AMD Won't Endorse SYSmark 2012 Benchmark

Status
Not open for further replies.

erhardm

Distinguished
Oct 19, 2010
16
0
18,520
[citation][nom]fleeb[/nom]AMD, nVidia, and VIA already left BAPCo. What does that say?[/citation]
Intel CPUs will be the world's champions from now on:)
 
We are committed to working with like minded companies that want to give consumers and business users an accurate, honest measure of what they can expect from their PCs and mobile devices,"

Yes thats all very noble but the point is if AMD are involved then Nvidia people will start shouting biased.
We already have the info needed to make an informed decision its out there on this and various other sites. Common sense says you look across a selection of sites to get a clearer more accurate picture. Some sites are after all leaning one way or the other.
Mactronix
 

mkrijt

Distinguished
Oct 28, 2009
79
0
18,630
I found some interesting read over here. Ok, It's old but I think it does cover the problems with SYSmark...

In fact, Fog points out that even benchmarking programs are affected by this, up to a point where benchmark results can differ greatly depending on how a processor identifies itself. Ars found out that by changing the CPUID of a VIA Nano processor to AuthenticAMD you could increase performance in PCMark 2005's memory subsystem test by 10% - changing it to GenuineIntel yields a 47.4% performance improvement!
 

KT_WASP

Distinguished
Apr 16, 2008
125
0
18,690
SYSmark should have been abandoned years ago by the companies that are leaving it now (its basically an Intel marketing tool anyway). What I hate is that tech/review sites still use it, even though they know how skewed it is towards Intel.

SYSmark = synthetic benchmark that falsely gives Intel the edge every time. Intel controls it and no input/suggestions are ever implemented from the other companies that finally said "enough".
Why no mention of Nvidia and VIA leaving at the same time as AMD? It was a mass exodus leaving only Intel. The deal is, these companies are finally fed up and are dropping this sham of a benchmark.

 
Yep, the big benchmarking companies have been in bed with the highest payer (usually Intel) for years now. Usually it takes the form of checking CPUID and using that to determine code path and optimizations. You then make the code for your preferred CPU more "efficient" and leave everyone else on a non-optimized path. This isn't only in benchmarking but also in software development. Lets say publisher A is making a game, and decides to "work with" Intel to "get the most" out of their code. Intel provides a SDK with a compiler they say will help optimize their code. The compiler does indeed optimize the code, but only for Intel branded systems, and further the compiler may intentionally compile the program so that it runs a very inefficient non-optimized path if it detects its running on a "non-Intel" system. After all Intel can claim they only support their own products and have no requirement to support competitors products.

This is why I take ~all~ "benchmarks" with a grain of salt. Different code paths can swing performance 10~40% depending.
 
[citation][nom]crisan_tiberiu[/nom]Still, where is Bulldozer? i have expected it on 20.06 ^^. I went i7 2600k on month ago, could not wait anymore[/citation]

sometime between next month to late September area is all the info i got. Although this info been out for a little while.
 

goodguy713

Distinguished
Oct 23, 2009
1,177
0
19,460
yea this is pretty interesting although its common knoledge that those bechmarks are rigged .. it would be interesting to see how well some of the current gen amd processors really fair with un-biased benchmarks. not that i think they would surprise a lot but it would still be interesting .. i mean in the end i guess if you can play pretty much any game at 60fps or shrink and convert a dvd in 5-6 mins then you have a pretty fast system but both of those are either pretty gpu intensive or hard drive intensive better off with a raid or dual gpu set up. lol
 

ta152h

Distinguished
Apr 1, 2009
1,207
2
19,285
In short, Bulldozer isn't competitive with Sandy Bridge on this benchmark (of course not, since it's design favors a different type of workload), so let's cry about it because they didn't change it for the Bulldozer type of workload where those two integers "cores" can show their advantage.
 
[citation][nom]mactronix[/nom]We already have the info needed to make an informed decision its out there on this and various other sites. Common sense says you look across a selection of sites to get a clearer more accurate picture.[/citation]Correct.
Thankfully we're not limited to just the AMD or Intel marketing hype (or any other MFGR for that matter). We have many good independent review sites that test and report what they find.
 
G

Guest

Guest
http://www.phoronix-test-suite.com/
http://openbenchmarking.org/
 

demonhorde665

Distinguished
Jul 13, 2008
1,492
0
19,280
Maybe it's jsut me but i think sysmark arnt teh only "intel-optimized" bench marking tools , i see this same pattern with futuremark and 3d mark for graphics , it always reads intel cpu as better regradless of the model (unless it is jsut a model taht is that much oplder than the amd model you test with. also whehn testing itnergarted graphic chips it will quite oddly favor , intel over invida and nivdia over ati NOW HOW CRAZY THAT !.

for this reason i gave up longa gout even bothering to read synthetic bench marks and i only look at the real world test , and in all hoensty i think tom's should DROP synthetic test
 

Marco925

Distinguished
Aug 11, 2008
967
0
18,990
[citation][nom]erhardm[/nom]Intel CPUs will be the world's champions from now on[/citation]
And all my friends said i was the best too!!! :D
 

Jax69

Distinguished
Feb 7, 2007
22
0
18,510
Intel will compete with itself from now on and the irony will be if will lose against itself...
 

f-14

Distinguished
[citation][nom]mkrijt[/nom]I found some interesting read over here. Ok, It's old but I think it does cover the problems with SYSmark...[/citation]
Quote :
In fact, Fog points out that even benchmarking programs are affected by this, up to a point where benchmark results can differ greatly depending on how a processor identifies itself. Ars found out that by changing the CPUID of a VIA Nano processor to AuthenticAMD you could increase performance in PCMark 2005's memory subsystem test by 10% - changing it to GenuineIntel yields a 47.4% performance improvement!

where was this found and link please.
from the sounds of it the results are pre-programmed based on CPUid or would this be pre-programmed overclocking results?
point is the same result should be nearly identical every time (temp variance permitted) no matter what CPUid is used for the same processor.
this needs more investigating and i would almost like to see tom's do a benchmark with a single via, amd, intel cpu and change the CPUid's on each one of them for the results.
any chance of this Chris?
 

upgrade_1977

Distinguished
May 5, 2011
665
0
18,990
Shouldn't test performance with synthetic benchmarks anyways. Each cpu or Gpu has there own advantages, so if you are gonna buy 1000 gpu's for a super computer then they should test it on a smaller scale with similar programs. Even if you are running an intel which is superior in most aspects, there are still applications which Amd will smoke them in, same for Amd and Nvidia. Most people who buy these processors or gpu's in bulk "should" know that.
 
Status
Not open for further replies.