• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

SuperPI Contest!!!

Page 10 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.
After a few mhz increase on the FSB and some tweaking to my timings its looks like I'll be taking the #1 Intel spot.

P4 3.2E @4079mhz = 26min 00sec!!!!!
......................................................................


P4 3.2E Prescott D0 Stepping @ 4079Mhz
Asus P4C800-E Deluxe Bios 1019 / Vdimm & Vcore Mods
OCZ PC4000 Gold EL DDR500 - 2x512MB Dual Channel @ 3.2v
Koolance Exos-Al External Water Cooling Setup w/CPU(41C Load), GPU(71C Load) & Northbridge Waterblocks
eVGA Geforce 6800GT 416Mhz/1.12Ghz
Creative Sound Blaster Audigy LS
Altec Lansing 5.1 Speakers
Maxtor 80GB Serial-ATA 7200RPM
Western Digital 160GB Serial-ATA 7200RPM
TDK 440N DVD+-RW
Plextor Premium 52x32x52
Antec TrueBlue 480watt PSU
Chieftec Tower Case w/ 4-80mm Intake & 2-80mm Exhaust
 
Here's my P4 540 at 28m 29s. The damn SuperPI window wasn't big enough so when it finished it chopped off half of the end result and you can't make it bigger without clicking the OK button. But you can tell its legit cos there is like 1min difference between loop 23 and 24.

Using patched SuperPI version and just plain air cooling as per sig. 😎
 
Originally posted by: Azsen
Here's my P4 540 at 28m 29s. The damn SuperPI window wasn't big enough so when it finished it chopped off half of the end result and you can't make it bigger without clicking the OK button. But you can tell its legit cos there is like 1min difference between loop 23 and 24.

Using patched SuperPI version and just plain air cooling as per sig. 😎

you need to extended the superpi window before running
open super pi, extend window and then run


by the way zakee00 can you include the P4s original clocks again ? its nicer IMO


Thanks
Dan
 
Originally posted by: Sc4freak
It utilises SSE3 instructions, I think. Which only the Prescotts currently have.

Anyway, looks like I was beaten by 6 seconds. Time to take back my position:

Picture, Patched Version

404, bad link

BTW.... "hacking" superpi isnt hard at all, its not a "cheat"....all you need to do is change the values in the text file.
thats why i dont take screenies of the main Pi screen.
 
Originally posted by: zakee00


INTEL SYSTEMS
1. Deachus- 26m 0s P4@ 4GHz (Patched)
2. Sc4freak- 26m 06s P4@ 4.02GHz (Patched)
3. Slulfyer06- 27m 0s P4@ 3.96GHz
4. Stardust- 27m 59s P4@ 3.95GHz
5. Stevty2889- 29m 18s P4@ 3.8GHz


Zakee, unless they show both patched and unpatched times at same Mhz You must assume all are patched. Why? Those times don't jive. All looked patched. A 4.0 Presshot should be right around 28... Also can A64's run patched version? http://xtremesystems.org/forums/attachment.php?attachmentid=23762

I think you should either include all or dis the patched.

Over at HARD they dis the patch.. For example Sc4freak is running - 27m 36s - P4 3.4E @ 4.10GHz over there.

http://www.hardforum.com/showthread.php?t=840858&page=1&pp=20
 
If a CPU can do SSE3 instructions why limit it to only doing SSE2 instructions. You paid for it to do SSE3, I don't see why you should be forced to use SSE2 just for superPi. It's a valid feature of the chip, and it's just as legit as having 1MB cache rather than 512KB.
 
Originally posted by: Azsen
If a CPU can do SSE3 instructions why limit it to only doing SSE2 instructions. You paid for it to do SSE3, I don't see why you should be forced to use SSE2 just for superPi. It's a valid feature of the chip, and it's just as legit as having 1MB cache rather than 512KB.

superpi is an old app, its not coded for sse2/3. the patches enable it.
 
Originally posted by: zakee00
Originally posted by: Azsen
If a CPU can do SSE3 instructions why limit it to only doing SSE2 instructions. You paid for it to do SSE3, I don't see why you should be forced to use SSE2 just for superPi. It's a valid feature of the chip, and it's just as legit as having 1MB cache rather than 512KB.

superpi is an old app, its not coded for sse2/3. the patches enable it.

Ahh right, my bad. Still I think if the CPU can do it, you shouldn't be disadvantaged by disallowing the patched overclock results.
 
Originally posted by: Azsen
If a CPU can do SSE3 instructions why limit it to only doing SSE2 instructions. You paid for it to do SSE3, I don't see why you should be forced to use SSE2 just for superPi. It's a valid feature of the chip, and it's just as legit as having 1MB cache rather than 512KB.

Apples to oranges... why run a different code path for same app? When they do video card tests they don't force the OpenGL path to make nV look good. We now have three different apps here with superpi. Maybe one is coded better too? Like the "new" ones?

If all it does is take advantage of sse3 and 2 it's not a problem, but do you know that's all it does, internally speaking?
 
Originally posted by: zakee00
Originally posted by: Sc4freak
It utilises SSE3 instructions, I think. Which only the Prescotts currently have.

Anyway, looks like I was beaten by 6 seconds. Time to take back my position:

Picture, Patched Version

404, bad link

BTW.... "hacking" superpi isnt hard at all, its not a "cheat"....all you need to do is change the values in the text file.
thats why i dont take screenies of the main Pi screen.

Fixed the link.
 
Originally posted by: Shenkoa
Athlon XP 2700+ Tbred
512 MB Corsair PC 3200
80 GB WD800JB

44 Minutes and 52 seconds. Crap I know!

Looks like I have some competition here... that's basically my specs except I use XMS... (*goes to download SuperPI*)
 
Back
Top