AMD Won't Endorse SYSmark 2012 Benchmark

[bluekoala]

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!

Am I the only one who thinks that Intel should be fined in the tens of billions for this?

If I was king of the world, this kind of crap would not go unpunished. I would make Intel pay a ridiculous sum and split it in 3. State, GCC and affected competitors(divided in volume).

I bet you Intel can't wait to sell you celeron grade chips for the price of a SB i5.

 

[twist3d1080]

@F-14
You can find an article here that uses Agner Fog's paper as a source:

http://www.osnews.com/story/22683/Intel_Forced_to_Remove_quot_Cripple_AMD_quot_Function_from_Compiler_

You can find his blog detailing some of his findings with the Intel compiler:

http://www.agner.org/optimize/blog/read.php?i=49#49

The question is has Intel followed through with the requirement to remove the block to optimized code paths on non Intel processors. This is something I would love to see from this website too.

 

[twist3d1080]

@F-14
You can find an article here that uses Agner Fog's paper as a source:

http://www.osnews.com/story/22683/Intel_Forced_to_Remove_quot_Cripple_AMD_quot_Function_from_Compiler_

You can find his blog detailing some of his findings with the Intel compiler:

http://www.agner.org/optimize/blog/read.php?i=49#49

The question is has Intel followed through with the requirement to remove the block to optimized code paths on non Intel processors. This is something I would love to see from this website too.

 

[captaincharisma]

i guess AMD is not supporting it because they know Intel dominates most of there CPU's.

 

[master9716]

Its actually Tomshardware , anadtech ,firingsquads and so on fault for keeping on putting sysmark benchmarks up. If all these famouse sites stoped doing it since they know those benchmarks dont mean anything then it wouldnt be an issue.

 

[JimmiG]

No need for benchmarks.. real world performance is what counts, and for that you can use real applications and games.. Stuff that actual people use their computer for in the real world.

 

[dread_cthulhu]

AMD was smart to do this. Why would you shoot yourself in the foot just to look good? AMD's quality over Intel speaks for itself. I've liked the way AMD's done business for a long time now, and Intel just seems sleazy, especially with benchmarks like SYSmark

 

[culgor]

[citation][nom]master9716[/nom]Its actually Tomshardware , anadtech ,firingsquads and so on fault for keeping on putting sysmark benchmarks up. If all these famouse sites stoped doing it since they know those benchmarks dont mean anything then it wouldnt be an issue.[/citation]

Exactly. I always ignore the Sysmark portion of the benchmarks and look at the benchmarks for the applications types I plan to use with the hardware. I couldn't even tell you what scale Sysmark is using these days.

 

[eddieroolz]

I'm more than ready to accept AMD's position. Anyone in the software engineering department knows that the majority of software out there work best with Intel processors, with a lot having to do with Intel-made compilers that these softwares use to compile their code.

Plus regular testing of hardware here at Tom's proves that too. Software like iTunes are obviously skewed towards Intel, it makes me wonder why it's still in the benchmark suite.

 

[beenthere]

I fully support AMD and will refuse to purchase any Intel product as the performance ratings using BAPCo are inaccurate and unreliable. I vote with my wallet.