BenchmarkXPRT Blog banner

Category: Benchmarking

The AIXPRT Request for Comments preview build

Bill Catchings
By Bill Catchings
on December 20, 2018

In the next few days, we’ll be publishing the first AIXPRT tool as a Request for Comments (RFC) preview build, an early version of one of the AIXPRT tools we’re developing to help evaluate machine learning performance.

We’re inviting folks to run the workload and send in their thoughts and suggestions. Only BenchmarkXPRT Development Community members have access to our RFCs and the opportunity to provide feedback. However, because we’re seeking broad input from experts in this field, we’ll gladly make anyone interested in participating a member.

This AIXPRT RFC preview build includes support for the Intel OpenVINO computer vision toolkit to run image classification workloads with ResNet-50 and SSD-MobileNet v1 networks. The test reports FP32 and FP16 levels of precision. The system requirements are:

  • Operating system = Ubuntu 16.04
  • CPU = 6th to 8th generation Intel Core or Xeon processors, or Intel Pentium processors N4200/5, N3350/5, N3450/5 with Intel HD Graphics


We welcome input on all aspects of the benchmark, including scope, workloads, metrics and scores, user experience, and reporting. We will add support for TensorFlow and TensorRT to the AIXPRT RFC preview build during the preview period. We are accepting feedback through January 25th, 2019, after which we’ll collect and evaluate responses before publishing the next build. Because this is an RFC release, we ask that testers do not publish scores or use the results for comparison purposes.

We’ll send out a community announcement when the RFC preview build is officially available, and we’ll also post an announcement and RFC preview build user guide on AIXPRT.com. We’re hosting the AIXPRT RFC preview build in a dedicated GitHub repository, so please contact us at BenchmarkXPRTsupport@principledtechnologies.com to gain access.

This is just the next step for AIXPRT. With your help, we hope to add more workloads and other frameworks in the coming months. We look forward to receiving your feedback!

Bill

Posted in AI, AIXPRT, BenchmarkXPRT development community, Collaborative benchmark development, Community Preview, Future of performance evaluation, Machine learning, Open development, OpenVINO, Performance benchmarking, TensorFlow, TensorRT, Ubuntu, What makes a good benchmark? |

The MobileXPRT 3 Community Preview is here!

Justin Greene
By Justin Greene
on December 19, 2018

The MobileXPRT 3 Community Preview is now available to BenchmarkXPRT Development Community members! If you are not familiar with the updates and changes we implemented in the newest version of MobileXPRT, you can read more in the XPRT blog.

Members can access the MobileXPRT 3 Community Preview APK on the MobileXPRT tab in the Members’ Area. We also posted an installation guide that provides a general overview of the app and walks users through each step. The entire process takes about five minutes on most devices.

If you have any questions about MobileXPRT 3 or joining the community, please let us know. Happy testing!

Justin

Posted in Android, Benchmarking, BenchmarkXPRT, BenchmarkXPRT development community, Mobile devices, MobileXPRT, MobileXPRT 3, Phones, Tablets |

The MobileXPRT 3 Community Preview is almost here!

Justin Greene
By Justin Greene
on December 13, 2018

We appreciate everyone’s patience and feedback during the MobileXPRT 3 development process. We’re in the process of wrapping up some final testing and expect to release the Community Preview (CP) within the next week.

The first thing testers will notice about the CP is a new UI/UX experience. The aesthetic is completely different than MobileXPRT 2015. We’ve made it easy to select and deselect individual workloads by tapping the workload name, and we’ve consolidated common menu items into an Android-style task bar at the bottom of the screen to improve navigation.

Fundamentally, we rebuilt MobileXPRT with Android Studio SDK 27 to bring it up to date with contemporary Android development standards. While we kept the five workloads from MobileXPRT 2015, we gave one a major overhaul, updated the test content in the remaining four, and added a sixth workload: Optical Character Recognition. You can find more details about these changes in our earlier discussion about MobileXPRT 3 development in the blog.

The screenshots below show the MobileXPRT 3 main screen, how the screen looks when users customize the combination of workloads, the end-of-test results screen, and the archived results page with one test result view expanded. Note that the archived results page also displays the median of all overall test scores completed to date.

We’ll announce the CP in a community message and here on the blog when it goes live. As with all community previews, the MobileXPRT 3 CP will be available only to BenchmarkXPRT Development Community members. If you have any questions about MobileXPRT 3 or joining the community, please let us know. Happy testing!

Justin

MobileXPRT 3 start screen   MobileXPRT 3 select workloadsMobileXPRT 3 results   MobileXPRT 3 results library

Posted in Android, BenchmarkXPRT development community, Collaborative benchmark development, Community Preview, Mobile devices, MobileXPRT, MobileXPRT 2015, MobileXPRT 3 |

XPRT collaborations: North Carolina State University

Justin Greene
By Justin Greene
on December 6, 2018

For those of us who work on the BenchmarkXPRT tools, a core goal is involving new contributors and interested parties in the benchmark development process. Adding voices to the discussion fosters the collaboration and innovation that lead to powerful benchmark tools with lasting relevance.

One vehicle for outreach that we especially enjoy is sponsoring a student project through North Carolina State University. Each semester, the Senior Design Center in the university’s Department of Computer Science partners with external companies and organizations to provide student teams with an opportunity to work on real-world programming projects. If you’ve followed the XPRTs for a while, you may remember previous student projects such as Nebula Wolf, a mini-game that shows how well different devices handle games, and VR Demo, a virtual reality prototype workload based on a room escape scenario.

This fall, a team of NC State students is developing a software console for automating machine learning tests. Ideally, the tool will let future testers specify custom workload combinations, compute a performance metric, and upload results to our database. The project will also assess the impact of the framework on performance scores. In fact, the console will perform many of the same functions we plan to implement with AIXPRT.

The students have worked very hard on the project, and have learned quite a bit about benchmarking practices and several new software tools. The project will wrap up in the next couple of weeks, and we’ll share additional details as soon as possible. Early next year, we’ll publish a video about the experience.

If you’d like to join the NC State students and hundreds of other XPRT community members in the future of benchmark development, please let us know!

Justin

Posted in AI, AIXPRT, Benchmarking, BenchmarkXPRT development community, Collaborative benchmark development, Education, Future of performance evaluation, Nebula Wolf, North Carolina State University, Virtual reality, VR Demo | Tagged , , , , , , , , , , |

HDXPRT 4: Getting it right

Justin Greene
By Justin Greene
on November 8, 2018

For BenchmarkXPRT Development Community members anticipating the HDXPRT 4 Community Preview (CP), we want to thank you for your patience and explain where we are in the release process.

This past month has brought a flurry of activity in the Windows 10 development world. We’ve been testing HDXPRT 4 extensively on each of the new prerelease builds available through the Windows Insider Program. While testing on a recent Windows 10 Redstone 5 preview build, we began to see inconsistent HDXPRT 4 workload scores on some systems. The difference between those workload scores and scores on the same systems with previous Windows 10 builds was significant enough for us to decide that the best course of action is to hold off on the CP until we understand the issue. We don’t want to release a CP only to run into serious problems with an imminent Windows release. We want to take the time to figure out what’s going on and get it right.

We hope to resolve these issues and publish the HDXPRT 4 CP as soon as possible. Thanks again for your patience. We’ll update the community soon with more information on the anticipated release schedule.

Justin

Posted in Application-based benchmarks, Benchmarking, BenchmarkXPRT, BenchmarkXPRT development community, Collaborative benchmark development, Community Preview, HDXPRT, HDXPRT 4, HDXPRT development process, HDXPRT release cycle, Performance benchmarking, Windows 10 | Tagged , , , , , |

A new BatteryXPRT 2014 for Android build is available

Justin Greene
By Justin Greene
on October 26, 2018

In last week’s blog, we discussed why we now consider full BatteryXPRT rundown tests to be the most accurate and why we’re releasing a new build (v110) that increases the default BatteryXPRT test from 5.25 hours (seven iterations) to 45 hours (60 iterations). We also built v110 using Android Studio SDK 27, in order to bring BatteryXPRT up to date with current Android standards. Today, we’ve posted the new build on BatteryXPRT.com and in the Google Play Store, and we’ve also published an updated user manual. Please contact us if you have any questions about BatteryXPRT testing.

Justin

Posted in Android, Battery life, BatteryXPRT 2014 for Android, Benchmarking, BenchmarkXPRT | Tagged , , , , , , |

Check out the other XPRTs:

Forgot your password?
© Principled Technologies, Inc. 2024   |   Privacy policy

Cookie Notice: Our website uses cookies to deliver a smooth experience by storing logins and saving user information. By continuing to use our site, you agree with our usage of cookies as our privacy policy outlines.

x