PT-Logo
Forgot your password?
BenchmarkXPRT Blog banner

Category: AI

Progress updates: HDXPRT 4 and AIXPRT

Over the next few weeks, we’re expecting to publish both an updated HDXPRT 4 build and the AIXPRT public release (GA). Timelines may change as a result of development or testing issues, but we want to provide a brief update on where both projects stand.

HDXPRT 4

As we discussed last week, Adobe removed Photoshop Elements 2018, the application that HDXPRT 4 uses for the Edit Photos scenario, from their public download page. This means that new HDXPRT 4 testers are currently unable to successfully complete the benchmark installation process.

To fix the problem, we adapted HDXPRT 4’s Edit Photos scripts to use PSE 2020, and we hope to begin testing by the end of this week. We appreciate everyone’s patience as we put a solution in place, and we’ll publish the new build as soon as possible.

AIXPRT

We’re now in the third week of the AIXPRT Community Preview 3 (CP3) period, and we’re working on finalizing the AIXPRT GA installation packages for release. Because several of AIXPRT’s component toolkits release updates on a regular basis, it’s likely that we’ll need to update AIXPRT’s installation packages more frequently than we have with previous XPRT benchmarks. At the moment, we’re working to integrate and test recent updates to OpenVINO and TensorRT before GA.

As usual, we’ll keep you informed here in the blog. If you have any questions or comments about HDXPRT or AIXPRT, please let us know. We do value your feedback.

Justin

How to use alternate configuration files with AIXPRT

In last week’s AIXPRT Community Preview 3 announcement, we mentioned the new public GitHub repository that we’re using to publish AIXPRT-related information and resources. In addition to the installation readmes for each AIXPRT installation package, the repository contains a selection of alternative test config files that testers can use to quickly and easily change a test’s parameters.

As we discussed in previous blog entries about batch size, levels of precision, and number of concurrent instances, AIXPRT testers can adjust each of these key variables by editing the JSON file in the AIXPRT/Config directory. While the process is straightforward, editing each of the variables in a config file can take some time, and testers don’t always know the appropriate values for their system. To address both of these issues, we are offering a selection of alternative config files that testers can download and drop into the AIXPRT/Config directory.

In the GitHub repository, we’ve organized the available config files first by operating system (Linux_Ubuntu and Windows) and then by vendor (All, Intel, and NVIDIA). Within each section, testers will find preconfigured JSON files set up for several scenarios, such as running with multiple concurrent instances on a system’s CPU or GPU, running with FP32 precision instead of FP16, etc. The picture below shows the preconfigured files that are currently available for systems running Ubuntu on Intel hardware.

AIXPRT public repository snip 2

Because potential AIXPRT use cases cut across a wide range of hardware segments, including desktops, edge devices, and servers, not all AIXPRT workloads and configs will be applicable to each segment. As we move towards the AIXPRT GA, we’re working to find the best way to parse out these distinctions and communicate them to end users. In many cases, the ideal combination of test configuration variables remains an open question for ongoing research. However, we hope the alternative configuration files will help by giving testers a starting place.

If you experiment with an alternative test configuration file, please note that it should replace the existing default config file. If more than one config file is present, AIXPRT will run all the configurations and generate a separate result for each. More information about the config files and detailed instructions for how to handle the files are available in the EditConfig.md document in the public repository.

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

AIXPRT Community Preview 3 is here!

We’re happy to announce that the AIXPRT Community Preview 3 (CP3) is now available! As we discussed in last week’s blog, testers can expect three significant changes in AIXPRT CP3:

  • We updated support for the Ubuntu test packages from Ubuntu version 16.04 LTS to version 18.04 LTS.
  • We added TensorRT test packages for Windows and Ubuntu. Previously, AIXPRT testers could test only the TensorFlow variant of TensorRT. Now, they can use TensorRT to test systems with NVIDIA GPUs.
  • We added the Wide and Deep recommender system workload with the MXNet toolkit for Ubuntu systems.


To access AIXPRT CP3, click this access link and submit the brief information form unless you’ve already done so for CP2. You will then gain access to the AIXPRT community preview page. (If you’re not already a BenchmarkXPRT Development Community member, we’ll contact you with more information about your membership.)

On the community preview page, a download table displays the currently available AIXPRT CP3 test packages. Locate the operating system and toolkit you wish to test, and click the corresponding Download link. For detailed installation instructions and information on hardware and software requirements for each package, click the corresponding Readme link. Instead of providing installation guide PDFs as we did for CP2, we are now directing testers to a public GitHub repository. The repository contains the installation readmes for all the test packages, as well as a selection of alternative test configuration files. We’ll discuss the alternative configuration files in more detail in a future blog post.

Note: Those who have access to the existing AIXPRT GitHub repository will be able to access CP3 in the same way as previous versions.

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 a while since we last discussed the AIXPRT Community Preview 3 (CP3) release schedule, so we want to let everyone know where things stand. Testing for CP3 has taken longer than we predicted, but we believe we’re nearly ready for the release.

Testers can expect three significant changes in AIXPRT CP3. First, we updated support for the Ubuntu test packages. During the initial development phase of AIXPRT, Ubuntu version 16.04 LTS (Long Term Support) was the most current LTS version, but version 18.04 is now available.

Second, we have added TensorRT test packages for Windows and Ubuntu. Previously, AIXPRT testers could test only the TensorFlow variant of TensorRT. Now, they can use TensorRT to test systems with NVIDIA GPUs.

Third, we have added the Wide and Deep recommender system workload with the MXNet toolkit. Recommender systems are AI-based information-filtering tools that learn from end user input and behavior patterns and try to present them with optimized outputs that suit their needs and preferences. If you’ve used Netflix, YouTube, or Amazon accounts, you’ve encountered recommender systems that learn from your behavior.

Currently, the recommender system workload in AIXPRT CP3 is available for Ubuntu testing, but not for Windows. Recommender system inference workloads typically run on datacenter hardware, which tends to be Linux based. If enough community members are interested in running the MXNet/Wide and Deep test package on Windows, we can investigate what that would entail. If you’d like to see that option, please let us know.

As always, if you have any questions about the AIXPRT development process, feel free to ask!

Justin

Understanding concurrent instances in AIXPRT

Over the past few weeks, we’ve discussed several of the key configuration variables in AIXPRT, such as batch size and level of precision. Today, we’re discussing another key variable: number of concurrent instances. In the context of machine learning inference, this refers to how many instances of the network model (ResNet-50, SSD-MobileNet, etc.) the benchmark runs simultaneously.

By default, the toolkits in AIXPRT run one instance at a time and distribute the compute load according to the characteristics of the CPU or GPU under test, as well as any relevant optimizations or accelerators in the toolkit’s reference library. By setting the number of concurrent instances to a number greater than one, a tester can use multiple CPUs or GPUs to run multiple instances of a model at the same time, usually to increase throughput.

With multiple concurrent instances, a tester can leverage additional compute resources to potentially achieve higher throughput without sacrificing latency goals.

In the current version of AIXPRT, testers can run multiple concurrent instances in the OpenVINO, TensorFlow, and TensorRT toolkits. When AIXPRT Community Preview 3 becomes available, this option will extend to the MXNet toolkit. OpenVINO and TensorRT automatically allocate hardware for each instance and don’t let users make manual adjustments. TensorFlow and MXNet require users to manually bind instances to specific hardware. (Manual hardware allocation for multiple instances is more complicated than we can cover today, so we may devote a future blog entry to that topic.)

Setting the number of concurrent instances in AIXPRT

The screenshot below shows part of a sample config file (the same one we used when we discussed batch size and precision). The value in the “concurrent instances” row indicates how many concurrent instances will be operating during the test. In this example, the number is one. To change that value, a tester simply replaces it with the desired number and saves the changes.

Config_snip

If you have any questions or comments (about concurrent instances or anything else), please feel free to contact us.

Justin

Understanding the basics of AIXPRT precision settings

A few weeks ago, we discussed one of AIXPRT’s key configuration variables, batch size. Today, we’re discussing another key variable: the level of precision. In the context of machine learning (ML) inference, the level of precision refers to the computer number format (FP32, FP16, or INT8) representing the weights (parameters) a network model uses when performing the calculations necessary for inference tasks.

Higher levels of precision for inference tasks help decrease the number of false positives and false negatives, but they can increase the amount of time, memory bandwidth, and computational power necessary to achieve accurate results. Lower levels of precision typically (but not always) enable the model to process inputs more quickly while using less memory and processing power, but they can allow a degree of inaccuracy that is unacceptable for certain real-world applications.

For example, a high level of precision may be appropriate for computer vision applications in the medical field, where the benefits of hyper-accurate object detection and classification far outweigh the benefit of saving a few milliseconds. On the other hand, a low level of precision may work well for vision-based sensors in the security industry, where alert time is critical and monitors simply need to know if an animal or a human triggered a motion-activated camera.

FP32, FP16, and INT8

In AIXPRT, we can instruct the network models to use FP32, FP16, or INT8 levels of precision:

  • FP32 refers to single-precision (32-bit) floating point format, a number format that can represent an enormous range of values with a high degree of mathematical precision. Most CPUs and GPUs handle 32-bit floating point operations very efficiently, and many programs that use neural networks, including AIXPRT, use FP32 precision by default.
  • FP16 refers to half-precision (16-bit) floating point format, a number format that uses half the number of bits as FP32 to represent a model’s parameters. FP16 is a lower level of precision than FP32, but it still provides a great enough numerical range to successfully perform many inference tasks. FP16 often requires less time than FP32, and uses less memory.
  • INT8 refers to the 8-bit integer data type. INT8 data is better suited for certain types of calculations than floating point data, but it has a relatively small numeric range compared to FP16 or FP32. Depending on the model, INT8 precision can significantly improve latency and throughput, but there may be a loss of accuracy. INT8 precision does not always trade accuracy for speed, however. Researchers have shown that a process called quantization (i.e., approximating continuous values with discrete counterparts) can enable some networks, such as ResNet-50, to run INT8 precision without any significant loss of accuracy.

Configuring precision in AIXPRT

The screenshot below shows part of a sample config file, the same sample file we used for our batch size discussion. The value in the “precision” row indicates the precision setting. This test configuration would run tests using INT8. To change the precision, a tester simply replaces that value with “fp32” or “fp16” and saves the changes.

Config_snip

Note that while decreasing the precision from FP32 to FP16 or INT8 often results in larger throughput numbers and faster inference speeds overall, this is not always the case. Many other factors can affect ML performance, including (but not limited to) the complexity of the model, the presence of specific ML optimizations for the hardware under test, and any inherent limitations of the target CPU or GPU.

As with most AI-related topics, the details of model precision are extremely complex, and it’s a hot topic in cutting edge AI research. You don’t have to be an expert, however, to understand how changing the level of precision can affect AIXPRT test results. We hope that today’s discussion helped to make the basics of precision a little clearer. If you have any questions or comments, please feel free to contact us.

Justin

Check out the other XPRTs: