Surreptitious Samsung Benchmark Shenanigans

[SiliconWars]

The only reason Nvidia weren't caught cheating is you can't find Tegra 4 in any devices worth mentioning.

 

[Idontcare]

The only reason Nvidia weren't caught cheating is you can't find Tegra 4 in any devices worth mentioning.

touché

 

[Exophase]

I don't think Tegra 4 will run all CPUs at 1.9GHz under any circumstances for any duration of time whatsoever, even in Shield. So if that's what you're looking for you won't see it. nVidia has always defined different max clock speeds depending on how many CPU cores are active.

 

[SlimFan]

So, nVidia is the only honest OEM/device maker who is not cheating. :hmm:

/Oh and Google...

Samsung + Qualcomm appear to be on the same page about cheating.

You said "nVidia doesn't do it on Tegra!" ... and then found out pretty much everyone else is doing it.

So, yes, your original post was "non responsive."

 

[SlimFan]

The only reason Nvidia weren't caught cheating is you can't find Tegra 4 in any devices worth mentioning.

Brilliant.

 

[Arachnotronic]

The only reason Nvidia weren't caught cheating is you can't find Tegra 4 in any devices worth mentioning.

LOL!

 

[jvroig]

The only reason Nvidia weren't caught cheating is you can't find Tegra 4 in any devices worth mentioning.

Yeah, I guess that's pretty much true.

I just finished reading it, but a similar sentiment actually was expressed by Anand in the comments of the latest Android-cheating article:

"With the exception of Apple and Motorola, literally every single OEM we’ve worked with ships (or has shipped) at least one device that runs this silly CPU optimization."
- Quote from the article

Technically, they should have included NVIDIA too according too their own chart as one of the non-cheaters... but then again, they barely make a blip on the map right now.

I didn't because I didn't go back and test the older Tegra 3 devices, but as you point out there's not a ton of Tegra 4 stuff out right now.

Link

 

[ShintaiDK]

Crazy to see that cheating is the norm. I would like to see Apple tested too.

 

[Nothingness]

I don't think Tegra 4 will run all CPUs at 1.9GHz under any circumstances for any duration of time whatsoever, even in Shield. So if that's what you're looking for you won't see it. nVidia has always defined different max clock speeds depending on how many CPU cores are active.

I would have thought the same, but in many sub-tests of GB3 the MT vs ST speedup reaches 4, though not in all (but other factors would obviously prevent perfect speedup).

 

[Gideon]

Crazy to see that cheating is the norm. I would like to see Apple tested too.

It seems they have done it already. From the Anand article:
http://anandtech.com/show/7384/state-of-cheating-in-android-benchmarks

We started piecing this data together back in July, and even had conversations with both silicon vendors and OEMs about getting it to stop. With the exception of Apple and Motorola, literally every single OEM we’ve worked with ships (or has shipped) at least one device that runs this silly CPU optimization.

I have to admit, A7 looks even better in that regard. It deserves quite some credit, considering its performance is at Bay Trail level CPU vise (much better GPU vise) and is built at a process disadvantage and out a quarter sooner.

Would have never thought i'd have to praise Apple for microarchitecture design :S

 

[jvroig]

I would like to see Apple tested too.

2nd comment in the article, from Anand:

Apple doesn't do any of the frequency gaming stuff, no.

Link.

And then on page 4 of the comments, Anand had this to say:

We have some internal tools to poke around at frequency, A7 appears to behave honestly. I explored this issue with engineers at a couple of different companies who were also interested in finding out the answer. Finally, much of what I used to characterize the A6/A7 aren't publicly available, so there's no gaming there.

Link