For applications such as high frequency trading (HFT), search engines and telecommunications, it is essential that latency can be minimized. My previous article Optimizing Computer Applications for Latency, looked at the architecture choices that support a low latency application. This article builds on that to show how latency can be measured and tuned within the application software.
Machine learning applications are very compute intensive by their nature. That is why optimization for performance is quite important for them. One of the most popular libraries, Tensorflow*, already has an embedded timeline feature that helps understand which parts of the computational graph are causing bottlenecks but it lacks some advanced features like an architectural analysis.
To get started using the SAP* IoT Starter Kit, you must first setup your account, by following the "Getting Started in the Cloud" steps listed at https://github.com/SAP/iot-starterkit#getting-started-in-the-cloud
SAP Cloud Platform* Developer signup
AT&T* M2X* IoT initial signup
1. Create an account on https://m2x.att.com, if you do not yet have one. If you already have an account, you can skip directly to "Adding your first device" below.
2. Fill out your information when signing up.
Download tutorial code and GPU compute samples media data:
IWOCL_2017_Tutorial.tgz (110.95 MB)
yuv_samples.tgz (27.94 MB)
Based on an IWOCL 2017 tutorial Unlock Intel GPUs for High Performance Compute, Media and Computer Vision.