Open Source Summit + AI_dev Japan 2024

The AGL SDV Expert Group has been adding new features to the AGL Unified Code Base. Jerry will present an update on their latest efforts. 

GPU Cloud has become a ubiquitous component of contemporary AI infrastructure, especially for distributed machine learning scenarios. While conversations around AI infrastructure optimization typically revolve around the application layer, such as machine learning tasks and distributed job schedulers, delving into the underhood of the GPU cloud is essential. Numerous factors, including POD Scheduler, Device Plugin, GPU/NUMA topology, ROCE/NCCL Stack, and more, can significantly impact performance.

This session will thoroughly explore the tuning of various machine models(CNN/RNN/Transformer) from MLPerf using an H100 Cluster as a reference. We will analyze the correlation between model performance and device operator configuration in nodes by presenting first-hand experimental results to unveil the hidden potential within a K8S GPU Cloud.

Many products and services are dependent on the Linux Kernel. Because of this the Linux Kernel has to be tested on many different hardware to ensure the stability and reliability of these products or services, this is why KernelCI needs more collaboration both from users and companies. The Linux Kernel upstream community has requested more contributions from companies and users, in particular on the testing ecosystem, such as adding and reporting test results. By understanding corporate usage, the community can more easily provide support and collaborate effectively. KernelCI is one of the current main Kernel testing frameworks and is helping ensure the quality, stability and long-term maintenance of the Linux kernel. As a member of the KernelCI Technical Steering Committee (TSC), I will give details on KernelCI developments and directions. I will talk about current KernelCI new projects. I will talk about KCI tool usage and how it is possible to test own patches with the current KernelCI API and running the test privately. This session will provide useful information for people interested in adopting KernelCI and encourage them to contribute to KernelCI.

The software industry, a bastion of innovation, often overlooks the mental well-being of its builders. This session delves into challenges at all career levels including open source, from layoffs to project pressures, underscoring the need to recognize and respond to mental health fluctuations for inclusive, resilient teams. Compelling narratives include: - Leadership: A startup CEO battling burnout and imposter syndrome. - Career transitions: A young developer overcoming job loss stigma. - Personal resilience: An SRE managing personal loss during critical projects. - Open Source enthusiast: A open-source enthusiast juggling his passion in open source with his official work. Weaving in our journeys with depression during the pandemic, we'll explore strategies for: - Overcoming discrimination in the tech industry. - Taking healthy breaks and prioritizing self-care. - Seeking support from mental health professionals. Our goal is an open, inclusive conversation about mental well-being in open source software. By acknowledging the interconnectedness of personal struggles and team success, we can build resilient, supportive environments for all tech talent to thrive.

The stability of software ecosystems heavily relies on the effective management of open source components across the supply chain. This session will highlight best practices demonstrating the strategic value of open source management talent through case studies and quantitative analyses. Ana Jiménez and Daniel Izquierdo will present practical scenarios where these professionals effectively communicate the importance of open source components to executives, identify bottlenecks affecting engineering teams, and leverage existing open source software toolkits to gather critical data for better decision-making.

In this session, we explore the Singapore Government's approach to modernising its security standards and policy development. By leveraging open formats such as OSCAL, open source tools, and integrating DevOps practices, Singapore is streamlining its cybersecurity governance, making it more lean, efficient and robust. Attendees will learn about the implementation of these technologies, the adoption of DevOps for policy development, and the benefits for government agencies. Join us to discover upcoming plans of compliance automation and security testing to further improve security and resiliency for public services.

Since its introduction 10 years ago, eBPF has steadily gain grounds in networking, tracing, observability, and security applications. But a great technology cannot not thrive on the technical part alone, the people part matters, too. This session hopes to bring eBPF user, developers, and enthusiasts together to exchange novel ideas, discuss best practices, share pain points, and most importantly, collaborate and grow together as a community.