Going "warp speed" on Air cooling 😁
OC'ing old stuff is so much FUN 😀

Most likely unstable at this speed, at least for games. Dropped it back to 4017mhz afterwards

One more result to the "table".

Dual P3 450MHz - 04m 23.797s

EDIT: After some RAM tweaks, 04m 20.734s

Abit AN7, Athlon XP-M 2800+ @ 11x228 (2500MHz), 1x1GB DDR @228 2.5-3-3-11 CPC

lazibayer wrote:

Still the same platform: […]
Show full quote

Still the same platform:

CPU: K6-3+450 ACZ
Mobo: P5A-B
RAM: 256MB PC133 2-2-2
OS: XP SP3

But this time I turned off some services and the fancy interface.
112x5.5:

p5a_112_55_superpi_0.jpg

124x5, no L3:

p5a_124_5_noL3_superpi_0.jpg

112x5.5, no L3:

p5a_112_55_noL3_superpi_0.jpg

Same hardware platform, OC to 133x4.5, no L3:

amd386dx-40
cyrix fastmath 83d87-40
the infamous macronics 83c306/305 chipset, which has 8kb integrated cache but no onboard cache
16mb dram
time: 5h 56m 15s

this is very disappointing because my original expectation was 4-4.5 hours. guess the only way to improve is to find a board with 128kb cache, it may get under 5:30 but less than 5 hours is unlikely.

Celeron 2.6 Northwood @ 3357mhz

Celeron D does quite a bit better than Celeron Northwood

X3370 + 240mm AIO w/Delta fans :

A bit slower than QX9770 @ 4,5GHz from before... however, it's with higher FSB and not deadly Vcore (stable for high load 3D benching as well).

already have collected these results, might as well post...

Athlon II X2 260 (3.2GHz, DDR2-800 CL5) - 25s
Athlon X2 7850 (2.8GHz, DDR2-800 CL5) - 28s
Core2 SU9600 (1.6GHz, 1.8GHz turbo, DDR2-667) - 34s
Athlon X2 4850e (2.5GHz, DDR2-800 CL5) - 36s
Turion X2 1.6GHz (DDR2-667) - 57s
Athlon XP 2800+ (2083MHz, KT333, DDR-333 CL3) - 1m
Athlon XP 2500+ (1833MHz, KT333, DDR-333 CL2) - 1m1s
Sempron 2300+ (1583MHz, KT333, DDR-333 CL2) - 1m15s
Pentium M 1MB 1.0GHz (i855pm, DDR-266) - 1m25s
Pentium M 2MB 1.2GHz (i855pm, DDR-266) - 1m4s
Pentium M 2MB 1.2GHz (i915gm, DDR2-400) - 1m1s
Pentium M 1MB 1.7GHz (i855pm, DDR-333) - 56s
Pentium M 2MB 1.6GHz (i855pm, DDR-333) - 53s
Pentium 3 933MHz (PC-133) - 2m17s
Pentium 3M 800 (i830gm, PC-133 CL2) - 2m35s
Pentium 3M 1333MHz (i830gm, PC-133 CL3) - 2m20s
Pentium 3M 1333MHz (i830gm, PC-133 CL2) - 2m06s
Pentium 3M 1333MHz (i830gm, PC-133 CL2) - 1m57s (screen mode at 800x600x16 instead of 1024x768x32)
Pentium 3 600e (PC-100) - 3m21s
Pentium MMX 166 (256KB L2) - 15m2s

Here is an Intel i7 3770K running on an Asus Maximus IV Extreme P67 motherboard. The OS used is Windows 10 with USB WLan and other bloat running in the background.

i7 3770K @4.8: 7.625s

Intel i9 i9900k , Asus Mamximus XI Hero , Win 10

noshutdown wrote:

amd386dx-40 cyrix fastmath 83d87-40 the infamous macronics 83c306/305 chipset, which has 8kb integrated cache but no onboard cac […]
Show full quote

amd386dx-40
cyrix fastmath 83d87-40
the infamous macronics 83c306/305 chipset, which has 8kb integrated cache but no onboard cache
16mb dram
time: 5h 56m 15s

this is very disappointing because my original expectation was 4-4.5 hours. guess the only way to improve is to find a board with 128kb cache, it may get under 5:30 but less than 5 hours is unlikely.

i got another board with umc82c491 chipset, and with 128kb cache installed.
time: 5h 43m 44s
so its only about 3.6% faster, and i guess its because the 387 is so slow that it takes up most of the time, making cache/ram performance unimportant for this benchmark.

disabling the IGP improved the time by over 35s on this Compaq 7476

for some reason I can't get the FSB 124 jumper setting to work with this CPU atm, it always worked fine with the PII (hmmm maybe I was running an older bios), with the p3 it detects it as 133, and that's too high for 1.65v and windows is unstable, so 112 it is for now, still kind of nice, compared to:

Celeron northwood + slow motherboard, not worthy of 2.8GHz performance, but hey at least is better than stock, that jumper setting to 133 decreases the time by 56s!
I remember when I bought this motherboard a long while back and it felt horribly slow even when it was fairly new, but the jumper OC to 2.8 made a nice difference, even for basic use, kind of the saving aspect of this combo.
disabling the IGP has potential to improve it even more, maybe another time

Forgot about this thread!

PIII-S @ 1628MHz, 155MHz FSB
2GB DDR @ 310MHz, 2-2-2-5
9800 Pro @ stock, Catalyst 4.12
X-Fi Platinum
QDI Advance 12T mobo, Via Apollo Pro266T chipset
WinXP Media Center 2005 SP3

1m 22.479s

Here's a Dell laptop I just picked up for $15 at a yard sale.

Pentium T4300 (2.1GHz Penryn with FSB800 and only 1MB of L2. Also missing SSE4.1)
4GB dual channel DDR2-800
GMA4500 MHD
Win10 x64, build 1809

27.547s

Not bad at first glance, but my C2D E8600 (3.33GHz) is almost twice as fast at 14.106s. That chip has the full 6MB of L2, FSB1333 + DDR3-1333, and SSE4.1.

My retro 99' rig.
Celeron 533A@600
2x256 MB SDRAM/133
PC-Chips M726MRT
GeForce2 MX

I've been running SuperPi on, like, everything, but especially a bunch of thin clients & USFF PCs, so may as well contribute them to this thread.

First up:

ComputerLab International ST5500X 99K thin client
Via Eden (Esther) 1GHz (5 x 200MHz)
1GB PC2-5300 (single channel @ 266 4-4-4-12-2T)
Win2K Advance Server SP4

1M: 465.813 s (7:44.937)
4M: 2201.797 s (36:41.797)

I believe this is the first VIA Eden result here? I couldn't find any others.

System: Termtek TK-3350

VIA C3 (Samuel 2), 533MHz @ 8x66(??)
VIA PLE133 chipset
256MB PC133
Windows 98SE

SuperPi 1M: 1439.929 s (23:59.929)

Full disclosure: I had an unbelievable amount of trouble with this thing. I managed to get Windows just barely installed enough to do a couple benchmarks, but it was completely unstable. I got SuperPi to run once and never again, so this 1M result is all you get. Not sure how representative it is of the optimal performance of this CPU. Even running CPU-Z would bring the whole thing down so I was never able to see the memory timings or detailed system info.

For comparison, this machine got 211 MIPS in 7zip, compared to 359 for my K6-2/500 and 499 for the 1GHz VIA Eden above.

Eventually the whole thing just stopped being able to boot after I tried to install the same old USB supplement I've used on every Win98 machine I've ever built. I ended up completely ripping out the jury-rigged HDD I was using, put JoJo's PC-DOS Mini image on a bootable USB stick, and that was the end of it. So apologies for no screenshots & no more benchmarks from this machine.

I have a question about Multicore SuperPi. I ran it on a P4 Northwood 3.06 Ghz cpu and set it to 32 with two threads for the hyperthreading . It finished at 72 seconds. Then ran it with one thread and got 111 seconds. This seems normal to me., but then I wanted to compare my P4 Prescot 3.2 Ghz. with hyperthreading and got the same as the Northwoods time of 72 seconds with 2 threads. What confuses me is I did it again with one thread and it was finished at 52 seconds? Why would it be faster with one thread? I thought the HT would boost it a bit like it did with the Northwood CPU.

The Prescott system is the newer model with 2 gigs cache, and it currently is running with one RAM stick of 1 gig, and the Northwood had 2 sticks of 512 megs each being dual channel. May be the longer pipeline of the Prescott is not liking the single channel RAM when using 2 threads?

Hope I wrote this clear enough to make sense, I worked all night and I smoked a fatty. Hope someone can shead some light on the subject, thanks in advance.

Tommaso