Mobile AI Just Got Faster: What’s Coming for Developers on Arm

What if you could get a 6x performance boost for on-device AI with zero code changes? See how Arm's new SME2 instructions make it a reality for developers.

#1about 3 minutes

Exploring generative AI use cases on mobile devices

Generative AI on mobile enables powerful, local-first applications like group chat summarization and high-quality audio generation without an internet connection.

#2about 3 minutes

Why you should run AI workloads on the Arm CPU

The Arm CPU offers scalability, security, and an "optimize once, deploy everywhere" model, making it ideal for high-performance, low-latency AI applications.

#3about 2 minutes

Navigating the diverse mobile AI framework ecosystem

A wide range of open-source frameworks, each with unique strengths, are available for deploying AI models on Arm-powered mobile devices.

#4about 3 minutes

How the KleidiAI library unifies AI performance

The KleidiAI library provides highly optimized, low-level routines that integrate directly into popular AI frameworks to ensure the best performance on Arm CPUs.

#5about 3 minutes

A deep dive into the on-device AudioGen pipeline

The AudioGen pipeline runs locally by combining multiple models and processing steps, requiring data type flexibility like FP32 and FP16 for optimal quality.

#6about 2 minutes

Building a private, fully on-device smart assistant

Generative AI enables smart speakers to run entirely locally, combining speech-to-text, LLM, and text-to-speech models for a private user experience.

#7about 3 minutes

Introducing SME2 for next-generation AI acceleration

The Scalable Matrix Extension 2 (SME2) for Armv9 CPUs uses the Matrix Outer Product Accumulate (MPA) instruction to dramatically accelerate matrix multiplication.

#8about 1 minute

Measuring performance gains with SME2 acceleration

SME2 delivers over six times better performance for key generative AI models like Gemma and Whisper, enabling real-time text summarization and audio generation.

#9about 2 minutes

How Android developers can prepare for SME2

With SME2 support coming to Android, developers using AI frameworks with KleidiAI integration will automatically receive significant performance boosts without any code changes.