mersenneforum.org  

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

Reply
 
Thread Tools
Old 2003-08-28, 10:31   #12
Xyzzy
 
Xyzzy's Avatar
 
Aug 2002

2·32·13·37 Posts
Default

Intel(R) Pentium(R) 4 CPU 2.40GHz
CPU speed: 2398.76 MHz
CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE, SSE2
L1 cache size: 8 KB
L2 cache size: 512 KB
L1 cache line size: 64 bytes
L2 cache line size: 128 bytes
TLBS: 64
Prime95 version 23.6, RdtscTiming=1
Best time for 384K FFT length: 14.690 ms.
Best time for 448K FFT length: 17.471 ms.
Best time for 512K FFT length: 19.890 ms.
Best time for 640K FFT length: 23.868 ms.
Best time for 768K FFT length: 29.038 ms.
Best time for 896K FFT length: 34.443 ms.
Best time for 1024K FFT length: 38.633 ms.
Best time for 1280K FFT length: 50.845 ms.
Best time for 1536K FFT length: 62.298 ms.
Best time for 1792K FFT length: 74.101 ms.
Best time for 2048K FFT length: 83.705 ms.

Intel(R) Pentium(R) 4 CPU 2.40GHz
CPU speed: 2640.04 MHz
CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE, SSE2
L1 cache size: 8 KB
L2 cache size: 512 KB
L1 cache line size: 64 bytes
L2 cache line size: 128 bytes
TLBS: 64
Prime95 version 23.6, RdtscTiming=1
Best time for 384K FFT length: 13.640 ms.
Best time for 448K FFT length: 16.208 ms.
Best time for 512K FFT length: 18.456 ms.
Best time for 640K FFT length: 22.110 ms.
Best time for 768K FFT length: 26.894 ms.
Best time for 896K FFT length: 31.832 ms.
Best time for 1024K FFT length: 35.729 ms.
Best time for 1280K FFT length: 47.144 ms.
Best time for 1536K FFT length: 57.754 ms.
Best time for 1792K FFT length: 68.477 ms.
Best time for 2048K FFT length: 77.737 ms.

Intel(R) Pentium(R) 4 CPU 2.40GHz
CPU speed: 2880.65 MHz
CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE, SSE2
L1 cache size: 8 KB
L2 cache size: 512 KB
L1 cache line size: 64 bytes
L2 cache line size: 128 bytes
TLBS: 64
Prime95 version 23.6, RdtscTiming=1
Best time for 384K FFT length: 12.513 ms.
Best time for 448K FFT length: 14.860 ms.
Best time for 512K FFT length: 16.932 ms.
Best time for 640K FFT length: 20.274 ms.
Best time for 768K FFT length: 24.655 ms.
Best time for 896K FFT length: 29.182 ms.
Best time for 1024K FFT length: 32.720 ms.
Best time for 1280K FFT length: 43.238 ms.
Best time for 1536K FFT length: 52.889 ms.
Best time for 1792K FFT length: 62.724 ms.
Best time for 2048K FFT length: 71.141 ms.

Intel(R) Pentium(R) 4 CPU 2.40GHz
CPU speed: 3123.92 MHz
CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE, SSE2
L1 cache size: 8 KB
L2 cache size: 512 KB
L1 cache line size: 64 bytes
L2 cache line size: 128 bytes
TLBS: 64
Prime95 version 23.6, RdtscTiming=1
Best time for 384K FFT length: 11.526 ms.
Best time for 448K FFT length: 13.691 ms.
Best time for 512K FFT length: 15.612 ms.
Best time for 640K FFT length: 18.692 ms.
Best time for 768K FFT length: 22.748 ms.
Best time for 896K FFT length: 26.893 ms.
Best time for 1024K FFT length: 30.142 ms.
Best time for 1280K FFT length: 39.838 ms.
Best time for 1536K FFT length: 48.765 ms.
Best time for 1792K FFT length: 57.819 ms.
Best time for 2048K FFT length: 65.483 ms.
Xyzzy is offline   Reply With Quote
Old 2003-08-28, 20:59   #13
E_tron
 
E_tron's Avatar
 
Sep 2002
Austin, TX

3×11×17 Posts
Default

I guess you have a really loud fan or your running very hot. I always want to overclock :) , but the acoustics kill me :( , so i stick with the quiet solutions :) .
E_tron is offline   Reply With Quote
Old 2003-08-28, 22:15   #14
Xyzzy
 
Xyzzy's Avatar
 
Aug 2002

2·32·13·37 Posts
Default

I use the stock fan with the 2 case fans that came with the case...

Idle temps are 30C and under load 55-58C...

Intel's yields are so good that a lot of people say that most any "C" model should break 3GHz with ease...

I haven't even tried anything fancy yet... All I did was bump the FSB up to 260...
Xyzzy is offline   Reply With Quote
Old 2003-08-28, 22:58   #15
Xyzzy
 
Xyzzy's Avatar
 
Aug 2002

207228 Posts
Default

I just pushed it to 267MHz FSB for 3.2GHz on stock voltage... At this point adding more voltage allows me to increase speed a little but it is starting to hit the wall...

I suppose getting a $650 CPU for $170 is not a bad deal... I did have to use a more expensive motherboard and memory, so there are other costs involved...

Of course, the memory isn't running at 267MHz FSB... I don't even know if there is any memory out there that will...

Code:
Intel(R) Pentium(R) 4 CPU 2.40GHz
CPU speed: 3195.69 MHz
CPU features: RDTSC, CMOV, PREFETCH, MMX, SSE, SSE2
L1 cache size: 8 KB
L2 cache size: 512 KB
L1 cache line size: 64 bytes
L2 cache line size: 128 bytes
TLBS: 64
Prime95 version 23.6, RdtscTiming=1
Best time for 384K FFT length: 11.271 ms.
Best time for 448K FFT length: 13.370 ms.
Best time for 512K FFT length: 15.244 ms.
Best time for 640K FFT length: 18.229 ms.
Best time for 768K FFT length: 22.230 ms.
Best time for 896K FFT length: 26.273 ms.
Best time for 1024K FFT length: 29.462 ms.
Best time for 1280K FFT length: 38.889 ms.
Best time for 1536K FFT length: 47.612 ms.
Best time for 1792K FFT length: 56.464 ms.
Best time for 2048K FFT length: 63.939 ms.
Xyzzy is offline   Reply With Quote
Old 2003-08-29, 11:12   #16
QuintLeo
 
QuintLeo's Avatar
 
Oct 2002
Lost in the hills of Iowa

26·7 Posts
Default

I suspect there is some ram out there that can be pushed past DDR500 equivilent - but you might have to do some "memory divider" tricks to get MUCH past 267Mhz quad pumped.

Might be better off with a C rev 533 FSB P-IV, for the higher multiplier, as you're probably going to be RAMspeed limited anyway.
QuintLeo is offline   Reply With Quote
Old 2003-08-30, 08:10   #17
NookieN
 
NookieN's Avatar
 
Aug 2002

59 Posts
Default

Quote:
Originally Posted by Xyzzy
The vCore is within Intel's guidelines... (There is no option on an Intel motherboard to adjust it anyways!)
It is 4.7% low... IIRC, the spec is within 5%...
Yeah 1.454V is well within spec for that chip under load. Intel motherboards are about the only ones that adhere to the spec though. Boards from other companies tend to overvolt in order to match the VID (I guess it makes them look like better overclocking boards).


Quote:
Originally Posted by Xyzzy
When I run 1 instance of the torture test, or LL testing, on the box with Hyperthreading turned on, the graph (above) shows that the CPU is not being used fully... When I kick on 2 instances it shows it being used fully and the temp goes up a few degrees... Is it possible to code Prime95 to use those extra cycles?
I did some experimenting with HT and Prime a while ago. You won't get more than a 5% increase in through-put by running two instances. And because of the way Windows handles multitasking with HT, two instances actually degrades overall system performance. One thing that might be nice is if Prime could be coded to do round-off checking in a second thread, but I don't know if that's possible (or worth it).


Quote:
Originally Posted by QuintLeo
Might be better off with a C rev 533 FSB P-IV, for the higher multiplier, as you're probably going to be RAMspeed limited anyway.
Nah, there's not much reason to get a 533 Mhz FSB chip now if you don't have to. Most of the overclockable boards allow you to raise the FSB:MEM clock ratio so you can keep your memory within its tolerance.
NookieN is offline   Reply With Quote
Old 2003-08-30, 18:47   #18
Xyzzy
 
Xyzzy's Avatar
 
Aug 2002

2·32·13·37 Posts
Default

Quote:
Originally Posted by NookieN
I did some experimenting with HT and Prime a while ago. You won't get more than a 5% increase in through-put by running two instances. And because of the way Windows handles multitasking with HT, two instances actually degrades overall system performance. One thing that might be nice is if Prime could be coded to do round-off checking in a second thread, but I don't know if that's possible (or worth it).
Yeah, I wouldn't actually run 2 projects, but for torture test purposes running 2 is harder on the system than 1, so I figured if it can pass 2 running concurrently then the system would be ready for anything...
Xyzzy is offline   Reply With Quote
Old 2003-10-16, 12:19   #19
xtreme2k
 
xtreme2k's Avatar
 
Aug 2002

2×3×29 Posts
Default

I always run 2 instances when stress testing my machine. It does seem to give me machine much more load and much easier to error out.
xtreme2k is offline   Reply With Quote
Reply



Similar Threads
Thread Thread Starter Forum Replies Last Post
Hyperthreading TheMawn Hardware 12 2013-08-15 00:03
Hyperthreading Primeinator Information & Answers 13 2010-05-20 15:15
Should hyperthreading be used? Electrolyte Hardware 5 2006-11-08 01:29
Hyperthreading dave_0273 Hardware 5 2003-12-12 13:22
Hyperthreading RickC Hardware 14 2003-12-04 14:23

All times are UTC. The time now is 16:12.


Fri Jul 7 16:12:38 UTC 2023 up 323 days, 13:41, 0 users, load averages: 2.02, 1.55, 1.30

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