Adaptive Computing Overview - Adaptive computing enables users to build custom processing pipelines, unlike CPUs and GPUs with fixed pipelines [1] - Adaptive computing allows for custom instruction sets, optimizing memory access and balancing throughput and latency [2] - Adaptive computing hardware can be optimized for specific applications and updated frequently, adapting to new design requirements without new hardware [2] AMD Adaptive Computing Portfolio - AMD Adaptive Computing portfolio includes FPGAs, Versal Adaptive SOCs, Kria SOMs, and Alveo Accelerator cards, reprogrammable for evolving customer needs [3] - AMD Versal AI Edge series Gen2 Adaptive SOCs optimize the complete AI data processing pipeline on a single chip [3] Applications and Customer Base - AMD Adaptive Computing is used in edge-based AI solutions, such as Subaru's EyeSight automated parking assist systems, Clarius' handheld ultrasound scanners, and SICK's intelligent sensor solutions [4] - Approximately 7,000 customers rely on the AMD Adaptive Computing portfolio [5]

Partnership & Vision - AMD and Astera Labs share a vision of solving AI's biggest challenges through collaboration [1] - The partnership focuses on driving a new era of open, scalable AI infrastructure through work on UA Link [1] Company Information & Legal - The document is copyrighted to Advanced Micro Devices, Inc in 2025 [1] - AMD trademarks include the AMD Arrow Logo and combinations thereof in the United States and other jurisdictions [1] - Other names mentioned are for informational purposes and may be trademarks of their respective owners [1] Call to Action - Encourages viewers to subscribe to AMD's YouTube channel [1] - Invites viewers to join the AMD Red Team Discord Server [1] - Promotes engagement through Facebook, Twitter, Twitch, LinkedIn, and Instagram [1]

True innovation comes from shared purpose. Hear from Tareq Amin, CEO of HUMAIN, to see how together we're building more than products—we're lowering the total cost of ownership and shaping the future of AI. #AdvancingAI *** Subscribe: https://bit.ly/Subscribe_to_AMD Join the AMD Red Team Discord Server: https://discord.gg/amd-red-team Like us on Facebook: https://bit.ly/AMD_on_Facebook Follow us on Twitter: https://bit.ly/AMD_On_Twitter Follow us on Twitch: https://Twitch.tv/AMD Follow us on LinkedIn: https ...

MulticoreWare is a software solutions provider and an engineering services company. We were established in 2009 and for the last 15 years we have pioneered solutions around video and video processing. So the old system for doing retail checkout relies on a barcode.And you can imagine somebody, you know, not running the barcode correctly or the barcode was hidden, which can also lead to incorrect checkouts in our system where they just show the object being checked out in the camera and the system automatica ...

AI Workloads & AMD's Solutions - AI workloads are classified into five buckets: traditional machine learning, recommendation systems, language models and generative AI, and mixed AI enabled workloads [7] - AMD offers both GPUs and CPUs to cover the span of all enterprise AI needs, supported through an open ecosystem [11] - AMD's 5 GHz EPYC processor is purpose-built as a host processor for AI accelerators, leveraging the x86 ecosystem for broad software support and flexibility [13][14] - AMD EPYC CPUs lead with 64 cores and 5 GHz operation, suitable for robust enterprise-class workloads [15] Performance & Efficiency - AMD EPYC CPUs demonstrate a 7% to 13% performance boost compared to Xeon when used as a host processor for GPUs [17] - For generative workloads, AMD EPYC CPUs show a 28% to 33% improvement compared to the competition [24] - For natural language workloads, AMD EPYC CPUs outperform the latest generation competition by 20% to 36% [25] - AMD EPYC processors are built for low power, low cost AI inference, offering fast inference, easy integration, and the ability to add AI workloads without adding significant power consumption [28] Uber's Use Case - Uber handles 33 million trips daily, serving 170 million monthly active users, requiring a robust technology stack [30] - Uber began its cloud migration journey with GCP and OCI in late 2022, focused on accelerating innovation and optimizing costs [33] - Uber is migrating more workloads to AMD CPUs in a multi-cloud environment, leveraging next-gen technologies like PCI Gen 6 and CXL [37] - Uber expects over 30% better SPECjbb2015-perf per dollar with GCP C40 chips based on Turin architecture compared to CKD [38]

AI Infrastructure & Market Positioning - Supermicro identifies itself as the fastest-growing AI OEM, projecting growth from $7 billion to $14 billion, and targeting approximately $22 billion [4] - The company emphasizes its focus on addressing missing elements in AI deployments, particularly concerning deployment scale and efficiency [5] - Supermicro aims to improve the experience of deploying, managing, and servicing AI infrastructure by collaborating with ecosystem partners [3] Liquid Cooling & Data Center Efficiency - Supermicro has a current capacity of 5,000 racks per month, with 2,000 racks per month dedicated to liquid cooling [7] - The company is investing in liquid cooling technologies and has an 18MW power capacity in its manufacturing facility for system-level testing [6] - Supermicro aims to improve liquid cooling efficiency up to 98% to reduce water consumption and noise levels [24] - Liquid cooling can improve efficiency by up to 40% by targeting CPUs, GPUs, memory, and power supplies [23] Holistic AI Deployment Approach - Supermicro advocates for a holistic approach to AI deployments, considering system, rack, and data center levels, including power, cooling, rack density, and weight [10][11][20] - The company emphasizes the importance of rapid deployment and monetization of AI infrastructure, working closely with technology partners [8] - Supermicro is validating networking solutions, including InfiniBand and Ethernet, to ensure efficient data transfer from GPUs [19][20] AMD Partnership & Solutions - Supermicro collaborates with AMD, offering systems from MI25 to MI300X, including air-cooled and liquid-cooled options [26][31] - Supermicro is shipping MI350 and MI355 series servers with both air-cooled and liquid-cooled options [36][50] - Supermicro was the first to qualify an A+ A+ A solution, combining AMD CPUs, GPUs, and Pensando AI NICs [49][50]

AI Acceleration - AMD Instinct 和 ROCm 软件正在加速人工智能性能，更快、更高效地将前沿 AI 模型投入生产 [1] - Microsoft 的 Eric Boyd 分享了 AMD 的硬件和软件如何推进 AI [1] Company Information - AMD 是一家半导体公司，其产品包括 CPU、GPU 和自适应计算 [1] - 该文档包含 AMD 的商标和版权信息，表明其对技术的知识产权保护 [1] Resources - 提供了 AMD Red Team Discord 服务器、Facebook、Twitter、Twitch、LinkedIn 和 Instagram 的链接，方便用户获取更多信息和互动 [1]

Sustainability & Efficiency Focus - AMD's research and advanced development team focuses on efficiency and sustainability, specifically power management of CPUs, GPUs, and SoCs [2] - The intersection of computing and sustainability is a key area of interest for AMD [2] - Sustainability is a significant concern for the next generation, influencing their interest in related fields [3] Innovation & Differentiation - AMD encourages exploring unconventional paths to discover innovative solutions [4] - AMD values nurturing individual talents and skills, even if they deviate from the norm [4] - AMD emphasizes the importance of going against the grain to find new opportunities [1][4] Historical Impact - AMD's work on power consumption in processor architecture was initially met with skepticism but later recognized as seminal [1]

Backstage with Sam Altman at #AdvancingAI. The future of AI is developer-first and open. *** Subscribe: https://bit.ly/Subscribe_to_AMD Join the AMD Red Team Discord Server: https://discord.gg/amd-red-team Like us on Facebook: https://bit.ly/AMD_on_Facebook Follow us on Twitter: https://bit.ly/AMD_On_Twitter Follow us on Twitch: https://Twitch.tv/AMD Follow us on LinkedIn: https://bit.ly/AMD_on_Linkedin Follow us on Instagram: https://bit.ly/AMD_on_Instagram ©2025 Advanced Micro Devices, Inc. AMD, the AMD A ...

To truly innovate AI at scale, you need the full stack. Listen to Tareq Amin, CEO of HUMAIN, to see how together we’re building state-of-the-art AI factories and data centers with the power, connectivity, and chipsets to lower infrastructure costs and accelerate global innovation. #AdvancingAI *** Subscribe: https://bit.ly/Subscribe_to_AMD Join the AMD Red Team Discord Server: https://discord.gg/amd-red-team Like us on Facebook: https://bit.ly/AMD_on_Facebook Follow us on Twitter: https://bit.ly/AMD_On_Twit ...