BenchmarkXPRT Blog banner

Tag Archives: WebAssembly

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

Justin Greene
By Justin Greene
on September 19, 2024

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

Posted in AI, benchmark, Benchmarking, BenchmarkXPRT, browser performance, Browser-based benchmarks, Chrome, Chromium, Collaborative benchmark development, Cross-platform benchmarks, Future of performance evaluation, GenAI, Google, Google Chrome, GPU, HTML5, inference, JavaScript, large language models, Machine learning, Microsoft, Microsoft Edge, NPU, Performance benchmarking, Wasm, Web AI, web API, WebAssembly, WebXPRT, WebXPRT 4 | Also tagged , , , , , , , , , , , , , , , , ,

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

Justin Greene
By Justin Greene
on September 5, 2024

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

Posted in AI, benchmark, Benchmarking, BenchmarkXPRT, BenchmarkXPRT development community, browser performance, Browser-based benchmarks, Collaborative benchmark development, computer vision, Cross-platform benchmarks, face detection, Future of performance evaluation, Google, GPU, image classification, inference, JavaScript, Machine learning, MediaPipe, Microsoft, NPU, on-device AI, ONNX Runtime Web, Open Source, OpenAI, Performance benchmarking, PyTorch, TensorFlow, Transformers.js, Video, Web AI, Web-based testing, WebAssembly, WebGPU, WebXPRT, WebXPRT 4 | Also tagged , , , , , , , , , , , , , , , ,

Making progress with WebXPRT 4 in iOS 17

Justin Greene
By Justin Greene
on October 12, 2023

In recent blog posts, we discussed an issue that we encountered when attempting to run WebXPRT 4 on iOS 17 devices. If you missed those posts, you can find more details about the nature of the problem here. In short, the issue is that the Encrypt Notes and OCR scan subtest in WebXPRT 4 gets stuck when the Tesseract.js Optical Character Recognition (OCR) engine attempts to scan a shopping receipt. We’ve verified that the issue occurs on devices running iOS 17, iPadOS 17, and macOS Sonoma with Safari 17.

After a good bit of troubleshooting and research to try and identify the cause of the problem, we decided to build an updated version of WebXPRT 4 that uses a newer version of Tesseract for the OCR task. Aside from updating Tesseract in the new build, we aimed to change as little as possible. To try and maximize continuity, we’re still using the original input image for the receipt scanning task, and we decided to stick with using the WASM library instead of a WASM-SIMD library. Aside from a new version of tesseract.js, WebXPRT 4 version number updates, and updated documentation where necessary, all other aspects of WebXPRT 4 will remain the same.

We’re currently testing a candidate build of this new version on a wide array of devices. The results so far seem promising, but we want to complete our due diligence and make sure this is the best approach to solving the problem. We know that OEM labs and tech reviewers put a lot of time and effort into compiling databases of results, so we hope to provide a solution that minimizes results disruption and inconvenience for WebXPRT 4 users. Ideally, folks would be able to integrate scores from the new build without any questions or confusion about comparability.

We don’t yet have an exact release date for a new WebXPRT 4 build, but we can say that we’re shooting for the end of October. We appreciate everyone’s patience as we work towards the best possible solution. If you have any questions or concerns about an updated version of WebXPRT 4, please let us know.

Justin

Posted in benchmark, Benchmark metrics, browser performance, Browser-based benchmarks, Performance benchmarking, results, WebAssembly, WebXPRT, WebXPRT 4 | Also tagged , , , , , , , , ,

Exploring the XPRT white paper library

Justin Greene
By Justin Greene
on July 20, 2023

As part of our commitment to publishing reliable, unbiased benchmarks, we strive to make the XPRT development process as transparent as possible. In the technology assessment industry, it’s not unusual for people to claim that any given benchmark contains hidden biases, so we take preemptive steps to address this issue by publishing XPRT benchmark source code, detailed system disclosures and test methodologies, and in-depth white papers. Today, we’re focusing on the XPRT white paper library.

The XPRT white paper library currently contains 21 white papers that we’ve published over the last 12 years. We started publishing white papers to provide XPRT users with more information about how we design our benchmarks, why we make certain development decisions, and how the benchmarks work. If you have questions about any aspect of one of the XPRT benchmarks, the white paper library is a great place to find some answers.

For example, the Exploring WebXPRT 4 white paper describes the design and structure of WebXPRT 4, including detailed information about the benchmark’s harness, HTML5 and WebAssembly (WASM) capability checks, and the structure of the performance test workloads. It also includes explanations of the benchmark’s scoring methodology, how to automate tests, and how to submit results for publication.

The companion WebXPRT 4 results calculation white paper explains the formulas that WebXPRT 4 uses to calculate the individual workload scenario scores and overall score, provides an overview of the statistical techniques WebXPRT uses to translate raw timings into scores, and explains the benchmark’s confidence interval and how it differs from typical benchmark variability. To supplement the white paper’s discussion of the results calculation process, we published a results calculation spreadsheet that shows the raw data from a sample test run and reproduces the exact calculations WebXPRT uses to produce test scores.

We hope that the XPRT white paper library will prove to be a useful resource for you. If you have questions about any of our white papers, or suggestions for topics that you’d like us to cover in possible future white papers, please let us know!

Justin

Posted in benchmark, Benchmarking, BenchmarkXPRT, BenchmarkXPRT development community, HTML5, WebAssembly, WebXPRT, WebXPRT 4, White papers | Also tagged , , , , , ,

Celebrating 10 years of WebXPRT!

Justin Greene
By Justin Greene
on March 30, 2023

We’re excited to announce that it’s been 10 years since the initial launch of WebXPRT! In early 2013, we introduced WebXPRT as a unique browser performance benchmark in a market space that was already crowded with a variety of specialized measurement tools. Our goal was to offer a benchmark that could compare the performance of almost any web-enabled device, using scenarios created to mirror real-world tasks. We wanted it to be a free, easily accessible, easy-to-run, useful, and appealing testing option for OEM labs, vendors, and the tech press.

When we look back on the last 10 years of WebXPRT, we can’t help but conclude that our efforts have been successful. Since those early days, the WebXPRT market presence has grown from humble beginnings into a worldwide industry standard. Hundreds of tech press publications have used WebXPRT in thousands of articles and reviews, and testers have now run the benchmark well over 1.1 million times.

Below, I’ve listed some of the WebXPRT team’s accomplishments over the last decade. If you’ve been following WebXPRT from the beginning, this may all be familiar, but if you’re new to the  community, it may be interesting to see some of the steps that contributed to making WebXPRT what it is today.

In future blog posts, we’ll look at how the number of WebXPRT runs has grown over time, and how WebXPRT use has grown among OEMs, vendors, and the tech press worldwide. Do you have any thoughts that you’d like to share from your WebXPRT testing experience? If so, let us know!

Justin

Posted in benchmark, Benchmarking, BenchmarkXPRT, Browser-based benchmarks, Cross-platform benchmarks, German, History of benchmarking, JavaScript, Performance benchmarking, results, Simplified Chinese, tech press, WebAssembly, WebXPRT, WebXPRT 2013, WebXPRT 2015, WebXPRT 3, WebXPRT 4, WebXPRT Processor Comparison Chart, White papers | Also tagged , , , , , , , , , , , ,

The Exploring WebXPRT 4 white paper is now available

Justin Greene
By Justin Greene
on September 1, 2022

This week, we published the Exploring WebXPRT 4 white paper. It describes the design and structure of WebXPRT 4, including detailed information about the benchmark’s harness, HTML5 and WebAssembly (WASM) capability checks, and changes we’ve made to the structure of the performance test workloads. We explain the benchmark’s scoring methodology, how to automate tests, and how to submit results for publication. The white paper also includes information about the third-party functions and libraries that WebXPRT 4 uses during the HTML5 and WASM capability checks and performance workloads.

The Exploring WebXPRT 4 white paper promotes the high level of transparency and disclosure that is a core value of the BenchmarkXPRT Development Community. We’ve always believed that transparency builds trust, and trust is essential for a healthy benchmarking community. That’s why we involve community members in the benchmark development process and disclose how we build our benchmarks and how they work.

You can find the paper on WebXPRT.com and our XPRT white papers page. If you have any questions about WebXPRT 4, please let us know, and be sure to check out our other XPRT white papers.

Justin

Posted in Automation, benchmark, Benchmarking, BenchmarkXPRT, BenchmarkXPRT development community, Performance benchmarking, results, results submission, WebAssembly, WebXPRT, WebXPRT 3, WebXPRT 4, White papers | Also 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