Skip to main content

Deploying Rack-Scale AI Infrastructure with AMD Helios

abstract background

Scale-up first. Scale-out when it matters. This session sets the foundation for how AI workloads are evaluated across the ecosystem training, inference, agentic and how AMD Helios is architected to support both. Learn how to match workload profiles to the right infrastructure pattern, from rack-scale density to distributed deployment at production scale.

July 23, 2026 12:00 - 12:45

Saurabh Kulkarni
Saurabh Kulkarni

CVP Product Management Datacenter GPU | AMD

Ravi Pendekanti
Ravi Pendekanti

Corporate Vice President, Product Management Datacenter Solutions | AMD

Topic

AI Infrastructure

Session Type

Breakout Session

Related Product

Instinct, EPYC

Related Sessions

View All Sessions
  • How to Right-size Your Memory

    Memory has rarely been in such short supply and is impeding customer data center refresh plans. In this interactive conversation, we’ll discuss tips and tools for right-sizing memory configurations to help move your data center efficiency initiatives forward and preserve ROI. Bring your questions and our experts will provide answers!;Memory has rarely been in such short supply and is impeding customer data center refresh plans. In this interactive conversation, we’ll discuss tips and tools for right-sizing memory configurations to help move your data center efficiency initiatives forward and preserve ROI. Bring your questions and our experts will provide answers!

    July 23, 2026

  • Power is Your Biggest Hidden Cost: How AMD Can Help

    Power is the AI infrastructure cost nobody budgets for until it breaks the business case. In this interactive technical session, an expert from 5C joins AMD to unpack how power consumption impacts total cost of ownership across inference and training deployments. Discuss how intelligent power management, real-world thermal constraints, and silicon-level efficiency shape what your AI infrastructure can sustain. Practical insight for architects and operators making deployment decisions today.;Power is the AI infrastructure cost nobody budgets for until it breaks the business case. In this interactive technical session, an expert from 5C joins AMD to unpack how power consumption impacts total cost of ownership across inference and training deployments. Discuss how intelligent power management, real-world thermal constraints, and silicon-level efficiency shape what your AI infrastructure can sustain. Practical insight for architects and operators making deployment decisions today.

    July 23, 2026

  • Deploying AI PC at Scale with AMD Pro

    Explore how enterprises can securely deploy and manage AI-capable PCs while improving ROI and operational efficiency. Join us to discuss how AMD PRO delivers enterprise-grade security, manageability, and AI performance, while helping organizations address rising AI token costs by shifting workloads closer to the endpoint. Includes a real-world customer case study on scaling AI-ready PC deployments.;Explore how enterprises can securely deploy and manage AI-capable PCs while improving ROI and operational efficiency. Join us to discuss how AMD PRO delivers enterprise-grade security, manageability, and AI performance, while helping organizations address rising AI token costs by shifting workloads closer to the endpoint. Includes a real-world customer case study on scaling AI-ready PC deployments.

    July 23, 2026

  • From AI Clusters to AI Factories: Exploring Network Transport

    As AI scales to “AI factories,” network efficiency becomes critical to GPU performance. In this interactive and conversational session, explore how Multipath Reliable Connection (MRC) overcomes RoCEv2 limits using intelligent packet spraying, adaptive failover, and congestion signaling. Learn how MRC enables resilient, high-throughput, multi-plane Ethernet architectures for next-gen AI training.;As AI scales to “AI factories,” network efficiency becomes critical to GPU performance. In this interactive and conversational session, explore how Multipath Reliable Connection (MRC) overcomes RoCEv2 limits using intelligent packet spraying, adaptive failover, and congestion signaling. Learn how MRC enables resilient, high-throughput, multi-plane Ethernet architectures for next-gen AI training.

    July 23, 2026

  • Driving Enterprise AI Outcomes with AMD

    As AI adoption scales, organizations need flexible infrastructure and trusted ecosystem partners to move faster with confidence. In this session, learn how AMD, together with ISV and OEM partners, is enabling scalable AI, HPC, and enterprise compute solutions that simplify deployment, increase choice, and accelerate innovation across the modern data center.;As AI adoption scales, organizations need flexible infrastructure and trusted ecosystem partners to move faster with confidence. In this session, learn how AMD, together with ISV and OEM partners, is enabling scalable AI, HPC, and enterprise compute solutions that simplify deployment, increase choice, and accelerate innovation across the modern data center.

    July 22, 2026

  • The Token Tsunami: Infrastructure Bets That Win in 2026

    Your AI applications are burning tokens faster than your runway. The inference era is here and the infrastructure decisions you make in the next 12 months will define whether you scale or stall. We'll break down what's driving token demand, which GPU bets pay off, when frontier models earn their cost, and when a lean SLM crushes it. Real benchmarks. No hype. Come find out where AMD fits in your stack.;Your AI applications are burning tokens faster than your runway. The inference era is here and the infrastructure decisions you make in the next 12 months will define whether you scale or stall. We'll break down what's driving token demand, which GPU bets pay off, when frontier models earn their cost, and when a lean SLM crushes it. Real benchmarks. No hype. Come find out where AMD fits in your stack.

    July 22, 2026

  • Securing Your Data with Confidential Compute

    In this audience-driven conversation, we’ll host a deep discussion on practical approaches to enabling trusted execution for AI and multi-tenant workloads. Explore how silicon-based security technologies protect data in use across enterprise and cloud environments. Attendees are encouraged to engage directly with AMD engineers, asking questions on architecture, deployment, and real-world use cases of technologies such as Secure Encrypted Virtualization (SEV) and Confidential Computing.;In this audience-driven conversation, we’ll host a deep discussion on practical approaches to enabling trusted execution for AI and multi-tenant workloads. Explore how silicon-based security technologies protect data in use across enterprise and cloud environments. Attendees are encouraged to engage directly with AMD engineers, asking questions on architecture, deployment, and real-world use cases of technologies such as Secure Encrypted Virtualization (SEV) and Confidential Computing.

    July 22, 2026

  • AMD-Based Solutions: The TCO Advantage You Can't Ignore

    AI infrastructure costs are rarely straightforward, and TCO is harder to calculate than most vendors let on. In this interactive session with our expert, bring your architecture, your constraints, and your real deployment questions. We'll walk through how AMD-based solutions factor into TCO decisions across compute, power, and software and help you build a sharper framework for evaluating what makes sense for your environment. Guidance over pitch. Your questions drive the conversation.;AI infrastructure costs are rarely straightforward, and TCO is harder to calculate than most vendors let on. In this interactive session with our expert, bring your architecture, your constraints, and your real deployment questions. We'll walk through how AMD-based solutions factor into TCO decisions across compute, power, and software and help you build a sharper framework for evaluating what makes sense for your environment. Guidance over pitch. Your questions drive the conversation.

    July 22, 2026