We’re happy to announce that the CloudXPRT results viewer is now live with results from the first few rounds of CloudXPRT
Preview testing we conducted in our lab. Here are some tips to help you to
navigate the viewer more efficiently:
Click the tabs at the top of the table to switch from Data analytics
workload results to Web microservices workload results.
Click the header of any column to sort the data on that
variable. Single click to sort A to Z and double-click to sort Z to A.
Click the link in the Source/details column to visit a detailed
page for that result, where you’ll find additional test configuration and
system hardware information and the option to download results files.
By default, the viewer displays eight results per page, which
you can change to 16, 48, or Show all.
The free-form search field above the table lets you filter for
variables such as cloud service or processor.
We’ll be adding more features, including expanded filtering and
sorting mechanisms, to the results viewer in the near future. We’re also
investigating ways to present multiple data points in a graph format, which
will allow visitors to examine performance behavior curves in conjunction with
factors such as concurrency and resource utilization.
We welcome your CloudXPRT results submissions! To learn about
the new submission and review process we’ll be using, take a look at last week’s blog.
If you have any questions or suggestions for ways that we can
improve the results viewer, please let us know!
A few weeks ago, we shared the general framework of the periodic results publication process we will use for CloudXPRT. Now that the CloudXPRT Preview is live, we’re ready to share more details about the results review group; the submission, review, and publication cycles; and the schedule for the first three months.
The results review group The CloudXPRT results review group will serve as a sanity check and a forum for comments on each month’s submissions. All registered BenchmarkXPRT Development Community members who wish to participate in the review process can join the group by contacting us via email. We’ll confirm receipt of your request and add you to the review group mailing list. Any non-members who would like to join the review group can contact us and we’ll help you become community members.
The submission, review, and publication cycle We will update the CloudXPRT results database once a month on a published schedule. While testers can submit results through the CloudXPRT results submission page at any time, two weeks prior to each publication date, we will close submissions for that review cycle. One week prior to each publication date, we will email details of that month’s submissions to the results review group, along with the deadline for sending post-publication feedback.
Schedule for the first three publication cycles We will publish results to the database on the last business day of each month and will close the submission window at 11:59 PM on the business day that falls two weeks earlier (with occasional adjustments for holidays). The schedule will be available at least six months in advance on CloudXPRT.com.
The schedule for the first three cycles is as follows:
July Submission deadline: Friday 7/17/20 Publication date: Friday 7/31/20 August Submission deadline: Monday 8/17/20 Publication date: Monday 8/31/20 September Submission deadline: Wednesday 9/16/20 Publication date: Wednesday 9/30/20
As a reminder, members of the tech press, vendors, and other testers are free to publish CloudXPRT results at any time. We may choose to add such results to our database on the monthly publication date, after first vetting them.
We look forward to reviewing the first batch of results! If you have any questions about CloudXPRT or the results submission or review process, let us know!
Earlier this month, we discussed
the possibility of using a periodic results submission process for CloudXPRT
instead of the traditional rolling publication process that we’ve used for the
other XPRTs. We’ve received some positive responses to the idea, and while
we’re still working out some details, we’re ready to share the general
framework of the process we’re planning to use.
We will establish
a results review group, which only official BenchmarkXPRT Development Community
members can join.
We will update
the CloudXPRT database with new results once a month, on a pre-published
schedule.
Two weeks before each
publication date, we will stop accepting submissions for consideration for
that review cycle.
One week before each
publication date, we will send an email to the results review group that
includes the details of that month’s submissions for review.
The results
review group will serve as a sanity check process and a forum for comments
on the month’s submissions, but we reserve the right of final approval for
publication.
We will not
restrict publishing results outside of the monthly review cadence, but we
will not automatically add those results to the results database.
We may add
externally published results to our database, but will do so only after
vetting, and only on the designated day each month.
Our goal is to
strike a balance between allowing the tech press, vendors, or other testers to
publish CloudXPRT results on their own schedule, and simultaneously building a curated
results database that OEMs or other parties can use to compete for the best
results.
We’ll share more
details about the review group, submission dates, and publications dates soon.
Do you have questions or comments about the new process? Let us
know what you think!
Testers who have started using the XPRT benchmarks recently
may not know about one of the free resources we offer. The XPRT results
database currently holds more than 2,400 test results from over 90 sources,
including major tech review publications around the world, OEMs, and
independent testers. It offers a wealth of current and historical performance
data across all the XPRT benchmarks and hundreds of devices.
We update the results database several times a week,
adding selected results from our own internal lab testing, end-of-test user
submissions, and reliable tech media sources. (After you run one of the XPRTs,
you can choose to submit the results, but they don’t automatically appear in
the database.)
Before adding a result, we evaluate whether the
score makes sense and is consistent with general expectations, which we can do
only when we have sufficient system information details. For that reason, we encourage
testers to disclose as much hardware and software information as possible when
publishing or submitting a result.
We encourage visitors to our site to explore the XPRT results database. There are three primary ways to do so. The first is by visiting the main BenchmarkXPRT results browser, which displays results entries for all of the XPRT benchmarks in chronological order (see the screenshot below). Users can narrow the results by selecting a benchmark from the drop-down menu and can type values, such as vendor or the name of a tech publication, into the free-form filter field. For results we produced in our lab, clicking “PT” in the Source column takes you to a page with additional disclosure information for the test system. For sources outside our lab, clicking the source name takes you to the original article or review that contains the result.
The second way to access our published results is by
visiting the results page for each individual XPRT benchmark. Go the page of
the benchmark you’re interested in, and look for the blue View Results button.
Clicking it takes you to a page that displays results for only that benchmark.
You can use the free-form filter on the page to filter those results, and can
use the Benchmarks drop-down menu to jump to the other individual XPRT results
pages.
The third way to view information in our results
database is with the WebXPRT Processor Comparison Chart.
When we publish a new WebXPRT result, the score automatically appears in the
processor comparison chart as well. For each processor, the chart shows a bar
representing the average score. Mousing over the bar displays a popup indicating
the number of WebXPRT results we currently have for that processor and clicking
the bar lets you view the results. You can change the number of results the
chart displays on each page, and use the drop-down menu to toggle back and
forth between the WebXPRT 3 and WebXPRT 2015 charts.
We hope you’ll take some time to browse the information in our results database. We welcome your feedback about what you’d like to see in the future and suggestions for improvement. Our database contains the XPRT scores that we’ve gathered, but we publish them as a resource for you. Let us know what you think!
Last
month, we provided an update
on the CloudXPRT development process and more information about the three workloads
that we’re including in the first build. We’d initially hoped to release the
build at the end of April, but several technical challenges have caused us to
push the timeline out a bit. We believe we’re very close to ready, and look
forward to posting a release announcement soon.
In
the meantime, we’d like to hear your thoughts about the CloudXPRT results publication
process. Traditionally, we’ve published XPRT results on our site on a rolling
basis. When we complete our own tests, receive results submissions from other
testers, or see results published in the tech media, we authenticate them and add
them to our site. This lets testers make their results public on their
timetable, as frequently as they want.
Some
major benchmark organizations use a different approach, and create a schedule
of periodic submission deadlines. After each deadline passes, they review the batch
of submissions they’ve received and publish all of them together on a single
later date. In some cases, they release results only two or three times per
year. This process offers a high level of predictability. However, it can pose
significant scheduling obstacles for other testers, such as tech journalists
who want to publish their results in an upcoming device review and need official
results to back up their claims.
We’d like to hear what you think about the different approaches to results submission and publication that you’ve encountered. Are there aspects of the XPRT approach that you like? Are there things we should change? Should we consider periodic results submission deadlines and publication dates for CloudXPRT? Let us know what you think!
Last week, we discussed the changes we made to the AIXPRT Community Preview 2 (CP2) download page as part of our ongoing effort to make AIXPRT easier to use. This week, we want to discuss the basics of understanding AIXPRT results by talking about the numbers that really matter and how to access and read the actual results files.
To understand AIXPRT results at a high level, it’s important to revisit the core purpose of the benchmark. AIXPRT’s bundled toolkits measure inference latency (the speed of image processing) and throughput (the number of images processed in a given time period) for image recognition (ResNet-50) and object detection (SSD-MobileNet v1) tasks. Testers have the option of adjusting variables such as batch size (the number of input samples to process simultaneously) to try and achieve higher levels of throughput, but higher throughput can come at the expense of increased latency per task. In real-time or near real-time use cases such as performing image recognition on individual photos being captured by a camera, lower latency is important because it improves the user experience. In other cases, such as performing image recognition on a large library of photos, achieving higher throughput might be preferable; designating larger batch sizes or running concurrent instances might allow the overall workload to complete more quickly.
The dynamics of these performance tradeoffs ensure that there is no single good score for all machine learning scenarios. Some testers might prefer lower latency, while others would sacrifice latency to achieve the higher level of throughput that their use case demands.
Testers can find latency and throughput numbers for each completed run in a JSON results file in the AIXPRT/Results folder. The test also generates CSV results files that are in the same folder. The raw results files report values for each AI task configuration (e.g., ResNet-50, Batch1, on CPU). Parsing and consolidating the raw data can take some time, so we’re developing a results file parsing tool to make the job much easier.
The results parsing tool is currently available in the AIXPRT CP2 OpenVINO – Windows package, and we hope to make it available for more packages soon. Using the tool is as simple as running a single command, and detailed instructions for how to do so are in the AIXPRT OpenVINO on Windows user guide. The tool produces a summary (example below) that makes it easier to quickly identify relevant comparison points such as maximum throughput and minimum latency.
In addition to the summary, the tool displays the throughput and latency results for each AI task configuration tested by the benchmark. AIXPRT runs each AI task multiple times and reports the average inference throughput and corresponding latency percentiles.
We hope that this information helps to make it easier to understand AIXPRT results. If you have any questions or comments, please feel free to contact us.
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.
