A flashy commercial tells you that a new gadget is the fastest that’s ever been created. It boggles the mind, how fast that thing is. And look, the company has boatloads of benchmark data to prove it!
It turns out, that data is almost always bullshit.
Recent research into the computer processor speed claims of top smartphones shows that most major gadget makers have been gaming standard benchmark tests. In the simplest of terms: they are cheating and the devices are not as fast as they say they are.
Research by technology publications Ars Technica and AnandTech have shown that almost all major smartphone manufacturers have ways to make their smartphones look faster than they really are. Samsung, HTC, ASUS, LG, NVIDIA have all employed a technique in their devices that will register the presence of a benchmarking app and then dial up the device to maximum output to trick the test into thinking the device is faster than it would normally be. Of the tests done by AnandTech, only Apple and Google-owned Motorola do not try to game most popular benchmarking apps.
Ars Technica reported earlier this week that Samsung’s Galaxy Note 3 was purposely tricking a benchmark app. The way Ars figured out Samsung’s trick was to take a popular benchmark test (called Geekbench 3) and monitor how it activated all four cores of Qualcomm Snapdragon 800 2.3 GHz processor when Geekbench 3 was running.
Ars Technica also found that Samsung employed this technique with the processors (both its Exynos processor in overseas phones and the Snapdragon processor in the United States) with the flagship Galaxy S4 smartphone. Ars Technica was able to strip away the code of the Note 3 to find lines of Java in the device’s operating system that told it when to activate all four cores in the presence of benchmarking apps.
AnandTech found that just about everybody else performs these types of tricks to make their smartphones and tablets seem faster. Authors Anand Lal Shimpi and Brian Klug note that chipmakers Intel and Qualcomm are likely against such optimization testing tricks and note that the decision to implement these benchmark cheats likely come from the manufacturers.
The hilarious part of all of this is we’re still talking about small gains in performance. The impact on our CPU tests is 0 - 5%, and somewhere south of 10% on our GPU benchmarks as far as we can tell. I can't stress enough that it would be far less painful for the OEMs to just stop this nonsense and instead demand better performance/power efficiency from their silicon vendors. Whether the OEMs choose to change or not however, we’ve seen how this story ends. We’re very much in the mid-1990s PC era in terms of mobile benchmarks.
Speeds & Feeds Blur The Storyline
The benchmark antics by smartphone manufacturers accomplishes very little except to make them look petty and fraudulent. As Shimpi notes, most of the speed improvements are minimal and getting caught only gives the companies negative press and consumer reactions.
Claiming the “fastest” smartphone right now is high up on the list of marketing gimmicks that manufacturers employ. Samsung is generally the king of this type of practice, adding features that are trivial or hardly work that it can place in its commercials to show just how advanced it is. Power plus functionality and a coolness factor? That’s how computers (even pocket-sized smartphone computers) are sold.
Speeds, feeds and specs are an important part of the tale for today’s smartphones. It is quite amazing to look at what type of hardware was running in smartphones in 2007 (including the original iPhone) and what is running now. RAM capability and CPU speeds are three to four times more robust than they were six years ago. Smartphones are now powerful, Internet-connected devices that we can take anywhere and through a variety of apps, do almost anything. The key is that users can experience much more with their devices than ever before.
Why Apple Wins: It Sells Experience Informed By Hardware, Not Defined By It
Apple understands this better than most companies. When it sells iPhones, it doesn’t say that it is faster than the competitor. It shows that you can connect with your friends, play great games and take pictures that record the moments of your life. The key for Apple is experience. Hence it is little surprise that Apple doesn’t play the same benchmarking games as HTC, Samsung and LG. It would be a surprise if Apple even considered it. Apple has its tricks to sell phones (Siri, TouchID), but basing its marketing on speeds and feeds is not one of them.
Google and Motorola have their own gimmicks (Moto X “assembled” in the USA, “OK Google Now…”) but the smartphone manufacturer and its paternal overlord have also realized that reliability and device experience are more effective ways to sell their new phones.
Yet, companies like Samsung and Microsoft (with their new Surface tablets) still don’t get it. It is better to tout the software, the ecosystem, the operating system to engender loyalty to the experience… not lie to consumers about how fast your phone may or may not be. Hardware informs that experience, but shouldn't be the story.