BenchmarkXPRT Blog banner

Category: Collaborative benchmark development

Web APIs: Possible paths for the AI-focused WebXPRT 4 auxiliary workload

In our last blog post, we discussed one of the major decision points we’re facing as we work on what we hope will be the first new AI-focused WebXPRT 4 auxiliary workload: choosing a Web AI framework. In today’s blog, we’re discussing another significant decision that we need to make for the future workload’s development path: choosing a web API.

Many of you are familiar with the concept of an application programming interface (API). Simply put, APIs implement sets of software rules, tools, and/or protocols that serve as intermediaries that make it possible for different computer programs or components to communicate with each other. APIs simplify many development tasks for programmers and provide standardized ways for applications to share data, functions, and system resources.

Web APIs fulfill the intermediary role of an API—through HTTP-based communication—for web servers (on the server side) or web browsers (on the client side). Client-side web APIs make it possible for browser-based applications to expand browser functionality. They execute the kinds of JavaScript, HTML5, and WebAssembly (Wasm) workloads—among other examples—that support the wide variety of browser extensions many of us use every day. WebXPRT uses those types of browser-based workloads to evaluate system performance. To lay a solid foundation for the first future browser-based AI workload, we need to choose a web API that will be compatible with WebXPRT and the Web AI framework and AI inference workload(s) we ultimately choose.

Currently, there are three main web API paths for running AI inference in a web browser: Web Neural Network (WebNN), Wasm, and WebGPU. These three web technologies are in various stages of development and standardization. Each has different levels of support within the major browsers. Here are basic overviews of each of the three options, as well as a few of our thoughts on the benefits and limitations that each may bring to the table for a future WebXPRT AI workload:

  • WebNN is a JavaScript API that enables developers to directly execute machine learning (ML) tasks on neural networks within web-based applications. WebNN makes it easier to integrate ML models into web apps, and it allows web apps to leverage the power of neural processing units (NPUs). WebNN has a lot going for it. It’s hardware-agnostic and works with various ML frameworks. It’s likely to be a major player in future browser-based inference applications. However, as a web standard, WebNN is still in the development stage and is only available in developer previews for Chromium-based browsers. Full default WebNN support could take a year or more.
  • Wasm is a binary instruction format that works across all modern browsers. Wasm provides a sandboxed environment that operates at near-native speeds and takes advantage of common hardware specs across platforms. Wasm’s capabilities offer web developers a great deal of flexibility for running complex client applications in the browser. Simply put, Wasm can help developers adapt their existing code for additional platforms and browser-based applications without requiring extensive code rewrites. Wasm’s flexibility and cross-platform compatibility is one of the reasons that we’ve already made use of Wasm in two existing WebXPRT 4 workloads that feature AI tasks: Organize Album using AI, and Encrypt Notes and OCR Scan. Wasm can also work together with other web APIs, such as WebGPU.
  • WebGPU enables web-based applications to directly access the graphics rendering and computational capabilities of a system’s GPU. The parallel computational abilities of GPUs make them especially well-suited to efficiently handle some of the demands of AI inference workloads, including image-based GenAI workloads or large language models. Google Chrome and Microsoft Edge currently support WebGPU, and it’s available in Safari through a tech preview.

Right now, we don’t think that WebNN will be fully out of the development phase in time to serve as our go-to web API for a new WebXPRT AI workload. Wasm and/or WebGPU appear to our best options for now. When WebNN is fully baked and available in mainstream browsers, it’s possible that we could port any existing Wasm- or WebGPU-based WebXPRT AI workloads to WebNN, which may open the possibility of cross-platform browser-based NPU performance comparisons.

All that said and as we mentioned in our previous post about Web AI frameworks, we have not made any final decisions about a web API or any aspect of the future workload. We’re still in the early stages of this project. We want your input.

If this discussion has sparked web AI ideas that you think would benefit the process, or if you have feedback you’d like to share, please feel free to contact us!

Justin

Web AI frameworks: Possible paths for the AI-focused WebXPRT 4 auxiliary workload

A few months ago, we announced that we’re moving forward with the development of a new auxiliary WebXPRT 4 workload focused on local, browser-side AI technology. Local AI has many potential benefits, and it now seems safe to say that it will be a common fixture of everyday life for many people in the future. As the growth of browser-based inference technology picks up steam, our goal is to equip WebXPRT 4 users with the ability to quickly and reliably evaluate how well devices can handle substantial local inference tasks in the browser.

To reach our goal, we’ll need to make many well-researched and carefully considered decisions along the development path. Throughout the decision-making process, we’ll be balancing our commitment to core XPRT values, such as ease of use and widespread compatibility, with the practical realities of working with rapidly changing emergent technologies. In today’s blog, we’re discussing one of the first decision points that we face—choosing a Web AI framework.

AI frameworks are suites of tools and libraries that serve as building blocks for developers to create new AI-based models and apps or integrate existing AI functions in custom ways. AI frameworks can be commercial, such as OpenAI, or open source, such as Hugging Face, PyTorch, and TensorFlow. Because the XPRTs are available at no cost for users and we publish our source code, open-source frameworks are the right choice for WebXPRT.

Because the new workload will focus on locally powered, browser-based inference tasks, we also need to choose an AI framework that has browser integration capabilities and does not rely on server-side computing. These types of frameworks—called Web AI—use JavaScript (JS) APIs and other web technologies, such as WebAssembly and WebGPU, to run machine learning (ML) tasks on a device’s CPU, GPU, or NPU.

Several emerging Web AI frameworks may provide the compatibility and functionality we need for the future WebXPRT workload. Here are a few that we’re currently researching:

  • ONNX Runtime Web: Microsoft and other partners developed the Open Neural Network Exchange (ONNX) as an open standard for ML models. With available tools, users can convert models from several AI frameworks to ONNX, which can then be used by ONNX Runtime Web. ONNX Runtime Web allows developers to leverage the broad compatibility of ONNX-formatted ML models—including pre-trained vision, language, and GenAI models—in their web applications.
  • Transformers.js: Transformers.js, which uses ONNX Runtime Web, is a JS library that allows users to run AI models from the browser and offline. Transformers.js supports language, computer vision, and audio ML models, among others.
  • MediaPipe: Google developed MediaPipe as a way for developers to adapt TensorFlow-based models for use across many platforms in real-time on-device inference applications such as face detection and gesture recognition. MediaPipe is particularly useful for inference work in images, videos, and live streaming.
  • TensorFlow.js: TensorFlow has been around for a long time, and the TensorFlow ecosystem provides users with a broad variety of models and datasets. TensorFlow is an end-to-end ML solution—training to inference—but with available pre-trained models, developers can focus on inference. TensorFlow.js is an open-source JS library that helps developers integrate TensorFlow with web apps.

We have not made final decisions about a Web AI framework or any aspect of the future workload. We’re still in the research, discussion, and experimentation stages of development, but we want to be transparent with our readers about where we are in the process. In future blog posts, we’ll discuss some of the other major decision points in play.

Most of all, we invite you to join us in these discussions, make recommendations, and give us any other feedback or suggestions you may have, so please feel free to share your thoughts!

Justin

Putting together a good WebXPRT workload proposal

Recently, we announced that we’re moving forward with the development of a new AI-focused WebXPRT 4 workload. It will be an auxiliary workload, which means that it will run as a separate, optional test, and it won’t affect existing WebXPRT 4 tests or scores. Although the inspiration for this new workload came from internal WebXPRT discussions—and, let’s face it, from the huge increase in importance of AI–we wanted to remind you that we’re always open to hearing your WebXPRT workload ideas. If you’d like to submit proposals for new workloads, you don’t have to follow a formal process. Just contact us, and we’ll start the conversation.

If you do decide to send us a workload proposal, it will be helpful to know the types of parameters that we keep in mind. Below, we discuss some of the key questions we ask when we evaluate new WebXPRT workload ideas.

Will it be relevant and interesting to real users, lab testers, and tech reviewers?

When considering a WebXPRT workload proposal, the first two criteria are simple: is it relevant in real life, and are people interested in the workload? We created WebXPRT to evaluate device performance using web-based tasks that consumers are likely to experience daily, so real-life relevance has always been an essential requirement for us throughout development. There are many technologies, functions, and use cases that we could test in a web environment, but only some are relevant to common applications or usage patterns and are likely to draw the interest of real users, lab testers, and technical reviewers.

Will it have cross-platform support?

Currently, WebXPRT runs on almost any web browser and almost every device that supports a web browser. We would like to keep that level of cross-platform support when we introduce new workloads. However, technical differences in how various browsers execute tasks make it challenging to include certain scenarios without undermining our cross-platform ideal. When considering any workload proposal, one of the first questions we ask is, “Will it work on all the major browsers and operating systems?”

There are special exceptions to this guideline. For instance, we’re still in the early days of browser-based AI, and it’s unlikely that a new browser-based AI workload will run on every major browser. If it’s a particularly compelling idea, such as the AI scenario we’re currently working on, we may consider including it as an auxiliary test.

Will it differentiate performance between different types of devices?

XPRT benchmarks provide users with accurate measures for evaluating how well target systems or technologies perform specific tasks. With a broadly targeted benchmark like WebXPRT, if the workloads are so heavy that most devices can’t handle them or so light that most devices complete them without being taxed, the results will be of little use for helping buyers evaluating systems and making purchasing decisions, OEM labs, and the tech press.

That’s why, with any new WebXPRT workload, we look for a sweet spot with respect to how computationally demanding it will be. We want it to run on a wide range of devices—from low-end devices that are several years old to brand-new high-end devices, and everything in between. We also want users to see a wide range of workload scores and resulting overall scores that accurately reflect the experiences those systems deliver, so they can easily grasp the different performance capabilities of the devices under test.

Will results be consistent and easily replicated?

Finally, WebXPRT workloads should produce scores that consistently fall within an acceptable margin of error and are easily replicated with additional testing or comparable gear. Some web technologies are very sensitive to uncontrollable or unpredictable variables, such as internet speed. A workload that measures one of those technologies would be unlikely to produce results that are consistent and easily replicated.

We hope this post will be useful if you’re thinking about potential new workloads that you’d like to see in WebXPRT. If you have any general thoughts about browser performance testing or specific workload ideas that you’d like us to consider, please let us know.

Justin

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

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

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

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

Accessing the WebXPRT 4 source code

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

Check out the other XPRTs:

Forgot your password?