Like and Subscribe! New Windows on Snapdragon Development Videos

Sunday 2/4/24 01:00am
|
Posted By Morris Novello
  • Up0
  • Down0

Snapdragon and Qualcomm branded products are products of
Qualcomm Technologies, Inc. and/or its subsidiaries.

Our Qualcomm Developer Network YouTube channel continues growing as a valuable resource for development videos. Recently, we added several videos to the channel’s Windows on Snapdragon (WoS) playlist for Windows app developers:

  1. Building on Windows on Snapdragon: 5 Reasons to Develop an App on WoS
  2. Building on Windows on Snapdragon: Power of Artificial Intelligence on WoS
  3. Building on Windows on Snapdragon: Introduction to Snapdragon Profiler
  4. Building on Windows on Snapdragon: Snapdragon LLVM for WoS

Let’s take a quick look at what each video has to offer.

1. Building on Windows on Snapdragon: 5 Reasons to Develop an App on WoS


In this video, Dileep Karpur, Staff Product Manager at Qualcomm Technologies, Inc. (QTI), explains how you can take advantage of Windows on Snapdragon to boost your Windows app’s performance and accelerate your AI workloads. He covers five key categories of benefits and capabilities that make the platform a standout in the world of Windows software development:

  1. Multiple powerful CPU cores and advanced GPUs for apps and games.
  2. Power efficiency and long battery life through heterogeneous computing.
  3. Dedicated AI cores for hardware-accelerated inference and support for popular ML frameworks.
  4. Growing ecosystem of diverse devices. From laptops and two-in-one devices to Windows Dev Kit 2023, developers and end users have more choices than ever before.
  5. Developer support with Qualcomm’s Technologies’ commitment to growing our developer support channels.

2. Building on Windows on Snapdragon: Power of Artificial Intelligence on WoS


In this video, Felix Baum, Senior Director of Product Management at QTI joins Dileep to discuss Qualcomm Technologies’ hardware and software solutions for AI.

Felix shares the possibilities that ML – notably generative AI – is creating for developers to take apps to the next level of end-user productivity. He notes that on-device or “edge ai” is essential for portable, cost-effective, secure, and powerful intelligence without cloud servers or even internet connectivity.

He then covers the hardware capabilities of Snapdragon technology, most notably its Qualcomm Hexagon NPU , and the Qualcomm AI Stack that enables developers to build ML models once and deploy them across Qualcomm Technologies’ range of Snapdragon SoCs. The Qualcomm AI Engine Direct SDK and the role of AIMET in optimizing ML models, are highlighted along with some key learning resources where you can find out more.

3. Building on Windows on Snapdragon: Snapdragon LLVM for WoS


For general development tools, Zhaoshi Zheng, Staff Engineer, Qualcomm Innovation Center, Inc. reviews Qualcomm Technologies’ LLVM C/C++ compiler for Windows on Snapdragon.

Based on the open-source LLVM compiler, our fork supports upstream features like pragmas, security features, and exception handling. Our internal developers work hard to upstream features developed in-house, to keep the fork and open-source codebase aligned as much as possible.

Zhaoshi covers performance gains from using Qualcomm Technologies’ LLVM in areas like media encoding/decoding and image processing, thanks to Snapdragon-specific performance optimizations.

Finally, Zhaoshi demonstrates how to obtain and install Qualcomm Technologies’ LLVM compiler for Windows 11 on Arm® architecture integrate it into Visual Studio, and use it to compile a simple “hello world “ app.

4. Building on Windows on Snapdragon: Introduction to Snapdragon Profiler


Continuing with general development tools, Swapnil Raut, Sr. Staff Engineer, QTI introduces Snapdragon Profiler – a tool for analyzing app performance on Snapdragon – now available for analyzing apps with Windows on Snapdragon.

Swapnil starts with an overview of how client and target Windows on Snapdragon apps communicate with each other. He then covers installation of the tool and connecting a client with a target, followed by a how-to on performing analysis. This includes a deeper dive into the tool’s real-time profiling features and trace functionality. Here, you’ll learn how to start a session and verify a connection, along with basic connection troubleshooting steps.

Swapnil then explores how to use real-time mode to visually analyze system-wide behavior (e.g., cache hits, throughput, etc.), and trace capture to view metrics (e.g., clocks, shader info, etc.) for graphics libraries like DirectX.

We hope you enjoy these videos and that they help you develop your apps for Windows on Snapdragon.

You can view our complete Windows on Snapdragon playlist here, and as always – don’t forget to like and subscribe! To start building your apps today, check Windows on Snapdragon developer hub to get more information and download the tools.

Snapdragon and Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. AIMET is a product of Qualcomm Innovation Center, Inc. Arm is a registered trademark of Arm Limited (or its subsidiaries or affiliates) in the US and/or elsewhere.