In the past year, we saw tremendous advancements for software developers in such areas as artificial intelligence (AI), Internet of Things (IoT), pre-silicon readiness, open source technology, content development, networking, gaming and more. To help developers take advantage of these advancements on Intel® architecture, Intel® Evangelists published more than 50 blogs on the Intel® Developer Zone. Following are the top five blogs that were the most popular for you, our readers, in 2018:
5. Accelerate Your Time to Market
Getting products to market faster is critical for competitive and business success. In June, Michael Greene, vice president and general manager of the Intel System Technologies and Optimization Division, posted a blog on Simulation throughout the Product Life Cycle Accelerates Time to Market. In the blog, he explored the advantages of using Intel’s simulation technology when designing systems on Intel® silicon. Simulation helps drive the product life cycle continuum by connecting the dots between system exploration, software development and validation. Three Intel technologies highlighted included: Intel® CoFluent™ technology for optimizing system design, Intel® Docea™ technology for testing power/thermal performance, and Simics® simulation technology for simulating hardware platforms to support software development and validation.
Learn more about what Intel offers for optimizing system design, testing power/thermal performance, and simulating hardware platforms to support software development and validation.
4. Manage CPU Performance for Containerized Workloads
Enabling better placement of workloads in the Kubernetes* is an emerging challenge for today’s open source developers. Last summer, Intel worked in partnership with the open source community to develop a beta feature in Kubernetes that enables better CPU performance management for containerized workloads and services. Intel Open Source Technology Center experts Balaji Subramaniam and Connor Doyle explain how CPU Manager can provide better performance isolation by allocating CPUs for exclusive-use for workloads facing CPU-intensive challenges in the August post, CPU Manager, a Beta Feature in Kubernetes for Performance-Sensitive Applications.
The authors ran experiments on an Intel® Xeon® processor-based dual-socket compute node with 48 logical CPUs (24 physical cores each with 2-way hyperthreading).
Learn more about their approach and the resulting test results.
3. Scale Data Analytics & AI with Open Source Software
In September, Ziya Ma, Intel vice president and director of Big Data Technologies, posted a new blog entitled Derive Value from Data Analytics & AI at Scale with Open Source Software In it, she discussed why companies have started transitioning from big data to fast data, which. She explained that data in motion provides the ability to learn continuously, make decisions, and enables people to take action as soon as data arrives, typically in milliseconds.
Ma describes how open source technologies, such as Apache Spark*, BigDL and Analytics Zoo, are bringing greater capacity and performance to advanced data analytics and why Intel® Optane™ DC persistent memory will be a real game changer for fast data.
Learn more about how your organization can use existing infrastructure as an AI foundation, reducing hardware cost and the total time to solution.
2. Ignite Innovation from the Edge to the Cloud
The latest Intel-optimized Microsoft Azure* cloud and Windows* data center environments were on display at the Microsoft Ignite 2018 in September. Andy Vargas, vice president and general manager of Intel’s Microsoft Technology Center, highlighted two of the many Intel demos for advancing artificial intelligence (AI) at the edge and IT modernization for the data center in his blog, Intel Innovations for the Data Center & Edge-to-Cloud Solutions.
Intel’s demo on Anomaly Detection showcased the acceleration of deep learning in AI from device to cloud using the power of Intel® processors, accelerators and the newest developer tool suite, the Intel® Distribution of OpenVINO™ toolkit, to advance such tasks as fraud detection, network intrusion, finding abnormal data clusters and checking values entered into a system. The solution featured Microsoft Azure* IoT Edge in containers for deploying apps to devices.
The IT Modernization with SQL Server* 2017 demo showcased performance improvements for data warehousing queries when using Intel® Xeon® Platinum 8180 processors, running SQL Server* 2017 RTM on Windows* Server 2019. The demo compared runtimes and performance of data simultaneously running the same set of queries on old and new hardware and software configurations.
Learn more about the latest innovations Intel is collaboratively delivering with Microsoft for the data center, cloud, edge and more.
1. Build Privacy into your Computer Vision Solutions
The honor of “Most-Read Intel Software Blog of 2018” goes to Computer Vision Solutions and Privacy-by-Design.
Last July, Charlotte Dryden, Intel’s director of Visual Computing Developer Solutions, looked at the benefits in safety, security, convenience and efficiency computer vision offers in the areas of safety, security, convenience and efficiency. She asked, “With cameras collecting our images in an always-connected, digital world, how can we manage the benefits with the risks to our privacy?” To answer that, she explored best practices for developing computer vision solutions with AI that enable consumers to have control over their privacy and options to limit image data from being shared.
Learn how Intel is working with hardware and software engineers, data scientists and developers in the computer vision ecosystem to design solutions that allow consumers to define their own terms for data privacy.