backtop


Print 88 comment(s) - last by testerguy.. on Mar 15 at 10:46 AM

Benchmarks or GTFO!

Yesterday when Apple unveiled the new iPad, the crew from Cupertino took some time to brag about its new A5X processor in comparison to NVIDIA’s Tegra 3. Apple certainly isn't widely known for offering up benchmarks on its own, so we'll likely have to wait until iPads land in the hands of reviewers and geeks around the web.
 
Apple used the iPad unveiling to boast that the A5X chip inside the new iPad is two times faster than A5, and four times more powerful in graphics performance than the Tegra 3.
 
 
NVIDIA isn't buying those claims without proof. The graphics company wants to know how Apple came by that number. Ken Brown, a spokesman for NVIDIA, stated, "[It was] certainly flattering " for Apple to compare its newest chip to their part.
 
Brown continued, “We don’t have the benchmark information. We have to understand what the application was that was used. Was it one or a variety of applications? What drivers were used? There are so many issues to get into with benchmark.”
 
Anyone that follows tech knows benchmarks are often handpicked to favor one particular brand over another when it comes to claims such as these. So it should be interesting to see if the new iPad’s performance lives up to the claims.

Source: ZDNet



Comments     Threshold


This article is over a month old, voting and posting comments is disabled

RE: Apple Picked the Wrong @!**@fight
By Guspaz on 3/8/2012 12:52:22 PM , Rating: 1
nVidia's mobile GPUs have always been the primary weakness of their SoCs. The Tegra 3 was an improvement, but it's still substantially slower than the PowerVR SGX543MP2 featured in the iPad 2. The PowerVR SGX543MP4 in the new iPad has double the theoretical performance. Claiming 4x Tegra 3 is a slight exaggeration since that doesn't hold true in all benchmarks, but it's not much of an exaggeration, because a bunch of the benchmarks do show it.

Since the MP2 was faster in every benchmark, though, there is no doubt that the A5X has more than double the GPU performance of the Tegra 3.


RE: Apple Picked the Wrong @!**@fight
By Cheesew1z69 on 3/8/2012 1:18:01 PM , Rating: 1
quote:
bunch of the benchmarks do show it.
Really? Show these benchmarks for the new ipad...because as far as everyone is aware, there are none. Yet.


RE: Apple Picked the Wrong @!**@fight
By Guspaz on 3/8/2012 1:17:51 PM , Rating: 1
Clearly you didn't bother to actually read the post you're replying to. There are plenty of benchmarks comparing the SGX543MP2 to the Tegra 3, and the new iPad's SGX543MP4 has exactly double the theoretical performance. We can make some reasonable guesses by extrapolating, enough to say that Apple's claim isn't completely outrageous, just slightly exaggerated.


RE: Apple Picked the Wrong @!**@fight
By Cheesew1z69 on 3/8/2012 1:32:37 PM , Rating: 2
Clearly, you didn't bother reading either, there are NO benchmarks so you have NO clue what the actual performance is...


RE: Apple Picked the Wrong @!**@fight
By Guspaz on 3/8/2012 1:37:05 PM , Rating: 1
Again, there are benchmarks for the SGX543MP2, and the SGX543MP4 has double the execution units. We can make some educated guesses, we're not flying completely blind here.


RE: Apple Picked the Wrong @!**@fight
By Cheesew1z69 on 3/8/2012 1:48:23 PM , Rating: 1
Again, there are no benchmarks for the new device.....


By Guspaz on 3/8/2012 2:01:47 PM , Rating: 1
And yet we know the theoretical performance of the components, which allows us to make some estimations, and those estimations indicate that Apple's claim is exaggerated but not enormously so.


By RyuDeshi on 3/8/2012 2:12:52 PM , Rating: 2
A quick google search found plenty of benchmarks comparing the Tegra 3 to the SGX543MP2.

You do realize the SGX543MP2 and the SGX543MP4 are very similar, the SGX543MP4 just has twice as many cores. That is how they can derive those theoretical performance claims.


RE: Apple Picked the Wrong @!**@fight
By nafhan on 3/8/2012 4:13:25 PM , Rating: 2
A little common sense says to me, that the likely situation we have here is:
a) There's at least one benchmark where A5X's GPU really is 4X faster
b) Real world performance is probably not 4X faster in very many/any situations

Basically, they're probably telling the truth in a misleading way - as is standard practice in this kind of setting. We'll find out the real performance next week.


RE: Apple Picked the Wrong @!**@fight
By omnicronx on 3/8/2012 4:24:08 PM , Rating: 2
c)This is theoretical performance.

In terms of raw performance they probably are not being that misleading.

What is misleading is this is going to make users think that everything that relies on the GPU will perform 2x faster which probably won't be the case.

Then again, I can't think of ANY company that would not have sugar coated it in this way..

'We had to beef up the GPU to give you this new fancy display' just does not have the same ring to it ;)


By nafhan on 3/9/2012 10:08:23 AM , Rating: 2
A and C are usually the same. Unless they're absolutely lying about the "theoretical" performance, a hand picked benchmark is probably going to be very close to max theoretical performance.

This is why a lot of people hate benchmarks, and it's why if you DO look at benchmarks, you need to understand how it relates to what you plan to do with the device in question.


RE: Apple Picked the Wrong @!**@fight
By omnicronx on 3/8/2012 3:27:57 PM , Rating: 5
Double the theoretical performance, yet 4x more pixels to push.

In practice the iPad 3's probably won't be faster than the iPad 2, unless they are running at the same resolution. This especially holds true for games. (They could scale games from 1024x768, but that kind of defeats the purpose of having a Retina display)

Its an incremental update for the GPU, one which was required to support the Retina display.

You can't merely compare a GPU head on without taking some pretty obvious variables into account. Yes the iPad 3's GPU is much faster than its predecessor, but this performance increase will most likely not be realized by its users in most situations if at all... (i.e it certainly has the raw performance crown and by a fair margin, but its not like you are going to see FPS rates double in practice)


By testerguy on 3/9/2012 8:27:19 AM , Rating: 4
I agree with your comment, but the GPU claims made by Apple which are the topic of this article are resolution independent, and would not be disproved even if real life FPS was lower.

Real performance of the devices in question would be a different benchmark, and that would open up a whole host of questions like 'is a device which can hit 100 FPS at a resolution of 10 x 10 better than one which hits 60 at 2000 x 1000?'. In other words, FPS is just as much a flawed benchmark.

I suspect that developers can, if they want, develop games for the lower resolution of the iPad 2 and they will run at 2x the speed on the new iPad as they would on an iPad 2 (and just be upscaled - without extra processing). This would mean a non-retina game but means there is the option there to choose performance over resolution. A choice the slower GPU's in Android tablets don't afford.


“And I don't know why [Apple is] acting like it’s superior. I don't even get it. What are they trying to say?” -- Bill Gates on the Mac ads














botimage
Copyright 2014 DailyTech LLC. - RSS Feed | Advertise | About Us | Ethics | FAQ | Terms, Conditions & Privacy Information | Kristopher Kubicki