BenchmarkXPRT Blog banner

Category: Collaborative benchmark development

Contribute to WebXPRT’s AI capabilities with your NPU-equipped gear

Justin Greene
By Justin Greene
on July 11, 2024

A few weeks ago, we announced that we’re developing a new auxiliary WebXPRT 4 workload focused on local, browser-based AI technology. This is an exciting project for us, and as we work to determine the best approach from the perspective of frameworks, APIs, inference models, and test scenarios, we’re also thinking ahead to the testing process. To best understand how the new workload will impact system performance, we’re going to need to test it on hardware equipped with the latest generation of neural processing units (NPUs).

NPUs are not new, but the technology is advancing rapidly, and a growing number of PC and laptop manufacturers are releasing NPU-equipped systems. Several vendors have announced plans to release systems equipped with all-new NPUs in the latter half of this year. As is often the case with bleeding-edge technology, however, official release dates do not always coincide with widespread availability.

We want to evaluate new AI-focused WebXPRT workloads on the widest possible range of new systems, but getting a wide selection of gear equipped with the latest NPUs may take quite a while through normal channels. For that reason, we’ve decided to ask our readers for help to expedite the process.

If you’re an OEM or vendor representative with access to the latest generation of NPU-equipped gear and want to contribute to WebXPRT’s evolution, consider sending us any PCs, white boxes, laptops, 2-in-1s, or tablets (on loan) that would be suitable for NPU-focused testing. We have decades of experience serving as trusted testers of confidential and pre-release gear, so we’re well-acquainted with concerns about confidentiality that may come into play, and we won’t publish any information about the systems or related test results without your permission.

We will, though, be happy to share with you our test results on your systems, and we’d love to hear any guidance or other feedback from you on this new workload.

We’re open to any suitable gear, but we’re especially interested in AMD Ryzen AI, Apple M4, Intel Lunar Lake and Arrow Lake, and Qualcomm Snapdragon X Elite systems.

If you’re interested in sending us gear for WebXPRT development testing, please contact us. We’ll work out all the necessary details. Thanks in advance for your help!

Justin

Posted in AI, AMD, Apple, Arrow Lake, benchmark, Benchmarking, browser performance, Browser-based benchmarks, Collaborative benchmark development, Cross-platform benchmarks, Future of performance evaluation, Intel, Laptops, Lunar Lake, M4, Machine learning, Mobile devices, NPU, on-device AI, PCs, Performance benchmarking, Qualcomm, Ryzen AI, Snapdragon X Elite, Tablets, Web-based testing, WebXPRT, WebXPRT 4 | Tagged , , , , , , , , , , , , , , , , , , , , , , |

Up next for WebXPRT 4: A new AI-focused workload!

Justin Greene
By Justin Greene
on May 30, 2024

We’re always thinking about ways to improve WebXPRT. In the past, we’ve discussed the potential benefits of auxiliary workloads and the role that such workloads might play in future WebXPRT updates and versions. Today, we’re very excited to announce that we’ve decided to move forward with the development of a new WebXPRT 4 workload focused on browser-side AI technology!

WebXPRT 4 already includes timed AI tasks in two of its workloads: the Organize Album using AI workload and the Encrypt Notes and OCR Scan workload. These two workloads reflect the types of light browser-side inference tasks that have been available for a while now, but most heavy-duty inference on the web has historically happened in on-prem servers or in the cloud. Now, localized AI technology is growing by leaps and bounds, and the integration of new AI capabilities with browser-based tasks is on the threshold of advancing rapidly.

Because of this growth, we believe now is the time to start work on giving WebXPRT 4 the ability to evaluate new browser-based AI capabilities—capabilities that are likely to become a part of everyday life in the next few years. We haven’t yet decided on a test scenario or software stack for the new workload, but we’ll be working to refine our plan in the coming months. There seems to be some initial promise in emerging frameworks such as ONNX Runtime Web, which allows users to run and deploy web-based machine learning models by using JavaScript APIs and libraries. In addition, new Web APIs like WebGPU (currently supported in Edge, Chrome, and tech preview in Safari) and WebNN (in development) may soon help facilitate new browser-side AI workloads.

We know that many longtime WebXPRT 4 users will have questions about how this new workload may affect their tests. We want to assure you that the workload will be an optional bonus workload and will not run by default during normal WebXPRT 4 tests. As you consider possibilities for the new workload, here are a few points to keep in mind:

  • The workload will be optional for users to run.
  • It will not affect the main WebXPRT 4 subtest or overall scores in any way.
  • It will run separately from the main test and will produce its own score(s).
  • Current and future WebXPRT 4 results will still be comparable to one another, so users who’ve already built a database of WebXPRT 4 scores will not have to retest their devices.
  • Because many of the available frameworks don’t currently run on all browsers, the workload may not run on every platform.

As we research available technologies and explore our options, we would love to hear from you. If you have ideas for an AI workload scenario that you think would be useful or thoughts on how we should implement it, please let us know! We’re excited about adding new technologies and new value to WebXPRT 4, and we look forward to sharing more information here in the blog as we make progress.

Justin

Posted in AI, benchmark, BenchmarkXPRT, BenchmarkXPRT development community, browser performance, Browser-based benchmarks, Chrome, Collaborative benchmark development, Future of performance evaluation, JavaScript, Microsoft Edge, on-device AI, ONNX Runtime Web, Performance benchmarking, Safari, WebGPU, WebNN, WebXPRT, WebXPRT 4 | Tagged , , , , , , , , , , , |

Accessing the WebXPRT 4 source code

Justin Greene
By Justin Greene
on March 7, 2024

If you’re new to the XPRTs, you may not be aware that we provide free access to XPRT benchmark source code. Publishing XPRT source code is part of our commitment to making the XPRT development process as transparent as possible. By allowing interested parties to access and review our source code, we’re encouraging openness and honesty in the benchmarking industry. We’re also inviting constructive feedback that can help ensure that the XPRTs continue to improve and contribute to a level playing field for all the types of products they measure.

While we do offer free access to the XPRT source code, we’ve decided to offer the code upon request instead of using a permanent download link. This approach prevents bots or other malicious actors from downloading the code. It also has the benefit of allowing us to interact with users who are interested in the source code and answer any questions they may have. We’re always keen to learn more about what others are thinking about the XPRTs and the types of work they measure.

We recently received some questions about accessing the WebXPRT 4 source code, which made us realize that we needed to make a clearer way for people to ask for the code. In response, we added a “Request WebXPRT 4 source code” link to the gray Helpful Info box on WebXPRT.com (see it in the screenshot below). Clicking the link will allow you to email the BenchmarkXPRT Support team directly and request the code.

After we receive your request, we’ll send you a secure link to the current WebXPRT 4 build package. For those users who wish to set up a local instance of WebXPRT 4 for their own internal testbeds, the package will contain all the necessary files and installation instructions. We allow folks to set up their own instances for purposes of review, internal testing, or experimentation, but we ask that users publish only test results from the official WebXPRT 4 site.

While we offer free access to XPRT source code, our approach to derivative works differs from some traditional open-source models that encourage developers to change products and even take them in different directions. Because benchmarking requires a product that remains static to enable valid comparisons over time, we allow people to download the source, but we reserve the right to control derivative works. This discourages a situation where someone publishes an unauthorized version of the benchmark and calls it an “XPRT.”

If you have any questions about accessing the WebXPRT 4 source code, let us know!

Justin

Posted in Benchmarking, BenchmarkXPRT development community, Collaborative benchmark development, Open Source, Performance benchmarking, Source code, WebXPRT, WebXPRT 4 | Tagged , , , , , , , , |

Looking back on 2023 with the XPRTs

Justin Greene
By Justin Greene
on January 4, 2024

Around the beginning of each new year, we like to take the opportunity to look back and summarize the XPRT highlights from the previous year. Readers of our newsletter are familiar with the stats and updates we include each month, but for our blog readers who don’t receive the newsletter, we’ve compiled highlights from 2023 below.

Benchmarks
In March, we celebrated the 10-year anniversary of WebXPRT! WebXPRT 4 has now taken the lead as the most commonly-used version of WebXPRT, even as the overall number of runs has continued to grow.

XPRTs in the media
Journalists, advertisers, and analysts referenced the XPRTs thousands of times in 2023. It’s always rewarding to know that the XPRTs have proven to be useful and reliable assessment tools for technology publications around the world. Media sites that used the XPRTs in 2023 include 3DNews (Russia), AnandTech, Benchlife.info (China), CHIP.pl (Poland), ComputerBase (Germany), eTeknix, Expert Reviews, Gadgetrip (Japan), Gadgets 360, Gizmodo, Hardware.info, IT168.com (China), ITC.ua (Ukraine), ITWorld (Korea), iXBT.com (Russia), Lyd & Bilde (Norway), Notebookcheck, Onchrome (Germany), PCMag, PCWorld, QQ.com (China), Tech Advisor, TechPowerUp, TechRadar, Tom’s Guide, TweakTown, Yesky.com (China), and ZDNet.

Downloads and confirmed runs
In 2023, we had more than 16,800 benchmark downloads and 296,800 confirmed runs. Users have run our most popular benchmark, WebXPRT, more than 1,376,500 times since its debut in 2013! WebXPRT continues to be a go-to, industry-standard performance benchmark for OEM labs, vendors, and leading tech press outlets around the globe.

Trade shows
In January, Justin attended the 2023 Consumer Electronics Show (CES) Las Vegas. In March, Mark attended Mobile World Congress (MWC) 2023 in Barcelona. You can view Justin’s recap of CES here and Mark’s thoughts from MWC here.

We’re thankful for everyone who used the XPRTs and sent questions and suggestions throughout 2023. We’re excited to see what’s in store for the XPRTs in 2024!

Justin

Posted in Barcelona, benchmark, BenchmarkXPRT, BenchmarkXPRT development community, CES, Collaborative benchmark development, Consumer Electronics Show, History of benchmarking, Las Vegas, Mobile World Congress, Performance benchmarking, results, results submission, tech press, Trade Shows, WebXPRT, WebXPRT 4 | Tagged , , , , , , , , , , , , , , , , , , , , , |

We want your thoughts about experimental WebXPRT 4 workloads

Justin Greene
By Justin Greene
on December 8, 2022

Two weeks ago, we discussed how users can automate WebXPRT 4 testing by appending several parameters and values to the benchmark’s URL. One of these lets you enable any available experimental workloads during the test run. While we don’t currently offer any experimental workloads for WebXPRT 4, we are seeking suggestions for possible future workload scenarios, or specific web technologies that you’d like to be able to test with an experimental workload.

The main purpose of optional, experimental workloads would be to test cutting-edge browser technologies or new use cases, even if the experimental workload doesn’t work on all browsers or devices. The individual scores for the experimental workloads would stand alone, and would not factor in the WebXPRT 4 overall score. WebXPRT 4 testers would be able to run the experimental workloads one of two ways: by adjusting a value in the WebXPRT 4 automation scripts, as mentioned above, or by manually selecting them on the benchmark’s home screen.

Testers would benefit from experimental workloads by learning how well certain browsers or systems handle new tasks (e.g., new web apps or AI capabilities). We would benefit from fielding workloads for large-scale testing and user feedback before we commit to including them as core WebXPRT workloads.

Do you have any general thoughts about experimental workloads for browser performance testing, or any specific workloads that you’d like us to consider? Please let us know.

Justin

Posted in AI, Automation, benchmark, Benchmark metrics, Benchmarking, BenchmarkXPRT, Browser-based benchmarks, Collaborative benchmark development, Cross-platform benchmarks, Future of performance evaluation, Performance benchmarking, WebXPRT, WebXPRT 4, What makes a good benchmark? | Tagged , , , , , , , , |

Looking forward to an important WebXPRT milestone

Justin Greene
By Justin Greene
on December 1, 2022

February 28, 2013 was a momentous day for the BenchmarkXPRT Development Community. On that day, we published a press release announcing the official launch of the first version of the WebXPRT benchmark, WebXPRT 2013. As difficult as it is for us to believe, the 10-year anniversary of the initial WebXPRT launch is in just a few short months!

We introduced WebXPRT as a truly unique browser performance benchmark in a field that was already crowded with a variety of measurement tools. Since those early days, the WebXPRT market presence has grown from a small foothold into a worldwide industry standard. Over the years, hundreds of tech press publications have used WebXPRT in thousands of articles and reviews, and the WebXPRT completed-runs counter rolled over the 1,000,000-run mark.

New web technologies are continually changing the way we use the web, and browser-performance benchmarks should evaluate how well new devices handle the web of today, not the web of several years ago. While some organizations have stopped development for other browser performance benchmarks, we’ve had the opportunity to continue updating and refining WebXPRT. We can look back at each of the four major iterations of the benchmark—WebXPRT 2013, WebXPRT 2015, WebXPRT 3, and WebXPRT 4—and see a consistent philosophy and shared technical lineage contributing to a product that has steadily improved.

As we get closer to the 10-year anniversary of WebXPRT next year, we’ll be sharing more insights about its reach and impact on the industry, discussing possible future plans for the benchmark, and announcing some fun anniversary-related opportunities for WebXPRT users. We think 2023 will be the best year yet for WebXPRT!

Justin

Posted in benchmark, Benchmark metrics, Benchmarking, BenchmarkXPRT, BenchmarkXPRT development community, Browser-based benchmarks, Collaborative benchmark development, Cross-platform benchmarks, Future of performance evaluation, History of benchmarking, Performance benchmarking, Web-based testing, WebXPRT, WebXPRT 2013, WebXPRT 2015, WebXPRT 3, WebXPRT 4 | 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