Back to All
Developer Blog

Recap and on demand sessions: Snapdragon Game Studios Developer Forum at GDC 2026

Sign up for Developer monthly newsletter-image

Sign up for Developer monthly newsletter

Join thousands of developers around the globe who receive latest news and updates from our monthly curated newsletter.

Sign up
Come for support, stay for the community-image

Come for support, stay for the community

Get support from experts, connect with like-minded developers, and access exclusive virtual events.

Join Developer Discord

At GDC 2026, the Snapdragon Game Studios team brought developers and engineers together for a full day of technical talks and partner case studies focused on high‑performance gaming across mobile, PC, and beyond. Developers can now watch the recorded sessions on demand.

TL;DR — what you’ll get from these sessions (before you hit play)

This forum’s recordings cluster into three practical themes:

1.     Sustained performance under power constraints (memory and bandwidth efficiency on mobile).

2.     Enginelevel mobile optimisation (how UE5 pipelines can be adapted to mobile GPU realities).

3.     Ondevice AI and neural rendering (production‑oriented AI workflows: ASR/LLMs/TTS; plus neural upscaling / frame generation).

If you only have time for one session, pick based on your role:

  • Graphics/engine programmers (mobile): start with Infinity Nikki + Adreno High Performance Memory.

  • UE5 rendering engineers: start with Neverness to Everness (UE5 Mobile).

  • Gameplay/AI engineers: start with Snapdragon Game AI SDK.

  • PC porting/performance engineers: start with Kingdom Come: Deliverance II on Windows on Snapdragon
Snapdragon Game Studios team at GDC 2026
Snapdragon Game Studios team at GDC 2026

Ondemand sessions (and what you will learn)

Faster Frames, Lower Power: How Infinity Nikki Leverages Adreno High Performance Memory

What this session is about (in plain terms): Memory access is a major power cost in modern mobile games, and this talk focuses on how Adreno High Performance Memory can reduce energy use while improving rendering throughput.

You’ll learn:

  • What Adreno High Performance Memory is designed to do (fast, power‑efficient embedded memory) and why it matters for sustained performance.

  • How to access and use it via Vulkan API extensions, with recommended integration strategies and best practices.

  • A reference implementation context in Unreal Engine 5, plus a partner example from Infold Games on Infinity Nikki.

Watch the session recording

UE5 Mobile, Unleashed on Snapdragon: How We Turbocharged Neverness to Everness

What this session is about: A deep dive into optimising a UE5 mobile title on Snapdragon—specifically aligning UE5’s mobile rendering pipeline with Adreno GPU architecture for efficiency and scalability.

You’ll learn:

  • Approaches to improve tile‑based rendering efficiency and reduce bandwidth pressure in a high‑fidelity UE5 mobile game.

  • Techniques and topics explicitly called out: Adreno Tile Memory Heap integration, render‑pass optimisation, and discussion of performance results.

  • Advanced Snapdragon technologies referenced in the session description: Adreno Frame Motion Engine 2.0 (AFME2), Snapdragon Game Super Resolution 2 (SGSR2), and Snapdragon Adaptive Game Configuration (SAGC)—positioned as system/GPU‑aware strategies for frame stability, scalability, and power efficiency.

Watch the session recording

Game AI SDK presentation
Game AI SDK presentation

NextGeneration InGame AI Experiences: Snapdragon Game AI SDK

What this session is about: A developer‑focused toolkit intended to make ondevice AI more approachable for game teams—covering building blocks like ASR, LLMs, and TTS for in‑game interactions.

You’ll learn (from the session description + the public video description):

  • How to enable richer gameplay with Automatic Speech Recognition, Large Language Models, and TexttoSpeech for AI‑driven NPC interactions, with emphasis on power efficiency and Snapdragon NPU performance.

  • AI NPCs / teammates / coaches / companions, plus running LLMs/ASR/TTS locally using CPU/GPU/Hexagon NPU, and engine‑friendly workflows (including Unreal plugins).

  • Hybrid edge + cloud strategies for scalable game AI.

Speaker: Andy Michel, PhD (Qualcomm Technologies).

Watch the session recording

Snapdragon, Honor of Kings, and Tencent GVoice: OnDevice AI ASR for Immersive Voice Experiences

What this session is about: A partner example of deploying an ondevice automatic speech recognition (ASR) model for gaming, powered by Qualcomm Hexagon NPU, to deliver real‑time speech‑to‑text in complex in‑game scenarios.

You’ll learn:

Benefits of on‑device ASR: lower latency, high recognition accuracy, and improved power efficiency for smoother player communication.

  • Deep integration between Snapdragon platform and Tencent’s GVoice speech tech, as groundwork for real‑time interaction between humans and AI.

Watch the session recording

Neural Super Resolution and Frame Generation for Snapdragon Mobile Devices

What this session is about: An overview of Qualcomm’s upcoming AI‑based frame upscaling / frame generation approach, including benefits, integration into a game engine, and expected results.

You’ll learn:

  • What AI Frame Fusion technology is, why it matters, and how to integrate it into an engine.

Watch the session recording

Kingdom Come: Deliverance II — Optimising Performance for Windows on Snapdragon

What this session is about: Practical guidance on maximising game performance on Windows on Snapdragon, including why x64 emulation overhead can leave performance on the table and how a native port captures the full benefits.

You’ll learn:

  • How porting to Windows on Snapdragon enables native runtime performance, plus a real‑world case study on the porting process for Kingdom Come: Deliverance II.

Watch the session recording

Mobile Development Best Practices: Delta Force Mobile

What this session is about: A shipping‑oriented talk on the trade‑offs and workflows involved in bringing high‑quality visuals to mobile while managing complex PC assets—covering pipeline, memory, and CPU/GPU/bandwidth bottlenecks.

You’ll learn:

  • Asset pipeline management, memory usage, and solutions for CPU/GPU/memory/bandwidth bottlenecks when optimising high‑complexity scenes for mobile.

  • Resource recomposition pipeline solutions, CPU/memory management, GPU strategies for graphics‑intensive titles, and approaches to bandwidth efficiency.

Watch the session recording

Keep exploring

You can find more resources and community entry points—including the developer forum, YouTube channel, GitHub community, and Discord—on the Snapdragon Game Studios hub.

Subscribe for news and updates on Snapdragon's game developer solutions.

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries ("Qualcomm"). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.

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

About the Author
Steve  Augustine
Steve AugustineProduct Manager, Staff at Qualcomm Technologies, Inc.
Qualcomm relentlessly innovates to deliver intelligent computing everywhere, helping the world tackle some of its most important challenges. Our leading-edge AI, high performance, low-power computing, and unrivaled connectivity deliver proven solutions that transform major industries. At Qualcomm, we are engineering human progress.

Stay connected

Get the latest Qualcomm and industry information delivered to your inbox.

Subscribe
Manage your subscription

© Qualcomm Technologies, Inc. and/or its affiliated companies.

Snapdragon and Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. Qualcomm patented technologies are licensed by Qualcomm Incorporated.

Note: Certain services and materials may require you to accept additional terms and conditions before accessing or using those items.

References to "Qualcomm" may mean Qualcomm Incorporated, or subsidiaries or business units within the Qualcomm corporate structure, as applicable.

Qualcomm Incorporated includes our licensing business, QTL, and the vast majority of our patent portfolio. Qualcomm Technologies, Inc., a subsidiary of Qualcomm Incorporated, operates, along with its subsidiaries, substantially all of our engineering, research and development functions, and substantially all of our products and services businesses, including our QCT semiconductor business.

Materials that are as of a specific date, including but not limited to press releases, presentations, blog posts and webcasts, may have been superseded by subsequent events or disclosures.

Nothing in these materials is an offer to sell or license any of the services or materials referenced herein.