Taipei, Taiwan

By the end of 2025 there will be more than 100 billion AI-capable Arm-powered devices in the world, all powered by the brightest leaders in this partner ecosystem. This enormous opportunity presents new challenges that we must come together to resolve ; delivering AI everywhere is bringing in a new level of power consumption and compute complexity that requires us to rethink everything.

The solution requires a platform that seamlessly combines power efficiency, optimized software, and integrated solutions that help bring your ideas to market faster. Join us as we highlight the technologies, solutions and the opportunity underpinning the Arm platform, and how together, we will build the AI compute platform for the future.

Chris Bergey hosts a panel discussion with Will Chen, Deputy General Manager, Wireless Business Group, MediaTek and Robert Wang, Managing Director, Hong Kong and Taiwan, Amazon Web Services.
In this session, Arm will conduct the conversation with the partners to explore the AI opportunities in their own domains and share how they are going to address them with their AI strategies.

Generative AI is revolutionizing industries worldwide. With its strong foundation in semiconductor and IT manufacturing, Taiwan is uniquely positioned to lead this transformation. To fully harness AI's potential, bridging the gap between hardware and software is critical.
This presentation will delve into the cutting-edge advancements in generative AI, exploring how they're driving innovation in various applications. We'll discuss the challenges and opportunities of integrating hardware and software, drawing from successful collaborations and lessons learned.
We look forward to joint efforts to seize the opportunities brought by AI and create a more prosperous AI ecosystem.

Benchmarking ML inference is crucial for software developers as it ensures optimal performance and efficiency of machine learning workloads. Attendees will learn how to install and run TensorFlow on their Arm-based cloud servers and utilize the MLPerf Inference benchmark suite from MLCommons to evaluate ML performance.

The IoT ecosystem has already shipped billions of chips based on Arm, so its fair to say the IoT already runs on Arm. The IoT industry however, never stands still. We are seeing a rapid market acceleration that demands even higher performance solutions to deliver new and exciting use cases. We all therefore have to continue to innovate.

In this session, we present our hardware, software, and standards solutions that enable our customers and the entire Arm ecosystem to participate and win in this rapidly changing environment. Join us to learn more about the latest and greatest technology Arm is creating for the leaders in IoT to succeed.

KleidiAI is a set of micro-kernels that integrates into machine learning frameworks, accelerating AI inference on Arm-based platforms. These micro-kernels are hand-optimized in Arm assembly code to leverage modern architecture instructions, significantly speeding up AI inference on Arm CPUs. This presentation is an introductory topic for developers who are curious about how KleidiAI works and delivers such speedup.

The latest Armv9 architecutre delivers industry-leading architecture enhancements to help increase compute capabilities with more AI performance for each generation, from Matmul and Neon, to SVE2. Join this session for the inside track on enabling more efficienct AI compute for your next-gen solution.

AI at the edge is built on the foundation of robust framework of secure, connected devices to perform critical tasks in real-time. In this session, Linaro wants to stress the accent on the importance of a solution like ONELab, a solution that empowers businesses to build AI-driven edge devices that are secure, compliant, ready for deployment and faster to be launched on the market. With ONELab the full potential of AI at the edge for innovative applications has never been closer and easier.

The use of ML and generative AI is rapidly shifting from hype into adoption, creating the need for more efficient inferencing at scale. Large language models are getting smaller and more specialized, offering comparable or improved performance at a fraction of the cost and energy. Advances in inferencing techniques, like quantization, sparse-coding, and the rise of specialized, lightweight frameworks like llama.cpp, enable LLMs to run on CPUs and provide good performance for a wide variety of use-cases. Arm has been advancing the capabilities of Neoverse cores to address both the compute and memory needs of LLMs, while maintaining its focus on efficiency. Popular ML frameworks like llama.cpp, PyTorch, and ML compilers allow easy migration of ML models to Arm-based cloud instances. These hardware and software improvements have led to an increase in on-CPU ML performance for use cases like LLMs and recommenders. This gives AI application developers flexibly in choosing CPUs or GPUs, depending on use case and sustainability targets. Arm is also making it possible for ML system designers to create their own bespoke ML solutions including accelerators combined with CPU chiplets to offer the best of both worlds.

This year, we launched Arm Kleidi libraries, designed to provide seamless acceleration for AI inference workloads running on Arm Cortex CPUs. In this session, we discuss their integration into today's AI frameworks, the new AI use cases they are enabling (e.g LLMs), and the future of these libraries.

Generative AI holds exciting potential for Edge AI applications, particularly in creating tangible business value with impactful use cases across industries and business functions. In the latter half of 2023, a trend emerged with the introduction of smaller, more efficient LLMs, such as Llama and tinyLLaMA by Meta, Gemini Nano by Google, and Phi by Microsoft. These advancements are facilitating the deployment of LLMs at the edge, ensuring data stays on the device, thus safeguarding individual privacy, and enhancing user experience by reducing latency and improving responsiveness. Join us as we unveil real-world examples of Arm-powered AI and Generative AI solutions spanning diverse industries. Explore how Arm enables you to harness the complete potential of Generative AI at the edge, even on the smallest devices, revolutionizing your business and sculpting a smarter, more interconnected future.

This speech will explore the architectural design of Arm solutions in rack-level server configurations and share key insights from Wiwynn’s experience implementing Arm-based servers, focusing on practical outcomes and lessons learned

ST explores the advancements and applications of Edge AI technology, highlighting the transition from cloud-based AI to embedded intelligence in smart objects. The adoption of Edge AI is accelerating across various industries, including industrial devices, home appliances, and smart cities, all based on Arm Cortex cores.

The presentation introduces the ST Edge AI Suite, a comprehensive set of tools and resources designed to facilitate the development, optimization, and deployment of AI models on STM32 microcontrollers and other hardware platforms. STM32 microcontrollers, built on Arm Cortex-M cores, offer high performance and low power consumption, making them ideal for edge AI applications. The suite includes tools like STM32Cube.AI and X-CUBE-AI for model conversion, optimization, and performance monitoring.

Moving workloads from x86_64 to the Arm architecture can be challenging. The main porting challenge is to make effective use of architectural features such as SVE2, Cache accesses and SIMD Vectorisation, which requires performance insights to determine how well these hardware features are being utilised. Compilers and libraries offer varying degrees of performance improvements by making effective use of the underlying hardware architecture, but they do not always get it right, which can cause performance degradation during the initial porting phase. Linaro Forge provides the performance insights to quickly identify performance hot spots that helps to determine if the code is utilising the hardware effectively. This in turn enables the user to tune their application for optimal performance on the hardware that their code is being migrated to.

Generative AI seems to be the buzz word of the year and is becoming one of the pillars of the next generation of AI. Technology advances and the pace of innovation are increasing rapidly. These large language models are changing levels of productivity and integrating into our daily lives. So how will the next generation of gen AI change compute requirments and redefine technology parameters?

Arm’s mission for relentless innovation for CPU Architecture means that we’re never standing still. In this talk we will explore the architectural challenges of AI, and how our architecture features will deliver significant improvements for running such AI and related workloads.

Arm Flexible Access and Arm Total Access enable a wide range of silicon and OEM partners with fast and easy access to Arm technology, tools and support through subscription access. Discover how easy evaluation, fewer contracts, and predictable cost is helping nearly 300 Arm partners get to market faster with their best products.
We’ll discuss how Arm accelerates a wide range of partner types, from startups through to high performance Cortex and Neoverse compute technology used by the biggest Arm partners.

Arm CPUs are widely used in traditional ML and AI use cases. In this talk, Arm will show attendees how to run generative AI inference-based use cases like a LLM chatbot on Arm-based CPUs. 

The rapid expansion of AI has led to a major shift in infrastructure technology. Arm Neoverse emerges as platform of choice, offering the best combination of performance, efficiency, and design flexibility. This roadmap session explores how Arm Neoverse forms the foundation for partner innovation across cloud, wireless, networking, HPC, and edge, enabling the deployment of performant and vastly more efficient AI infrastructure on Arm. From Neoverse IP products to the Arm Neoverse Compute Subsystems (CSS) and Arm Total Design, we show why Arm Neoverse is the platform of choice for industry leaders and how it is pivotal in accelerating and shaping the future of AI infrastructure.

Arm has worked with the Google AI Edge team to integrate KleidiAI into the MediaPipe framework through XNNPACK. These improvements increase the throughput of quantized LLMs running on Arm chips that contain the i8mm feature. This presentation will share new techniques for Android developers who want to efficiently run LLMs on-device.