BenchmarkXPRT Blog banner

Category: Future of performance evaluation

CES 2020: AI in action and a “smart” future

During last year’s Consumer Electronics Show (CES), one question kept coming to mind as I walked the floor: Are we approaching the tipping point where AI truly affects most people in meaningful ways on a daily basis? I think it’s safe to say that we’ve reached that point as a result of AI integration with phones. After all, for many of us, AI improves the quality of our photography, recommends words and phrases as we text and search the web, and lets us know when to allow extra drive time because traffic is heavy.

However, for me, the most intriguing aspects of this year’s CES are the glimpses of how AI will change every area of our lives, with and without mobile devices. The show floor is jam-packed with ways to integrate AI with everything from athletic shoes to pet care to the kitchen sink. Many of these ideas are fascinating on their own, and they’re all part of a much bigger picture. The next few years will see increased AI utilization in medicine, transportation, agriculture, water and energy distribution, natural resource protection, and many more areas. Our personal smart devices will connect to smart vehicles, smart homes, smart grids, and smart cities. In the near future, CES shows won’t need AI sections because AI will be a part of everything.

At each step of this journey, people will need objective data about how well their tech can handle the demands of common AI workloads. We’re excited that AIXPRT is already becoming a go-to tool for testing inference performance on laptops, desktops, and servers. There’s much more to come with AIXPRT in 2020, along with news about XPRTs in the datacenter, so stay tuned to the blog for exciting developments in the weeks to come!

I’ll leave you with pics from three of my favorite displays at this year’s show. The first is a model of Toyota’s Woven City. Toyota announced plans to build an entire mini city on existing company land near Mount Fuji. The city will house 2,000 people and will serve as an enormous real-time lab where designers and engineers can test ubiquitous AI and sensor technology. Toyota will also design the city to be fully sustainable with the use of hydrogen fuel cells and solar panels.

The second picture shows the electric Hyundai Urban Air Mobility prototype. Hyundai is partnering with Uber on this project, and the planned vertical take-off and landing (VTOL) craft will seat five passengers plus a pilot, have a range of 60 miles, and be able to recharge in less than 10 minutes. These concepts aren’t new, but battery and material sciences technologies are progressing to the point that this one may get off the ground!

The third picture shows BrainCo’s AI Prosthetic Hand display. The hand provides amputees with new levels of dexterity compared to previous prosthetics, and it uses AI to learn from the user’s patterns of movement. The idea is that the accuracy of gestures and grips will improve over time, allowing users to accomplish tasks that are impossible with existing technology. A young man in the booth was using the hand to paint beautiful and precise Chinese calligraphy. Very cool!


AIXPRT’s unique development path

With four separate machine learning toolkits on their own development schedules, three workloads, and a wide range of possible configurations and use cases, AIXPRT has more moving parts than any of the XPRT benchmark tools to date. Because there are so many different components, and because we want AIXPRT to provide consistently relevant evaluation data in the rapidly evolving AI and machine learning spaces, we anticipate a cadence of AIXPRT updates in the future that will be more frequent than the schedules we’ve used for other XPRTs in the past. With that expectation in mind, we want to let AIXPRT testers know that when we release an AIXPRT update, they can expect minimized disruption, consideration for their testing needs, and clear communication.

Minimized disruption

Each AIXPRT toolkit (Intel OpenVINO, TensorFlow, NVIDIA TensorRT, and Apache MXNet) is on its own development schedule, and we won’t always have a lot of advance notice when new versions are on the way. Hypothetically, a new version of OpenVINO could release one month, and a new version of TensorRT just two months later. Thankfully, the modular nature of AIXPRT’s installation packages ensures that we won’t need to revise the entire AIXPRT suite every time a toolkit update goes live. Instead, we’ll update each package individually when necessary. This means that if you only test with a single AIXPRT package, updates to the other packages won’t affect your testing. For us to maintain AIXPRT’s relevance, there’s unfortunately no way to avoid all disruption, but we’ll work to keep it to a minimum.

Consideration for testers

As we move forward, when software compatibility issues force us to update an AIXPRT package, we may discover that the update has a significant effect on results. If we find that results from the new package are no longer comparable to those from previous tests, we’ll share the differences that we’re seeing in our lab. As always, we will use documentation and versioning to make sure that testers know what to expect and  that there’s no confusion about which package to use.

Clear communication

When we update any package, we’ll make sure to communicate any updates in the new build as clearly as possible. We’ll document all changes thoroughly in the package readmes, and we’ll talk through significant updates here in the blog. We’re also available to answer questions about AIXPRT and any other XPRT-related topic, so feel free to ask!


AIXPRT Community Preview 3 is here!

We’re happy to announce that the AIXPRT Community Preview 3 (CP3) is now available! As we discussed in last week’s blog, testers can expect three significant changes in AIXPRT CP3:

  • We updated support for the Ubuntu test packages from Ubuntu version 16.04 LTS to version 18.04 LTS.
  • We added TensorRT test packages for Windows and Ubuntu. Previously, AIXPRT testers could test only the TensorFlow variant of TensorRT. Now, they can use TensorRT to test systems with NVIDIA GPUs.
  • We added the Wide and Deep recommender system workload with the MXNet toolkit for Ubuntu systems.

To access AIXPRT CP3, click this access link and submit the brief information form unless you’ve already done so for CP2. You will then gain access to the AIXPRT community preview page. (If you’re not already a BenchmarkXPRT Development Community member, we’ll contact you with more information about your membership.)

On the community preview page, a download table displays the currently available AIXPRT CP3 test packages. Locate the operating system and toolkit you wish to test, and click the corresponding Download link. For detailed installation instructions and information on hardware and software requirements for each package, click the corresponding Readme link. Instead of providing installation guide PDFs as we did for CP2, we are now directing testers to a public GitHub repository. The repository contains the installation readmes for all the test packages, as well as a selection of alternative test configuration files. We’ll discuss the alternative configuration files in more detail in a future blog post.

Note: Those who have access to the existing AIXPRT GitHub repository will be able to access CP3 in the same way as previous versions.

We’ll continue to keep everyone up to date with AIXPRT news here in the blog. If you have any questions or comments, please let us know.


Planning for the next TouchXPRT

We’re in the very early planning stages for the next version of TouchXPRT, and we’d love to hear any suggestions you may have. What do you like or dislike about TouchXPRT? What features do you hope to see in a new version?

For those who are unfamiliar with TouchXPRT, it’s a benchmark for evaluating the performance of Windows 10 devices. TouchXPRT 2016, the most recent version, runs tests based on five everyday scenarios (Beautify Photos, Blend Photos, Convert Videos for Sharing, Create Music Podcast, and Create Slideshow from Photos) and produces results for each of the five scenarios plus an overall score. The benchmark is available two ways: as a Universal Windows App in the Microsoft Store and as a sideload installer package on

When we begin work on a new version of any benchmark, one of the first steps we take is to assess its workloads to determine whether they will provide value during the years ahead. This step involves evaluating whether to update test content such as photos and videos to more contemporary file resolutions and sizes, and can also involve removing workloads or adding completely new ones. Should we keep the TouchXPRT workloads listed above or investigate other use cases? Should we research potential AI-related workloads? What do you think?

As we did with MobileXPRT 3 and HDXPRT 4 earlier this year, we’re also planning to update the TouchXPRT UI to improve the look of the benchmark and make it easier to use. We’re just at the beginning of this process, so any feedback you send has a chance to really shape the future of the benchmark.

On a related note, TouchXPRT 2016 testers who use the installer package available on may have noticed that the package has a new file name ( Microsoft requires developers to assign a security certificate to all sideload apps, and the new TouchXPRT file contains a refreshed certificate. We did not change the benchmark in any other way, so scores from this package are comparable to previous TouchXPRT 2016 scores.


WebXPRT: What would you like to see?

At over 412,000 runs and counting, WebXPRT is our most popular benchmark. From the first release in 2013, it’s been popular with device manufacturers, developers, tech journalists, and consumers because it’s easy to run, it runs on almost anything with a web browser, and it evaluates device performance using the types of web-based tasks that people are likely to encounter on a daily basis.

With each new version of WebXPRT, we analyze browser development trends to make sure the test’s underlying web technologies and workload scenarios adequately reflect the ways people are using their browsers to work and play. BenchmarkXPRT Development Community members can play an important part in that process by sending us feedback on existing tests and suggestions for new workloads to include.

For example, when we released WebXPRT 3, we updated the photo workloads with new images and a deep learning task used for image classification. We also added an optical character recognition task in the Encrypt Notes and OCR scan workload, and combined part of the DNA Sequence Analysis scenario with a writing sample/spell check scenario to simulate online homework in an all-new Online Homework workload.

Consider for a moment what an ideal future version of WebXPRT would look like for you. Are there new web technologies or workload scenarios that you would like to see? Would you be interested in an associated battery life test? Should we include experimental tests? We’re interested in what you have to say, so please feel free to contact us with your thoughts or questions.

If you’re just now learning about WebXPRT, we offer several resources to help you better understand the benchmark and its range of uses. For a general overview of why WebXPRT matters, watch our video titled What is WebXPRT and why should I care? To read more about the details of the benchmark’s development and structure, check out the Exploring WebXPRT 3 white paper. To see WebXPRT 2015 and WebXPRT 3 scores from a wide range of processors, visit the WebXPRT 3 Processor Comparison Chart.

We look forward to hearing from you!


An updated HDXPRT 4 build is on the way

HandBrake recently released a new version, v1.2.2, of their video conversion software. Among other improvements, the new version includes support for certain AMD (VCE) and NVIDIA (NVENC) hardware-accelerated video encoders. Because we include HandBrake as one of the commercial applications in the HDXPRT installer package, and because we want to keep HDXPRT 4 up-to-date for testers, we’ve put together a new HDXPRT 4 build: v1.1.  It includes HandBrake 1.2.2’s new capabilities, and we’re currently testing it in the lab.

With the new build, testers will be able to choose whether HDXPRT’s HandBrake tasks target a system’s integrated or discrete graphics cards by changing a flag called “UseIntegrated” in the config file. In HDXPRT 4 v1.1, the flag is set to “true” by default, directing HandBrake to use the codec provided by the system’s integrated graphics hardware. On the other hand, if a system has both integrated and discrete graphics available, and a user sets the flag to “false,” HandBrake will use the codec provided by the discrete graphics.

This update allows users to compare the video conversion performance of different video codecs on the same system. In all other respects, the benchmark has not changed. So apart from a scenario where a tester changes the targeted graphics hardware, scores from previous HDXPRT 4 builds will be comparable to those from the new build.

We’ll let the community know as soon as the new build is available, and we’ll update the HDXPRT 4 User Manual to reflect the changes.

If you have any questions about the upcoming HDXPRT 4 build, please let us know!


Check out the other XPRTs:

Forgot your password?