB) DDR5-4800 CL40 Memory
Storage: 1 × Samsung 970 Pro 512 GB M.2-2280 NVME Solid State Drive
Video Card: 1 × EVGA GeForce RTX 3060 Ti 8 GB XC GAMING Video Card
Case: 1 × Cooler Master MasterBox NR200 Mini ITX Desktop Case
Power Supply: 1 × Corsair SF 450 W 80+ Platinum Certified Fully Modular SFX Power Supply
Case Fan: 3 × ARCTIC P12 PST CO 56.3 CFM 120 mm Fan
Xyzzy is offline   Reply With Quote
Old 2022-02-08, 23:23   #29
Mark Rose
 
Mark Rose's Avatar
 
"/X\(‘-‘)/X\"
Jan 2013
https://pedan.tech/

24·199 Posts
Default

Quote:
Originally Posted by Xyzzy View Post
This benchmark is from a 12400F set to 65W and DDR5 4800 (40-40-40-76) memory on a B660 motherboard.

Just for fun compare these timings with the 10900K and 10600K earlier in this thread.

Code:
Timings for 6144K FFT length (1 core, 1 worker): 15.32 ms.  Throughput: 65.29 iter/sec.
Timings for 6144K FFT length (2 cores, 1 worker):  8.95 ms.  Throughput: 111.74 iter/sec.
Timings for 6144K FFT length (3 cores, 1 worker):  5.71 ms.  Throughput: 175.28 iter/sec.
Timings for 6144K FFT length (4 cores, 1 worker):  4.70 ms.  Throughput: 212.91 iter/sec.
Timings for 6144K FFT length (5 cores, 1 worker):  4.12 ms.  Throughput: 242.86 iter/sec.
Timings for 6144K FFT length (6 cores, 1 worker):  3.71 ms.  Throughput: 269.43 iter/sec.
Twice as fast. Nice.
Mark Rose is offline   Reply With Quote
Old 2022-08-27, 02:11   #30
Xyzzy
 
Xyzzy's Avatar
 
Aug 2002

7·1,237 Posts
Default

A mystery CPU:
Code:
Timings for 6144K FFT length (1 core, 1 worker): 19.09 ms.  Throughput: 52.38 iter/sec.
Timings for 6144K FFT length (2 cores, 1 worker):  9.71 ms.  Throughput: 103.03 iter/sec.
Timings for 6144K FFT length (3 cores, 1 worker):  6.64 ms.  Throughput: 150.64 iter/sec.
Timings for 6144K FFT length (4 cores, 1 worker):  4.99 ms.  Throughput: 200.51 iter/sec.
Timings for 6144K FFT length (5 cores, 1 worker):  4.12 ms.  Throughput: 242.67 iter/sec.
Timings for 6144K FFT length (6 cores, 1 worker):  3.44 ms.  Throughput: 291.02 iter/sec.
Timings for 6144K FFT length (7 cores, 1 worker):  3.00 ms.  Throughput: 333.33 iter/sec.
Timings for 6144K FFT length (8 cores, 1 worker):  2.63 ms.  Throughput: 379.54 iter/sec.
Xyzzy is offline   Reply With Quote
Old 2022-08-27, 06:45   #31
kruoli
 
kruoli's Avatar
 
"Oliver"
Sep 2017
Porta Westfalica, DE

23×71 Posts
Default

Looks like the new Ryzen lineup.
kruoli is online now   Reply With Quote
Old 2022-08-27, 15:44   #32
Xyzzy
 
Xyzzy's Avatar
 
Aug 2002

207238 Posts
Default

Attached Thumbnails
Click image for larger version

Name:	5800X3D.png
Views:	105
Size:	77.5 KB
ID:	27253  
Xyzzy is offline   Reply With Quote
Old 2022-08-27, 19:52   #33
sdbardwick
 
sdbardwick's Avatar
 
Aug 2002
North San Diego Coun

821 Posts
Default

Quote:
Originally Posted by Xyzzy View Post
You are getting better results than my 5800x3d /x570 setup. I'll have to go see if I ever enabled any performance enhancements (PBO, XMS, etc,)

Last fiddled with by sdbardwick on 2022-08-27 at 19:53
sdbardwick is offline   Reply With Quote
Reply



Similar Threads
Thread Thread Starter Forum Replies Last Post
2020 Prime95 observations, issues, and suggestions rainchill Software 53 2021-05-04 13:07
Observations of Wieferich primes and Wieferich-1 friendly club hansl Math 3 2020-09-02 10:40
Observations with MaxHighMemWorkers petrw1 PrimeNet 5 2011-04-20 15:56
GIMPS emotions and random observations stars10250 Lounge 6 2008-09-10 05:01

All times are UTC. The time now is 16:30.


Fri Jul 7 16:30:02 UTC 2023 up 323 days, 13:58, 1 user, load averages: 2.98, 2.34, 1.89

Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2023, Jelsoft Enterprises Ltd.

This forum has received and complied with 0 (zero) government requests for information.

Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation.
A copy of the license is included in the FAQ.

≠ ± ∓ ÷ × · − √ ‰ ⊗ ⊕ ⊖ ⊘ ⊙ ≤ ≥ ≦ ≧ ≨ ≩ ≺ ≻ ≼ ≽ ⊏ ⊐ ⊑ ⊒ ² ³ °
∠ ∟ ° ≅ ~ ‖ ⟂ ⫛
≡ ≜ ≈ ∝ ∞ ≪ ≫ ⌊⌋ ⌈⌉ ∘ ∏ ∐ ∑ ∧ ∨ ∩ ∪ ⨀ ⊕ ⊗ 𝖕 𝖖 𝖗 ⊲ ⊳
∅ ∖ ∁ ↦ ↣ ∩ ∪ ⊆ ⊂ ⊄ ⊊ ⊇ ⊃ ⊅ ⊋ ⊖ ∈ ∉ ∋ ∌ ℕ ℤ ℚ ℝ ℂ ℵ ℶ ℷ ℸ 𝓟
¬ ∨ ∧ ⊕ → ← ⇒ ⇐ ⇔ ∀ ∃ ∄ ∴ ∵ ⊤ ⊥ ⊢ ⊨ ⫤ ⊣ … ⋯ ⋮ ⋰ ⋱
∫ ∬ ∭ ∮ ∯ ∰ ∇ ∆ δ ∂ ℱ ℒ ℓ
𝛢𝛼 𝛣𝛽 𝛤𝛾 𝛥𝛿 𝛦𝜀𝜖 𝛧𝜁 𝛨𝜂 𝛩𝜃𝜗 𝛪𝜄 𝛫𝜅 𝛬𝜆 𝛭𝜇 𝛮𝜈 𝛯𝜉 𝛰𝜊 𝛱𝜋 𝛲𝜌 𝛴𝜎𝜍 𝛵𝜏 𝛶𝜐 𝛷𝜙𝜑 𝛸𝜒 𝛹𝜓 𝛺𝜔