Category: Cross-platform benchmarks
News on AIXPRT development
Improvements to the AIXPRT results table
Over the last few weeks, we’ve gotten great feedback about the kinds of data points people are looking for in AIXPRT results, as well as suggestions for how to improve the AIXPRT results viewer. To make it easier for visitors to find what they’re looking for, we’ve made a number of changes:
- You can now filter results in categories such as framework, target hardware, batch size, and precision, and can designate minimum throughput and maximum latency scores. When you select a value from a drop-down menu or enter text, the results change immediately to reflect the filter.
- You can search for variables such as processor vendor or processor speed.
- The viewer displays eight results per page by default and lets you change this to 16, 48, or Show all.
The following features of the viewer, which have been present previously, can help you to navigate more efficiently:
- Click the tabs at the top of the table to switch from ResNet-50 network results to SSD-MobileNet network results.
- Click the header of any column to sort the data on that variable. One click sorts A-Z and two clicks sort Z-A.
- Click the link in the Source column to visit a detailed page on that result. The page contains additional test configuration and system hardware information and lets you download results files.
We hope these changes will improve the utility of the results table. We’ll continue to add features to improve the experience. If you have any suggestions, please let us know!
Justin
AIXPRT Community Preview 2 is almost here!
In last week’s blog, we predicted that the second AIXPRT Community Preview (CP2) would be ready for release later this month. Since then, the development process has accelerated, and we now expect to release CP2 as early as tomorrow, May 10.
Those who have access to the existing AIXPRT Community Preview GitHub repository will be able to access CP2 the same way as before. In addition to making the build available on GitHub, we’ll also post CP2 on an AIXPRT tab in the XPRT Members’ Area (login required). If you don’t have a BenchmarkXPRT Development Community membership, please contact us and we’ll help you register.
Testing with AIXPRT CP2 in Ubuntu will be the same as with the first CP, and none of the CP2 changes will affect results. In Windows, testers will be able to use OpenVINO to target a system’s CPU and GPU, and TensorFlow to target CPUs. We’re still investigating ways to support TensorFlow GPU and TensorFlow-TensorRT testing in Windows.
We’re also continuing to work on the improvements to the AIXPRT results viewer that we mentioned last week. We won’t be able to implement all of the changes by tomorrow, but rather than waiting until we’re finished, we’ll be rolling out improvements as they become ready.
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.
Justin
An update on AIXPRT development
It’s been almost two months since the AIXPRT Community Preview went live, and we want to provide folks with a quick update. Community Preview periods for the XPRTs generally last about a month. Because of the complexity of AIXPRT and some of the feedback we’ve received, we plan to release a second AIXPRT Community Preview (CP2) later this month.
One of the biggest additions in CP2 will be the ability to run AIXPRT on Windows. AIXPRT currently requires test systems to run Ubuntu 16.04 LTS. This is fine for testers accustomed to Linux environments, but presents obstacles for those who want to test in a traditional Windows environment. We will not be changing the tests themselves, so this update will not influence existing results from Ubuntu. We plan to make CP2 available for download from the BenchmarkXPRT website for people who don’t wish to deal with GitHub.
Also, after speaking with testers and learning more about the kinds of data points people are looking for in AIXPRT results, we’ve decided to make significant adjustments to the AIXPRT results viewer. To make it easier for visitors to find what they’re looking for, we’ll add filters for key categories such as batch size, toolkit, and latency percentile (e.g., 50th, 90th, 99th), among others. We’ll also allow users to set desired ranges for metrics such as throughput and latency.
Finally, we’re adding a demo mode that displays some images and other information on the screen while a test is running to give users a better idea what is happening. While we haven’t seen results change while running in demo mode, users should not publish demo results or use them for comparison.
We hope to release CP2 in the second half of May and a GA version in mid-June. However, this project has more uncertainties than we usually encounter with the XPRTs, so that timeline could easily change.
We’ll continue to keep everyone up to date with AIXPRT news here in the blog. As always, we appreciate your suggestions. If you have any questions or comments about AIXPRT, please let us know.
Bill
A new playing field for WebXPRT
WebXPRT is one of the go-to benchmarks for evaluating browser performance, so we’re always interested in browser development news. Recently, Microsoft created a development channel where anyone can download early versions of an all-new Microsoft Edge browser. Unlike previous versions of Edge, Microsoft constructed the new browser using the Chromium open-source project, the same foundation underlying the Google Chrome browser and Chrome OS.
One interesting aspect of the new Edge development strategy is the changes that Microsoft is making to more than 50 services that Chromium has included. If you use Chrome daily, you’ve likely become accustomed to certain built-in services such as ad block, spellcheck, translate, maps integration, and form fill, among many others. While each of these is useful, a large number of background services running simultaneously can slow browsing and sap battery life. In the new Edge, Microsoft is either reworking each service or removing it altogether, with the hope of winning users by providing a cleaner, faster, and more power-efficient experience. You can read more about Microsoft’s goals for the new project on the Microsoft Edge Insider site.
As we’ve discussed before, many factors contribute to the speed of a browsing experience and its WebXPRT score. It’s too early to know how the new Microsoft Edge will stack up against other browsers, but when the full version comes out of development, you can be sure that we’ll be publishing some comparison scores. I’ve installed the Dev Channel version of Edge on my personal machine and run WebXPRT 3. While I can’t publish the scores from this early version, I can tell you that the results were interesting. Have you run WebXPRT 3 on the new Microsoft Edge? How do you think it compares to competitors? We’d love to hear your thoughts.
Justin
An update on the AIXPRT Request for Comments preview
As we approach the end of the original feedback window for the AIXPRT Request for Comments preview build, we want to update folks on the status of the project and what to expect in the coming weeks.
First, thanks to those who’ve downloaded the AIXPRT OpenVINO package and sent in their questions and comments. We value your feedback, and it’s instrumental in making AIXPRT a better tool. We’re currently working through some issues with the TensorFlow and TensorRT packages, and hope to add support for those to the RFC preview build repository very soon.
We’re also hoping to have a full-fledged community preview (CP) ready in mid to late February. Like our other community previews, the AIXPRT CP would be solid enough to allow folks to start quoting numbers. We typically make our benchmarks available to the general public four to six weeks after the community preview period begins, so if that schedule holds, it would place the public AIXPRT release around the end of March.
In light of the schedule described above, you still have time to gain access to the AIXPRT RFC preview build and give your feedback, so let us know if you’d like to check it out. The installation and testing process can take less than an hour, but getting everything properly set up can take a few tries. We are hard at work trying to make that process more straightforward. We welcome your input on all aspects of the benchmark, including workloads, ease of use, metrics, scores, and reporting.
Thanks for your help!
Justin
Check out the other XPRTs:
