Faking Benchmarks, The Good Benchmark List, How To Spot Cheats and More...

[burnout]

You mention all these seemingly complicated ways to cheat, when all you need is Photoshop.. seems kinda obvious. In this case, M$ Paint can do this as well...

you didn't get it, hmmm?

the thing is cheating, so that the cpu-z checksum ist correct

[iddqd]

There's also no such thing as ToyHammer.

Or, I could just see what others got on, say P4's and then apply that to an A64... see, I could easily obtain a correct checksum for 4.8GHz, if I wanted to.

[burnout]

and den checksum would say "pentium 4 4800mhz"

[Karnivore]

The point here isn't how to cheat the easiest, or best way, we all know it can be done, we all know its not difficult. Nothing will 100% safe if someone has made the decision to cheat..

[iddqd]

This one time, I had a bug, where Sandra would (for some reason) read my PIII as 10.1GHz. I got astronimical scores, based on that.. just to show how useful Sandra CPU benchmark is..

[jjcom]

I remember when I first found out about these programs...This has been awhile long before I came to XS, but anyway, The program was to clock up my processor so I'm like cool lets try it on the old Pentium 2. Alright...later I found out the program was not ligit, since I had a CPU-Z screen shot of a Pentium 2 at 3ghz getting insane benchmarks. So what I'm saying is that these programs will sometimes be advertised as really overclocking componets

jjcom

[Fewture]

About the pifast bench..

We have seen so many pifast scores now that a second off shows when you compare it to other scores.
I was thinking of making a table with some standard scores to compare results with and see if they are faked or not.

I have my doubts about starting this thread btw... Why let everyone know how it is done? Just my 2 cts..

[CodeRed]

About the pifast bench..

We have seen so many pifast scores now that a second off shows when you compare it to other scores.
I was thinking of making a table with some standard scores to compare results with and see if they are faked or not.

I have my doubts about starting this thread btw... Why let everyone know how it is done? Just my 2 cts..

dunno if this helps or not, but I have a table of scores for the FX chips for each different memory multiplier and aggressive mem timings (A64 tweaker style). These are the fastest times I could achieve with an FX for the given CPU/mem speed:

pifast_estimate.jpg

I also have the excel spreadsheet if you want it

[PMM]

But different boards have differing results

Good example are the ones that are in Shuttle Computers i've had results 2sec quicker
on Nf2 and A64 versions compared to standard boards under Pifast for the same Speed & mem freq on my own hardware.

So results should only hold true for that board in question

For example I've had 48.x sec @2500 on socket 754 you check the tables most
48.x results are around 2600mhz

A generic rule fails to cover all possibility's

[CodeRed]

But different boards have differing results

Good example are the ones that are in Shuttle Computers i've had results 2sec quicker
on Nf2 and A64 versions compared to standard boards under Pifast for the same Speed & mem freq on my own hardware.

So results should only hold true for that board in question

For example I've had 48.x sec @2500 on socket 754 you check the tables most
48.x results are around 2600mhz

A generic rule fails to cover all possibility's

All boards go at the same speed if the exact same timings are used via A64 Tweaker (pifast only not 3dmark).

That table is not a general rule just a lower bound to highly tweaked FX chips. The only way to get faster is to go 2x512 or 4x256 an have interleave enabled.

[eshbach]

is anyone working a on a new pi program yet? i'm going to start one, let me know what kind of features you'd want.

[Kunaak]

a program that runs off internet time, perferably remote connection, like a internet bandwidth test is.

something you don't download, but connect to.

if not like this, then something that runs off a bootable floppy disc.

[jjcom]

some similar to Super Pi, its got the 1m and tests etc. Keep it simple, closed source, maybe a bootable floppy/CD version and a Windows version

jjcom

[eshbach]

ok how about i use a remote time server? you'd have to be connected to the internet, but it would get times from a server that i would keep secret (in the closed-source)?

also uploadable results and a checksum style verification system in a later version?

[Kunaak]

sounds great to me, the idea is to keep the actual benchmark outta peoples hands so they can't cheat on it.

unfortunatly, I just no of no way to make a cheat free, windows based pi program.
they all work in the same basic way, and are vulernerable to the same basic cheats, and when done in small moderation, like only a second or two faster, IE-should be 40 seconds, but they cheat to make it 38 seconds.... then it's impossible to spot.

both super Pi and Pi fast, are extremely easy to cheat on, in literally any degree. a tiny cheat is impossible to spot, which makes it really hard to be excited about records done with these programs anymore for me

[eshbach]

well there will still be a downloaded program (~50k right now) that runs the math locally...

[racoontje]

Remind me, why don't we just use a normalized linux boot cd? It's really stable, you can use a ram disk w/ MD5'ed tarball (the MD5 is downloaded at runtime) and it sends data tor a server somewhere.

[Slickthellama]

you know, CS is having speed hack problems right now but in the opposite direction. People dont slow down windows they speed it up O_O. This makes them move extremely fast and reload very fast, shoot very fast. But cheating in benchmarks? why? It's rediculous. Good post Kunaak.

[bh2k]

ok how about i use a remote time server? you'd have to be connected to the internet, but it would get times from a server that i would keep secret (in the closed-source)?

also uploadable results and a checksum style verification system in a later version?

What would happen if this unknown remote machine were ever to go offline for whatever reason? How would people benchmark then?

[Kunaak]

I am aware of cheats, that will allow you to reverse the speed of windows to super speeds. these cheats are meant to enable online cheating.
unfortunatly, I know of no way to disable, or stop these cheats.

I added a few new things to the list of good and useless programs.

for a PI program, I would highly suggest people look into "Cpu Mathmark"

I found only 1 method to cheat on this program, and it's not an easy one.
it's a fairly good solid program.
the details can be found in my list on the first page of good, or atleast decent programs you can use to verify OC's.

[racoontje]

Well, running programs off of remote shells (I'm assuming you're not going to be a dumbass and run telnet over the internet) will cause it to actually run remotely, not locally. What I would do:

• Make your own Gentoo Linux livecd using Catalyst (poke me if you need someone inaugurated)
• Make sure it has a very recent kernel, preferably with racoontje's closed source patches of joy (I've been replacing lots of low level kernel functions w/ ASM)
• Make sure it has all the modules you need, think ethernet cards
• Run a python script nohup (ie "disable all user intervention until program is done or user pulls power wire :P)

This script would:

• Check the MD5sum of the tarball that's on the CD
• Create a small (<1 MB) RAM disk where the tarball is extracted
• Runs a series of tests

Remember that 1 MB will get you a LOT of tests... ASM people can put a lot of processor torture in a few bytes

[IvanAndreevich]

If the quarz on the motherboard gets modded then how do we detect it?

[masterofpuppets]

Someone needs to write a decent superpi equivalent for unix.

[Kunaak]

NEWS

I am helping to beta test a pi program right now from a author here.
so far...

his work is very encouraging as I have not been able to cheat on it with any method I know of.
neither windows speed cheats.
timer cheats. clock cheats. pause cheats or manual cheats have effected this little program...

it's not perfect.
does have a few little bugs to fix.
but so far, the author has been very very fast about fixing this stuff.

if he were to release it, even in the buggy phase...
It would still be the only PI benchmark I have heard of, that I cannot cheat on I look forward to testing the next build, and will keep any news of the program, listed here, and hopefully in a few days have a version he's willing to release.

it's kinda like Hexus Pifast.
but has 2 versions, one for SSE, and one for SSE2.
nothing mentiond about a SSE3 version of prescotts.
but this is definatly, the best news I know of, for a benchmark, thats cheat free.

[IvanAndreevich]

Kunaak
Excellent. Does it require internet connection?