BAPCo Bites Back at AMD's Departure

Didnt even know such a program (SYSmark 2012 oe 2011 or whatever) existed .

Wont know either now, i dont have an Intel cpu .

blah blah blah it's funny how they just talk about other bs and not actually respond to whether their software is biased. with the muscle intel has, is it really any surprise that amd always gets the sh1t end of the stick

PassMark 'CPU Marks' sucks worse that BAPCo 'Sysmarks' It's a synthetic test race to the bottom between those two.

And for those with a little spare cash laying around, you can buy your way into BAPCo for 20-large.

This all rings hollow, especially since independent third parties have proven that the software is biased. What we have here, is, a poor attempt at damage control.

Move along, nothing to see here.....Just like their benchmarking software.

Slap...from a slap.

Seems like AMD has been getting crap we are not getting to understand. If so, i wouldn't doubt the Intel Cousin would leave because of its bigger cousin...Intel.

Well now I'd like Tom's to run a test of BAPCo (stupid name, btw.) benchmarks. Tom's Hardware, like myself, is sympathetic to the underdog AMD, so it might not be best to risk hurting AMD if the benchmark makes them look bad while being accurate.

The only way I really see Sysmark 2012 being biased is if the home user workloads use more than one or two threads since very few typical user applications are multi-threaded. Other than that, the benchmarks should be faster on whatever CPU is faster.

I'm pretty sure 3dsmax and AutoCAD are faster on current non-AMD CPUs. We are talking about Intel, right?

I got a good laugh at this...

Source: http://www.crn.com/news/applicatio [...] e-quit.htm

Seems BAPco is simply trying to "pull the wool over our eyes" so to speak.... It was also found by other sites, that by changing the CPUID, you could effectively alter the benchmark results. If that is actually true, it would seem that BAPco is trying to work as a marketing team for Intel.

BAPCo should be renamed BarkCo!

The howls of a lost dog. AMD was right in departing.

Hmmm - no comment by BAPCo that Nvidia & VIA also just quit BAPCo at the same time for the same reasons

... but many use irrelevant synthetic benchmarks or don't use benchmarks that show the power of GPGPU... sometimes i see tests for a system like mine and wonder, where come the low results from... my system behave much faster... in a real world applications... but that is, because i use a GPU too for some heavy operations... it's much faster...

Software in general is optimized for Intel cpu's bc THEY HAVE GREATER MARKET SHARE and quite simply a larger percentage of software developers' end users are going to see better performance by doing this. That's just the way it is.

I fully support AMD's position on the bogus BAPCo bench and will not use this bench in consideration for any future purchases as it is unreliable and disengenuous.

I am surprised soo many of you are backing AMD. They are soooo far behind Intel that they are trying to discredit a benchmark that shows this. Seeing as Adobe Creative Suite is part of this benchmark, AMD probably fought extremely hard to get rid of it because they don't have the newer SSE extensions; thus, Intel walks all over them (in Premiere Pro CS5). Just search PPBM5 and see how badly AMD does in rendering and encoding tests.

The problem, as I understand it, is that supposedly everything is compiled for Intel chips and gives Intel an artificial advantage. Thus, apparently, every benchmark site that gives an Intel chip a better review or shows higher performance is a part of a greater conspiracy. Also apparently the sky is blue due to NASA sending too many blueberries and Smurfs into space. Same difference -- next time use chipmunks.

I'd be just as doubtful if Intel claimed the same about AMD.

http://www.osnews.com/story/22683/ [...] _Compiler_

That is the inherent problem with Sysmark 2007, whether they continued the "dual thread only" for 2012 would explain why AMD would leave. you don't make a cpu only to have benchmark software test 1/4 of the power that is available.

Seriously tho, how much faster can microsoft office load.

Person A .. wow this doctument loaded in 1/2 a second.
Person B ... haha mine only took 1/4 second.

Here is another interesting fact on how disappointing Sysmark 2012 is.

What this tells me is that Sysmark (updated every 5 or so years) will only be up to date on current software .... never.

The thing is, I'm curious about the timing. Bulldozer does indeed have the broadest support for extensions out of any AMD and Intel CPU and would indeed sufficiently outperform previous AMD offerings. Is this anything like the compiler furore we had over the past years where all CPUs are equal but some are more equal than others...?

I'm afraid I know very little on this subject so I'd like to know which tests performed particularly badly on AMD hardware. I do believe, however, that - going back to the subject of compilers - Intel were ordered to remove the code that purposefully hijacks performance on non-Intel CPUs.

So Tom's, when you guys going to release an article about whether or not Sysmark is bias?

AMD is leaving because it can't keep up with intel....they should really just start making video cards

Yeah ... particularly when their latest cpu's fr low power devices cream Intel ... good time to leave?

I don't think so.

Might be a good time to leave for NVidia in the IGP space as they have nothing to offer now with the low end 5 and 6 series ATI GPU integrated on die for the Brazos and Llanos CPU's ... and at the muckier end even the Intel ondie GPU ... whatever its called on the i3's and anon.

AMD is whining because their new products emphasize a new type of processing that these benchmarks, in their opinion, do not adequate use.

You'll get the fools here crying about Intel rigging the game, because they are poor and can't afford Intel and want to cry "conspiracy". The reality is probably very different, although AMD does have something of a point.

Intel had destroyed AMD in performance based on "conventional" workloads. BAPco reflects that. Bulldozer is not going to change anything there. AMD changed the way their processors work, by including two integer units, and emphasizing the GPU in processing. They need benchmarks to use software that will emphasize these advantages, or they will keep losing miserably.

Put another way, if you're using apps that don't use the extra integer unit on the Bulldozer, or the GPU, AMD processors are going to continue to be embarrassed for a long, long time. AMD needs a shift to take advantage of their newest, non-traditional resources, and BAPco obviously was not willing to do it.

You can't blame AMD for wanting this, except BD is not even out, and their Fusion is just out. My guess is that BAPco didn't show any desire to move their in the near future either, leaving AMD the choice of looking lousy in a benchmark they are part of, or having them look lousy in a benchmark they aren't part of.

You can bet your last dollar Intel had a hand in this to make AMD score bad on the test to make their product look that much better. Intel has a history of shady business practices aimed at downing AMD, even if that includes illegal sales incentives and patent violations. Same old same old.

Is anyone who is in the know going to pay any attention to what BAPco is saying on this matter?

BAPco has had its 15-mins of fame. Time for them to face up to the fact that their benchmark is an Intel marketing tool.

I agree with AMD'S decision to leave. Since the benchmark only comes out about every 5 years it should include software that will test the most updated scenarios such as GPU processing which is where processing is headed.

woops forgot Office that is tested as 2010, where the new Office 11 also supports the use of the GPU to lighten the workload for the CPU.

If nothing else all these examples show how out of date a benchmark not giving the GPU any value is today and I almost don\t dare to think how many of the programs on the list at http://www.bapco.com/products/sysm [...] ations.php will also have been switched with GPU accelerated versions in the year this bnchmark is supposed to represent by its name.

A clear fail, most likely due to BAPCo still favoring to Intel who would loose greatly if GPU friendly languages like OpenCL entered the picture. .

Somehow my previous message never posted...
I only pointed out that in the most used parts of the everyday experience, surfing the net, the software chosen somehow always was the last version before the software got GPU acceleration.

They choose IE8, where IE9 uses the GPU
and Firefox 3.6.8, where 3.7 was renamed Firefox 4 and use the GPU
finally they decided to go with Adobe Flash 10.1, where all later versions have GPU acceleration.

If AMD SYSmark is unfair for AMD’s processors then I agree with its decision in leaving the consortium .

Stop whining AMD and stop releasing junk.

Seeing a recent benchmark of AMD and intel CPUs was the most hilarious thing I've read in a long time. APUs are junk.

@otacon72

Given the right conditions a car could appear to be faster then an airplane (accelerating over 100m), must make you feel proud to believe your car is faster then an airplane.....

ps i think you missed the article about cracking an encrypted file with GPU assistance, junk indeed