Month: October 2015

Things are looking good!

on October 29, 2015

It’s been a couple of weeks since we talked about TouchXPRT 2016. I’m happy to say that we have made great progress since then.

The UI is adapting to the different form factors very well. We’ve tested the resizing on phones and on tablets with the screen snapped to half and quarter screen. While a couple of UI elements still need work, we’ve had no problems running the tests. Here’s how TouchXPRT looks on a phone:

We have also greatly simplified installing the application on phones, so we’re no longer concerned about that.

All in all, things are looking good for releasing the community preview soon. However, we’re going to wait until we can test on the Windows 10 Fall Update (Threshold Build 2). That’s supposed to be released on November 2. We’re not expecting any problems with the Fall Update, but it’s always to wise to check.

November can’t come quickly enough!

Eric

Posted in Benchmarking, BenchmarkXPRT, Collaborative benchmark development, Community Preview, TouchXPRT, TouchXPRT 2016, TouchXPRT development process, TouchXPRT release cycle |

More than the sum of its parts

By Eric Hale

on October 22, 2015

There was a recent article in Bloomberg about phone maker ZTE’s increasing market share in the US. The article singled out one phone, the ZTE Maven, which costs about $60 (US).

This phrase jumped out at me: “a processor with capabilities somewhere between the iPhone 5 and 6.” The iPhone 5S could also fit that description. The ZTE Maven uses the ARM Cortex-A53, 64-bit processor running at 1.2 GHz. The Apple iPhone 5s uses the Apple Cyclone-A7 Cortex-A7 Harvard Superscalar processor running at 1.3 GHz.

We decided to put that statement to the test. We ran WebXPRT 2015 on the ZTE Maven and its score was 47. The iPhone 5s scored 100. The Maven was not even close.

As we’ve said before, the performance of a device depends on more than the GHz of its processor. For example, the ZTE Maven uses the Snapdragon 410 SoC, which was aimed at mid-level devices. The iPhone 5s uses the Apple A7, which was intended for higher-end devices. You can find side by side specs here.

Be wary when you see unsupported performance claims. As this example shows, specs can appear comparable even when the actual performance of the devices differs considerably. A good benchmark can provide insights into performance that specs alone can’t.

Eric

Posted in Android, Benchmark metrics, Benchmarking, WebXPRT, WebXPRT 2015 |

We haven’t mentioned this in a while

By Eric Hale

on October 15, 2015

I had a conversation with a community member yesterday who wanted to know whether we would test his device with one of the XPRTs. The short answer is “Absolutely!” The somewhat longer answer follows.

If you send us a device you want us to test, we will do so, with the appropriate set of XPRTs, free of charge. You will know that an impartial, third-party lab has tested your device using the best benchmarking practices. After we share the results with you, you will have three options: (1) to keep the results private, (2) to have us make the results public immediately in the appropriate XPRT results databases, or (3) to delay releasing the results until a future date. Regardless of your choice, we will keep the device so that we can use it as part of our testbed for developing and testing future versions of the XPRTs.

When we add the results to our online databases, we will cite Principled Technologies as the source, indicating that we stand behind the results.

The free testing includes no collateral beyond publishing the results. If you would like to publicize them through a report, an infographic, or any of the other materials PT can provide, just let us know and the appropriate person will contact you to discuss the how much those services would cost.

If you’re interested in getting your device tested for free, contact us at BenchmarkXPRTSupport@principledtechnologies.com.

Eric

Posted in Benchmarking, Benchmarking computing devices, BenchmarkXPRT, BenchmarkXPRT development community, Principled Technologies |

An update on TouchXPRT 2016

By Eric Hale

on October 8, 2015

We’ll be releasing the MobileXPRT 2015 white paper tomorrow. It contains lots of information about MobileXPRT 2015 that you won’t find anywhere else. We hope you’ll find it very informative.

A couple of weeks ago, we released the design document for TouchXPRT 2016 (login required). This week, we put the first build of TouchXPRT 2016 into testing. It’s a Universal Windows app that runs on Windows 10 tablets, PCs, and phones. This means that TouchXPRT can now run on a wider variety of devices. However, it also means that TouchXPRT 2016 will not be backward compatible with Windows 8 and 8.1.

Given the current state of the SDKs, installing the test builds on phones is more complicated than we would like. We’re looking into ways to simplify the install before releasing the community preview. Testing on phones is particularly important because we made many of the UI changes to enable TouchXPRT to work acceptably on a small display.

We’ll keep you informed as testing proceeds. We’re hoping to release the community preview in the next couple of weeks.

Eric

Posted in Android, MobileXPRT, MobileXPRT 2015, TouchXPRT, TouchXPRT 2016, TouchXPRT release cycle, White papers, Windows 10, Windows 8, Windows 8.1 |

Question we get a lot

By Eric Hale

on October 2, 2015

“How come your benchmark ranks devices differently than [insert other benchmark here]?” It’s a fair question, and the reason is that each benchmark has its own emphasis and tests different things. When you think about it, it would be unusual if all benchmarks did agree.

To illustrate the phenomenon, consider this excerpt from a recent browser shootout in VentureBeat:

While this looks very confusing, the simple explanation is that the different benchmarks are testing different things. To begin with, SunSpider, Octane, JetStream, PeaceKeeper, and Kraken all measure JavaScript performance. Oort Online measures WebGL performance. WebXPRT measures both JavaScript and HTML 5 performance. HTML5Test measures HTML5 compliance.

Even with benchmarks that test the same aspect of browser performance, the tests differ. Kraken and SunSpider both test the speed of JavaScript math, string, and graphics operations in isolation, but run different sets of tests to do so. PeaceKeeper profiles the JavaScript from sites such as YouTube and FaceBook.

WebXPRT, like the other XPRTs, uses scenarios that model the types of work people do with their devices.

It’s no surprise that the order changes depending on which aspect of the Web experience you emphasize, in much the same way that the most fuel-efficient cars might not be the ones with the best acceleration.

This is a bigger topic than we can deal with in a single blog post, and we’ll examine it more in the future.

Eric

Posted in Benchmark metrics, Benchmarking, Benchmarking computing devices, BenchmarkXPRT development community, Collaborative benchmark development, Performance benchmarking, Performance of computing devices, WebXPRT, What makes a good benchmark? |

Month: October 2015

Things are looking good!

More than the sum of its parts

We haven’t mentioned this in a while

An update on TouchXPRT 2016

Question we get a lot

Check out the other XPRTs: