Azure Delivers Strong MLPerf Inference v6.1 Results with NVIDIA GB300 & GB200
By Mark Gitau and Azin Heidarshenas In the MLPerf Inference v6.1 round, Azure demonstrated strong Deepseek-R1 performance on GB300 NVL72 and GB200 NVL72 platforms. Azure submitted GB200 results at 18-node (1-rack) and 72-node (4-rack) scale, and GB300 results at 18 nodes (1 rack), marking our first rack-scale and cross-rack MLPerf Inference submissions. According to results published by MLCommons, Azure achieved the highest reported Interactive score on GB300 NVL72 and the highest reported Server and Offline scores on GB200 NVL72 at both 1- and 4-rack scale, demonstrating the ability to sustain high throughput across latency-constrained and throughput-optimized deployment scenarios. DeepSeek-R1 is a large Mixture-of-Experts (MoE) model, making it an ideal benchmark for modern AI infrastructure. It stresses compute, networking (both NVLink and scale-out network), memory, and serving infrastructure under realistic large-scale deployment conditions. As a result, performance is determined by the effectiveness of the entire system stack rather than GPU capability alone. MLPerf Inference evaluates system performance across several deployment scenarios. Offline measures maximum throughput for batch-oriented workloads with no latency constraints. Server simulates production online serving, where requests arrive continuously and systems must maximize throughput while meeting latency targets, evaluating how efficiently a system balances responsiveness and utilization. Interactive focuses on user-facing AI experiences by measuring token generation performance under stringent latency requirements on metrics such as time-to-first token and token-to-token latency. Together, these scenarios provide a comprehensive view of both throughput and real-time serving performance. Results Summary Scenario Throughput (Tokens/second) Platform Interactive Offline Server ND GB300 NVL72 (18 nodes) 260,098 661,143 589,391 ND GB200 NVL72 (18 nodes) - 542,075 426,796 ND GB200 NVL72 (72 nodes) - 2,091,190 1,598,510 Beyond the top results on GB200, Azure's GB300 submission achieved 97.7% of the best reported Server performance and 95.8% of the best reported Offline performance while maintaining the highest Interactive performance among all reported submissions. Together, these results demonstrate competitive performance across diverse deployment scenarios and highlight the strength of Azure's full-stack AI infrastructure. Acknowledgments This submission was led by Mark Gitau and Azin Heidarshenas, who drove the benchmarking, performance characterization, and submission efforts across GB200 and GB300 platforms. MLPerf from MLCommons® MLCommons® is an open engineering consortium of AI leaders from academia, research, and industry where the mission is to “build fair and useful benchmarks” that provide unbiased evaluations of training and inference performance for hardware, software, and services—all conducted under predetermined conditions.Azure NCv6 Virtual Machines: Enhancements and GA Transition
NCv6 Virtual Machines are Azure's flexible, next generation platform enabling both leading-edge graphics and generative AI compute workloads. Featuring NVIDIA RTX PRO 6000 Blackwell Server Edition (BSE) GPUs, Intel Xeon™ 6 "Granite Rapids" 6900P series CPUs, and a suite of Microsoft Azure technologies, NCv6 VMs are available now in Preview. Today, we are pleased to share a series of exciting updates coming soon to Azure NCv6 that will: Enhance VM performance and capabilities Provide more VM sizes for customers to "right size" their usage Bring NCv6 to production readiness with a transition to General Availability, and Expand accessibility across the global Azure cloud New VM Sizes, Features, and Performance Enhancements In the coming weeks, Azure will debut seven new NCv6-series VM sizes and two different sub-families for customers to choose from. The standout features introduced with the new VM sizes include: 🧩 Fractional GPU support, enabling graphics workload customers to deploy VMs with as little as 1/2 or 1/4 of a RTX PRO™ 6000. VMs with fractional GPU support also feature reduced vCPU, memory, SSD, and networking to help customers optimize costs and right size their VMs to their workloads. ⚡ Increased vCPU per VM size (e.g. 288 vCPU instead of 256) to provide more performance for high-end VDI workstations and better align with the Intel Xeon 6900P's triple compute tile architecture. 🛠️ General Purpose and Compute Optimized VM sizes. The former provides larger amounts of CPU memory for demanding generative AI inference and ISV CAD/CAE simulations, while the latter offers reduced memory to enable customers with less memory intensive workloads to cost optimize their deployments. The new VM sizes will replace the existing three VM sizes offered in Preview, and be available as follows: NCv6 - General Purpose VM sizes: Size Name vCPUs Memory (GB) Networking (Mb/s) GPUs GPU Mem (GB) Temp Disk NVMe Disk Standard_NC36ds_xl_RTXPro6000_v6 36 132 22500 1/4 24 256 1600 Standard_NC72ds_xl_RTXPro6000_v6 72 264 45000 1/2 48 512 3200 Standard_NC144ds_xl_RTXPro6000_v6 144 516 90000 1 96 1024 6400 Standard_NC288ds_xl_RTXPro6000_v6 288 1032 180000 2 192 2048 12800 Standard_NC324ds_xl_RTXPro6000_v6 324 1284 180000 2 192 2048 12800 NCv6-Compute Optimized VM sizes: Size Name vCPUs Memory (GB) Networking (Mbps) GPUs GPU Mem (GB) Temp Disk NVMe Disk Standard_NC24lds_xl_RTXPro6000_v6 24 72 22500 1/4 24 256 1600 Standard_NC36lds_xl_RTXPro6000_v6 36 72 22500 1/4 24 256 1600 Standard_NC72lds_xl_RTXPro6000_v6 72 132 45000 1/2 48 512 3200 Standard_NC144lds_xl_RTXPro6000_v6 144 264 90000 1 96 1024 6400 Standard_NC288lds_xl_RTXPro6000_v6 288 516 180000 2 192 2048 12800 Standard_NC324lds_xl_RTXPro6000_v6 324 648 180000 2 192 2048 12800 Note that, until the new VM sizes are available, Microsoft Learn resources will continue to reflect the currently offered VM sizes and technical specifications. Transition to General Availability In the coming weeks, Azure will transition NCv6-series from Preview to General Availability (GA) status. With this transition, NCv6 VMs will become covered by the Azure Service Level Agreement (SLA) and thus ready to support production-grade deployments by customers, partners, and service providers. When the transition to NCv6 VMs occurs, they will be available in the Azure West US2 and Southeast Asia regions. Information on availability timing of additional regions is provided below. Regional Expansion Across the Azure Cloud At the beginning of Preview, NCv6 VMs debuted in the West US2 region. Since then, we have also added NCv6 VMs to the Southeast Asia region. Both regions will be part of the transition to GA status. We are pleased to share that in the proceeding months covering Q3 of 2026, NCv6 VMs will also become available in the following Azure regions: • East US • West Europe • East US 2 • North Europe • South Central US • Germany West Central • West US • Korea Central Ready to build for the future with Azure NCv6? NCv6 Virtual Machines are available now in Preview. Start your production-grade AI journey today and explore the next frontier of Azure AI infrastructure. Join the PreviewMicrosoft at NVIDIA GTC 2026
Microsoft returns to NVIDIA GTC 2026 in San Jose with a strong presence across conference sessions, in‑booth theater talks, live demos, and executive‑level ancillary events. Together with NVIDIA and our partner ecosystem, Microsoft is showcasing how Azure AI infrastructure enables AI training, inference, and production at global scale. Visit us at Booth #521 to see the latest innovations in action and connect with Azure and NVIDIA experts. Exclusive GTC Experiences LEGO® Datacenter Model Explore Azure AI infrastructure at the Park Container. Candy Lounge Visit the high-traffic candy wall for co-branded treats all day long. Networking Lounge Relax and recharge with comfy seating and vital charging options. Outdoor Juice Truck Free, refreshing beverages served during outdoor park hours. Sponsored Breakout Sessions Microsoft Featured Reinventing Semiconductor Design with Microsoft Discovery S82398 · Mon, Mar 16 · 4:00 PM Prashant Varshney Microsoft · Semiconductor & AI Engineering Abstract: Semiconductor teams face exploding design complexity and shrinking verification windows. This session shows how the Microsoft Discovery AI for Science platform, combined with Synopsys Agent Engineers, introduces an agentic approach to EDA that automates routine steps and accelerates expert decision-making on Azure. Microsoft Featured Operationalizing Agentic AI at Hyperscale S82399 · Tue, Mar 17 · 1:00 PM Nitin Nagarkatte Microsoft · Azure AI Infrastructure Anand Raman Microsoft · Azure AI Vipul Modi Microsoft · AI Systems Abstract: As enterprises move to agentic systems, the challenge shifts to operating intelligent agents reliably at scale. This session demonstrates how Microsoft builds AI Factories on Azure using NVIDIA technology and explores Microsoft Foundry as the control plane for deploying and operating coordinated AI agents. Live from GTC: AI Podcast Dayan Rodriguez Corporate Vice President Global Manufacturing and Mobility Alistair Spiers General Manager Azure Infrastructure Live Special Feature A conversation with Microsoft Azure Listen & Subscribe: aka.ms/GTC2026Podcast Scan to Listen Earned Conference Sessions Don't miss these high-impact sessions where Microsoft and NVIDIA leaders discuss the future of AI factories and infrastructure. Mon · Mar 16 5:00 PM Drive Optimal Tokens per Watt on AI Infrastructure Using Benchmarking Recipes Speakers: Paul Edwards, Emily Potyraj Microsoft, NVIDIA Tue · Mar 17 9:00 AM Autonomous AI Factories: Technical Preview of Agent-Native Production Speakers: JP Vasseur, César Martinez Spessot NVIDIA, Microsoft Research Tue · Mar 17 4:00 PM The Road to Intelligent Mobility: Vehicle GenAI Speakers: Raj Paul, Thomas Evans, Bryan Goodman Microsoft, NVIDIA, Bosch Wed · Mar 18 9:00 AM Supercharging AI with Multi-Gigawatt AI Factories Speakers: Gilad Shainer, Peter Salanki, Evan Burness NVIDIA, CoreWeave, Meta, Microsoft Daily Booth Theater Schedule Visit the Microsoft Theater for lightning talks from engineering leaders and partners. Monday, March 16 2:00 PM BTH208 · NVIDIA Accelerate AI Innovation on Azure with NVIDIA Run:ai — Rob Magno 2:30 PM BTH202 · General Robotics Models to Machines: Deploying Agentic AI in Real-World Robotics — Dinesh Narayanan 3:00 PM BTH200 · Fractal Analytics From Generalist to Enterprise-Ready: Fractal Builds Domain AI — C. Chaudhuri 3:30 PM BTH109 · Microsoft Agentic cloud ops - Smarter Operations with Azure Copilot — Jyoti Sharma 4:00 PM BTH103 · Microsoft Build a Deep Research Agent for Enterprise Data — D. Casati, A. Slutsky, H. Alkemade 4:30 PM BTH205 · NetApp Azure NetApp Files: Powering Your Data for AI Capabilities — Andy Chan 5:00 PM BTH207 · NVIDIA The Agentic Commerce Stack: Open Models on Azure — Antonio Martinez 5:30 PM BTH217 · OPAQUE Confidential AI on Azure Unlocks Sovereign AI at Scale — Aaron Fulkerson 6:00 PM BTH218 · Simplismart Making BYOC work at scale with modular inference — Amritanshu Jain 6:30 PM Expo Reception Tuesday, March 17 1:30 PM BTH100 · Microsoft From Open Weights to Enterprise Scale: Open-Source Models — Sharmila Chockalingam 2:00 PM BTH212 · Personal AI Unlocking the power of memory in Teams with Personal AI — Sam Harkness 2:30 PM BTH111 · Microsoft / NVIDIA Scalable LLM Inference on AKS Using NVIDIA Dynamo — Mohamad Al jazaery, Anton Slutsky 3:00 PM BTH204 · Mistral AI Innovate with Mistral AI on Microsoft Foundry — Ian Mathew 3:30 PM BTH104 · Microsoft GPU-Accelerated CFD at Scale: Star-CCM+ on Azure — Jason Scheffelmaer 4:00 PM BTH206 · NeuBird AI Agentic AI for Incident Response on Microsoft Azure — Grant Griffiths 4:30 PM BTH101 · GitHub Agentic DevOps: Evolving software with GitHub Copilot — Glenn Wester 5:00 PM BTH209 · Rescale Real-World AI Physics: GM & NVIDIA on Rescale — Dinal Perera 5:30 PM BTH107 · Microsoft Intro to LoRA Fine-Tuning on Azure — Christin Pohl 6:30 PM Raffle Wednesday, March 18 1:00 PM BTH219 · VAST Data Scaling AI Infrastructure on Azure with VAST Data — Jason Vallery 1:30 PM BTH110 · Microsoft Physical AI and Robotics: The Next Frontier — F. Miller, C. Souche, D. Narayanan 2:00 PM BTH105 · Microsoft Sovereign AI options with Azure Local — Kim Lam 2:30 PM BTH108 · Microsoft Automating HPC Workflows with Copilot Agents — Param Shah 3:00 PM BTH102 · Microsoft Trustworthy Multi-Agent Workflows with Microsoft Foundry — Brian Benz 4:00 PM BTH106 · Microsoft Scaling Enterprise AI on ARO with NVIDIA H100 & H200 — Lachie Evenson 4:30 PM BTH211 · WEKA Hybrid AI Data Orchestration with WEKA NeuralMesh™ — Desiree Campbell 5:00 PM BTH202 · Hammerspace NVIDIA AI Enterprise Software with NIM — Mike Bloom 5:30 PM BTH203 · Kinaxis Reimagining Global Supply Planning with Azure — Dane Henshall 6:00 PM BTH214 · AT&T Connected AI on Azure for Manufacturing — Brad Pritchett 6:30 PM Raffle Thursday, March 19 11:00 AM BTH210 · Wandelbots Physical AI: Powering Software-Defined Automation in Robotics — Marwin Kunz, Martin George 11:30 AM Raffle Explore Our Demo Pods Visit the Microsoft booth to see our technology in action with live demonstrations across four dedicated pod areas. POD 1 Azure AI Infrastructure End‑to‑end AI infrastructure for training and inference at scale, featuring the latest NVIDIA GPU integrations on Azure. POD 2 Microsoft Foundry Our comprehensive platform for building, deploying, and operating agentic AI systems with enterprise reliability. POD 3 Building AI Together Showcasing joint Microsoft and NVIDIA solutions across diverse industries, from manufacturing to retail. POD 4 Startups Powering AI Discover how innovative startups are running next‑generation AI workloads on the Azure platform. Ancillary Events & Networking Join Microsoft leadership and our partner ecosystem at these curated networking experiences. Click the location to view on Bing Maps. Sun · Mar 15 6:00 PM Microsoft for Startups Executive Leadership Dinner 📍 Morton’s Steakhouse, San Jose Exclusive gathering for startup leaders and Microsoft executives. Mon · Mar 16 1:30 PM Microsoft × NVIDIA Open Meet 📍 Signia by Hilton · International Suite Strategic alignment session for Microsoft and NVIDIA executives. Mon · Mar 16 7:30 PM Microsoft + NVIDIA Executive Dinner 📍 Il Fornaio, San Jose Executive dinner for key customers and leadership teams. Tue · Mar 17 11:00 AM to 1:00 PM Microsoft AI Luncheon: Research, Robotics, & Real‑World AI 📍 Signia by Hilton · International Suite Invite-only: A curated executive lunch exploring the journey from AI research to physical enterprise deployments in robotics and manufacturing. Tue · Mar 17 7:30 PM Networking in AI & Tech 📍 San Pedro Square Market Community networking mixer for Microsoft teams, partners, and customers. Wed · Mar 18 10:00 AM to 1:00 PM AI Innovator’s Circle Brunch: Powering Intelligent Systems Across the Ecosystem 📍 Il Fornaio, San Jose Hosted by Microsoft & NVIDIA at GTC. Join us for an exclusive brunch and discussion on the intelligent ecosystem.Azure Recognized as an NVIDIA Cloud Exemplar, Setting the Bar for AI Performance in the Cloud
As AI models continue to scale in size and complexity, cloud infrastructure must deliver more than theoretical peak performance. What matters in practice is reliable, end-to-end, workload-level AI performance—where compute, networking, system software, and optimization work together to deliver predictable, repeatable results at scale. This directly translates to business value: efficient full-stack infrastructure accelerates time-to-market, maximizes ROI on GPU and cloud investments, and enables organizations to scale AI from proof-of-concept to revenue-generating products with predictable economics. Today, Microsoft is proud to share an important milestone in partnership with NVIDIA: Azure has been validated as an NVIDIA Exemplar Cloud, becoming the first cloud provider recognized for Exemplar-class AI performance aligned with GB300-class (Blackwell generation) systems. This recognition builds on Azure’s previously validated Exemplar status for H100 training workloads and reflects NVIDIA’s confidence in Azure’s ability to extend that rigor and performance discipline into the next generation of AI platforms. What Is NVIDIA Exemplar Cloud? The NVIDIA Exemplar Cloud initiative celebrates cloud platforms that demonstrate robust end-to-end AI workload performance using NVIDIA’s Performance Benchmarking suite. Rather than relying on synthetic microbenchmarks, Performance Benchmarking evaluates real AI training workloads using: Large-scale LLM training scenarios Production-grade software stacks Optimized system and network configurations Workload-centric metrics such as throughput and time-to-train Achieving Exemplar validation signals that a provider can consistently deliver world-class AI performance in the cloud, showcasing that end users are getting optimal performance value by default. Proven Exemplar Validation on H100 Azure’s Exemplar Cloud journey began with publicly shared benchmarking results for H100-based training workloads, where Azure ND GPU clusters demonstrated exemplar performance using NVIDIA Performance Benchmarking recipes. Those results—published previously and validated through NVIDIA’s benchmarking framework—established a proven foundation of end-to-end AI performance for large-scale, production workloads running on Azure today. Extending Exemplar-Class AI Performance to GB300-Class Platforms Building on the rigor and learnings from H100 validation, Microsoft has now been recognized by NVIDIA as the first cloud provider to achieve Exemplar-class performance and readiness aligned with GB300-class systems. This designation reflects NVIDIA’s assessment that the same principles applied to H100—including end-to-end system tuning, networking optimization, and software alignment—are being successfully carried forward into the Blackwell generation. Rather than treating GB300 as a point solution, Azure approaches it as a continuation of a proven performance model: delivering consistent world-class AI performance in the cloud while preserving the flexibility, elasticity, and global scale customers expect. What Enables Exemplar-Class AI Performance on Azure Delivering Exemplar-class AI performance requires optimization across the full AI stack: Infrastructure and Networking High-performance Azure ND GPU clusters with NVIDIA InfiniBand NUMA-aware CPU, GPU, and NIC alignment to minimize latency Tuned NCCL communication paths for efficient multi-GPU scaling Software and System Optimization Tight integration with NVIDIA software, including Performance Benchmarking recipes and NVIDIA AI Enterprise Parallelism strategies aligned with large-scale LLM training Continuous tuning as models, workloads, and system architectures evolve End-to-End Workload Focus Measuring real training performance, not isolated component metrics Driving repeatable improvements in application-level throughput and efficiency Closing the performance gap between cloud and on-premises systems—without sacrificing manageability Together, these capabilities enabled Azure to deliver consistent Exemplar-class AI performance across generations of NVIDIA platforms. What This Means for Customers For customers training and deploying advanced AI models, this milestone delivers clear benefits: World-class AI performance in a fully managed cloud environment Predictable scaling from small clusters to thousands of GPUs Faster time to train and improved performance per dollar Confidence that Azure is ready for Blackwell-class and GB300-class AI workloads As AI workloads become more complex and reasoning-heavy, infrastructure performance increasingly determines outcomes. Azure’s NVIDIA Cloud Exemplar recognition provides a clear signal: customers can build and scale next-generation AI systems on Azure without compromising on performance. Learn More DGX Cloud Benchmarking on Azure DGX Cloud Benchmarking on Azure | Microsoft Community Hub
Azure V710 V5 Series -AMD Radeon GPU - Validation of Siemens CAD -NX
Overview of Siemens NX Siemens NX is a next-generation integrated CAD/CAM/CAE platform used by aerospace, automotive, industrial machinery, energy, medical, robotics, and defense manufacturers. It spans: Complex 3D modeling Assemblies containing thousands to millions of parts Surfacing and composites Tolerance engineering CAM and machining simulation Integrated multi physics through Simcenter / NX Nastran Because NX is used to design real-world engineered systems — aircraft structures, automotive platforms, satellites, robotic arms, injection molds — its usability and performance directly affect engineering velocity and product timelines. NX Needs GPU Acceleration NX is highly visual. It leans heavily on: OpenGL acceleration Shader-based rendering Hidden line removal Real-time shading / material rendering Ray-Traced Studio for photorealistic output Switch shading modes → CAD content must stay readable Zoom, section, annotate → requires stable frame pacing NVads V710 v5-Series on Azure The NVads V710 v5-series virtual machines on Azure are designed for GPU-accelerated workloads and virtual desktop environments. Key highlights: Hardware Specs: o GPU: AMD Radeon™ Pro V710 (up to 24 GiB frame buffer; fractional GPU options available). o CPU: AMD EPYC™ 9V64 F (Genoa) with SMT, base frequency 3.95 GHz, peak 4.3 GHz. o Memory: 16 GiB to 160 GiB. o Storage: NVMe-based ephemeral local storage supported. VM Sizes: o Ranges from Standard_NV4ads_V710_v5 (4 vCPUs, 16 GiB RAM, 1/6 GPU) to Standard_NV28adms_V710_v5 (28 vCPUs, 160 GiB RAM, full GPU). Supported Features: o Premium storage, accelerated networking, ephemeral OS disk. o Both Windows and Linux VMs supported. o No additional GPU licensing is required. AMD Radeon™ PRO GPUs offer: o Optimized OpenGL professional driver stack o Stable interactive performance vs large assemblies Business Scenario Enabled by NX + Cloud GPU Engineering Anywhere Distributed teams can securely work on the same assemblies from any geographic region. Supplier Ecosystem Collaboration Tier-1/2 manufacturers and engineering partners can access controlled models without local high-end workstations. Secure IP Protection Data stays in Azure — files never leave the controlled workspace. Faster Engineering Cycles Visualization + simulation accelerate design reviews, decision making, and manufacturability evaluations. Scalable Cost Model Pay for compute only when needed — ideal for burst design cycles and testing workloads. Architecture Overview – Siemens NX on Azure NVads_v710 Key Architecture Elements Create Azure Virtual Machine- NVads_v710_24 Install Azure AMD V710 GPU drivers Deploy Azure File-based storage Hosting assemblies, metadata, drawing packages, PMI, simulation data. Configure Vnet with Accelerated Networking Install NX licenses and software. Install NXCP & ATS Test suites on the Virtual Machine Qualitative Benchmark on Azure NVads_v710_24 Siemens has approved the following qualitative test results. The certification matrix update is currently in progress. Technical variant: Complex assemblies with thousands of components maintained smooth rotation, zooming, and selection, even under concurrent session load. NXCP and ATS test results on NVads_v710_24 Non-Interactive test results: Note: Execution Time (seconds) ATS Non‑Interactive Test Results validate the correctness and stability of Siemens NX graphical rendering by comparing generated images against approved reference outputs. The minimal or zero pixel differences confirm deterministic and visually consistent rendering, indicating a stable GPU driver and visualization pipeline. The reported test execution times (in seconds) represent the duration required to complete each automated graphics validation scenario, demonstrating predictable and repeatable processing performance under non‑interactive conditions. Interactive test results on Azure NVads_v710_24: Note: Execution Time (seconds) ATS Interactive Test Results evaluate Siemens NX graphics behavior during real‑time user interactions such as rotation, zoom, pan, sectioning, and view manipulation. The results demonstrate stable and consistent rendering during interactive workflows, confirming that the GPU driver and visualization stack reliably support user‑driven NX operations. The measured execution times (in seconds) reflect the responsiveness of each interactive graphics operation, indicating predictable behavior under live, user‑controlled conditions rather than peak performance tuning. NX CAD functions Automatic Tests Interactive Tests Grace1 Basic Tests GrPlayer_xp64.exe <FILE> Basic_Features.tgl Passed! Passed! GrPlayer_xp64.exe <FILE> Fog_Measurement_Clipping.tgl Passed! Passed! GrPlayer_xp64.exe <FILE> lighting.tgl Passed! Passed! GrPlayer_xp64.exe <FILE> Shadow_Bump_Environment.tgl Passed! Passed! GrPlayer_xp64.exe <FILE> Texture_Map.tgl Passed! Passed! Grace2 Graphics Tests GrPlayer_64.exe <FILE> GrACETrace.tgl Passed! Passed! Grace2 Graphics Tests GrPlayer_64.exe <FILE> GrACETrace.tgl Passed! Passed! NXCP Test Scenarios Automatic Tests NXCP Gdat Tests gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_1.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_2.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_4.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_5.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_6.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_7.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_8.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_9.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_10.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_11.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_12.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_13.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_14.cgi Passed! gdat_leg_xp64.exe -infile <FILE> leg_gfx_cert_15.cgi Passed! Benefits Azure NVads_v710 (AMD GPU Platform for NX Workstation-class AMD Radeon PRO graphics drivers baked into Azure Ensures ISV-validated driver pipeline. Excellent performance for CAD workloads Makes GPU-accelerated NX accessible to wider user bases. Remote engineering enablement Critical for companies who now operate global design teams. Elastic scale Spin up GPU when development peaks; scale down when idle. Conclusion: Siemens NX on Azure NVads_v710 powered by AMD GPUs enables enterprise-class CAD/CAM/CAE experiences in the cloud. NX benefits directly from workstation-grade OpenGL optimization, shading stability, and Ray Traced Studio acceleration, allowing engineers to interact smoothly with large assemblies, run visualization workloads, and perform design reviews without local hardware dependencies. Right‑sized GPU delivers workstation‑class experience at lower cost The family enables fractional GPU allocation (down to 1/6 of a Radeon™ Pro V710), allowing Siemens NX deployments to be right‑sized per user role. This avoids over‑provisioning full GPUs while still delivering ISV‑grade OpenGL and visualization stability, resulting in a lower per‑engineer cost compared to fixed full‑GPU cloud or on‑prem workstations Elastic scale improves cost efficiency for burst engineering workloads NVads_V710_v5 instances support on demand scaling and ephemeral NVMe storage, allowing NX environments to scale up for design reviews, supplier collaboration, or peak integration cycles and scale down when idle. This consumption model provides a cost advantage over fixed on prem workstations that remain underutilized outside peak engineering periods NX visualization pipelines benefit from balanced CPU–GPU architecture The combination of high‑frequency AMD EPYC™ Genoa CPUs (up to 4.3 GHz) and Radeon™ Pro V710 GPUs addresses Siemens NX’s mixed CPU–GPU workload profile, where scene graph processing, tessellation, and OpenGL submission are CPU‑sensitive. This balance reduces idle GPU cycles, improving effective utilization and overall cost efficiency when compared with GPU‑heavy but CPU‑constrained configurations The result is a scalable, secure, and cost-efficient engineering platform that supports distributed innovation, supplier collaboration, and digital product development workflows — all backed by the Rendering and interaction consistency of AMD GPU virtualization on Azure.Monitoring HPC & AI Workloads on Azure H/N VMs Using Telegraf and Azure Monitor (GPU & InfiniBand)
As HPC & AI workloads continue to scale in complexity and performance demands, ensuring visibility into the underlying infrastructure becomes critical. This guide presents an essential monitoring solution for AI infrastructure deployed on Azure RDMA-enabled virtual machines (VMs), focusing on NVIDIA GPUs and Mellanox InfiniBand devices. By leveraging the Telegraf agent and Azure Monitor, this setup enables real-time collection and visualization of key hardware metrics, including GPU utilization, GPU memory usage, InfiniBand port errors, and link flaps. It provides operational insights vital for debugging, performance tuning, and capacity planning in high-performance AI environments. In this blog, we'll walk through the process of configuring Telegraf to collect and send GPU and InfiniBand monitoring metrics to Azure Monitor. This end-to-end guide covers all the essential steps to enable robust monitoring for NVIDIA GPUs and Mellanox InfiniBand devices, empowering you to track, analyze, and optimize performance across your HPC & AI infrastructure on Azure. DISCLAIMER: This is an unofficial configuration guide and is not supported by Microsoft. Please use it at your own discretion. The setup is provided "as-is" without any warranties, guarantees, or official support. While Azure Monitor offers robust monitoring capabilities for CPU, memory, storage, and networking, it does not natively support GPU or InfiniBand metrics for Azure H- or N-series VMs. To monitor GPU and InfiniBand performance, additional configuration using third-party tools—such as Telegraf—is required. As of the time of writing, Azure Monitor does not include built-in support for these metrics without external integrations. 🔔 Update: Supported Monitoring Option Now Available Update (December 2025): At the time this guide was written, monitoring InfiniBand (IB) and GPU metrics on Azure H-series and N-series VMs required a largely unofficial approach using Telegraf and Azure Monitor. Microsoft has since introduced a supported solution: Azure Managed Prometheus on VM / VM Scale Sets (VMSS), currently available in private preview. This new capability provides a native, managed Prometheus experience for collecting infrastructure and accelerator metrics directly from VMs and VMSS. It significantly simplifies deployment, lifecycle management, and long-term support compared to custom Telegraf-based setups. For new deployments, customers are encouraged to evaluate Azure Managed Prometheus on VM / VMSS as the preferred and supported approach for HPC and AI workload monitoring. Official announcement: Private Preview: Azure Managed Prometheus on VM / VMSS Step 1: Making changes in Azure for sending GPU and IB metrics from Telegraf agents to Azure monitor from VM or VMSS. Register the microsoft.insights resource provider in your Azure subscription. Refer: Resource providers and resource types - Azure Resource Manager | Microsoft Learn Step 2: Enable Managed Service Identities to authenticate an Azure VM or Azure VMSS. In the example we are using Managed Identity for authentication. You can also use User Managed Identities or Service Principle to authenticate the VM. Refer: telegraf/plugins/outputs/azure_monitor at release-1.15 · influxdata/telegraf (github.com) Step 3: Set Up the Telegraf Agent Inside the VM or VMSS to Send Data to Azure Monitor In this example, I'll use an Azure Standard_ND96asr_v4 VM with the Ubuntu-HPC 2204 image to configure the environment for VMSS. The Ubuntu-HPC 2204 image comes with pre-installed NVIDIA GPU drivers, CUDA, and InfiniBand drivers. If you opt for a different image, ensure that you manually install the necessary GPU drivers, CUDA toolkit, and InfiniBand driver. Next, download and run the gpu-ib-mon_setup.sh script to install the Telegraf agent on Ubuntu 22.04. This script will also configure the NVIDIA SMI input plugin and InfiniBand Input Plugin, along with setting up the Telegraf configuration to send data to Azure Monitor. Note: The gpu-ib-mon_setup.sh script is currently supported and tested only on Ubuntu 22.04. Please read the InfiniBand counter collected by Telegraf - https://enterprise-support.nvidia.com/s/article/understanding-mlx5-linux-counters-and-status-parameters Run the following commands: wget https://raw.githubusercontent.com/vinil-v/gpu-ib-monitoring/refs/heads/main/scripts/gpu-ib-mon_setup.sh -O gpu-ib-mon_setup.sh chmod +x gpu-ib-mon_setup.sh ./gpu-ib-mon_setup.sh Test the Telegraf configuration by executing the following command: sudo telegraf --config /etc/telegraf/telegraf.conf --test Step 4: Creating Dashboards in Azure Monitor to Check NVIDIA GPU and InfiniBand Usage Telegraf includes an output plugin specifically designed for Azure Monitor, allowing custom metrics to be sent directly to the platform. Since Azure Monitor supports a metric resolution of one minute, the Telegraf output plugin aggregates metrics into one-minute intervals and sends them to Azure Monitor at each flush cycle. Metrics from each Telegraf input plugin are stored in a separate Azure Monitor namespace, typically prefixed with Telegraf/ for easy identification. To visualize NVIDIA GPU usage, go to the Metrics section in the Azure portal: Set the scope to your VM. Choose the Metric Namespace as Telegraf/nvidia-smi. From there, you can select and display various GPU metrics such as utilization, memory usage, temperature, and more. In example we are using GPU memory_used metrics. Use filters and splits to analyze data across multiple GPUs or over time. To monitor InfiniBand performance, repeat the same process: In the Metrics section, set the scope to your VM. Select the Metric Namespace as Telegraf/infiniband. You can visualize metrics such as port status, data transmitted/received, and error counters. In this example, we are using a Link Flap Metrics to check the InfiniBand link flaps. Use filters to break down the data by port or metric type for deeper insights. Link_downed Metric Note: The link_downed metric with Aggregation: Count is returning incorrect values. We can use Max, Min values. Port_rcv_data metrics Creating custom dashboards in Azure Monitor with both Telegraf/nvidia-smi and Telegraf/infiniband namespaces allows for unified visibility into GPU and InfiniBand. Testing InfiniBand and GPU Usage If you're testing GPU metrics and need a reliable way to simulate multi-GPU workloads—especially over InfiniBand—here’s a straightforward solution using the NCCL benchmark suite. This method is ideal for verifying GPU and network monitoring setups. NCCL Benchmark and OpenMPI is part of the Ubuntu HPC 22.04 image. Update the variable according to your environment. Update the hostfile with the hostname. module load mpi/hpcx-v2.13.1 export CUDA_VISIBLE_DEVICES=2,3,0,1,6,7,4,5 mpirun -np 16 --map-by ppr:8:node -hostfile hostfile \ -mca coll_hcoll_enable 0 --bind-to numa \ -x NCCL_IB_PCI_RELAXED_ORDERING=1 \ -x LD_LIBRARY_PATH=/usr/local/nccl-rdma-sharp-plugins/lib:$LD_LIBRARY_PATH \ -x CUDA_DEVICE_ORDER=PCI_BUS_ID \ -x NCCL_SOCKET_IFNAME=eth0 \ -x NCCL_TOPO_FILE=/opt/microsoft/ndv4-topo.xml \ -x NCCL_DEBUG=WARN \ /opt/nccl-tests/build/all_reduce_perf -b 8 -e 8G -f 2 -g 1 -c 1 Alternate: GPU Load Simulation Using TensorFlow If you're looking for a more application-like load (e.g., distributed training), I’ve prepared a script that sets up a multi-GPU TensorFlow training environment using Anaconda. This is a great way to simulate real-world GPU workloads and validate your monitoring pipelines. To get started, run the following: wget -q https://raw.githubusercontent.com/vinil-v/gpu-monitoring/refs/heads/main/scripts/gpu_test_program.sh -O gpu_test_program.sh chmod +x gpu_test_program.sh ./gpu_test_program.sh With either method NCCL benchmarks or TensorFlow training you’ll be able to simulate realistic GPU usage and validate your GPU and InfiniBand monitoring setup with confidence. Happy testing! References: Ubuntu HPC on Azure ND A100 v4-series GPU VM Sizes Telegraf Azure Monitor Output Plugin (v1.15) Telegraf NVIDIA SMI Input Plugin (v1.15) Telegraf InfiniBand Input Plugin DocumentationAzure NCv6 Public Preview: The new Unified Platform for Converged AI and Visual Computing
As enterprises accelerate adoption of physical AI (AI models interacting with real-world physics), digital twins (virtual replicas of physical systems), LLM inference (running language models for predictions), and agentic workflows (autonomous AI-driven processes), the demand for infrastructure that bridges high-end visualization and generative AI inference has never been higher. Today, we are pleased to announce the Public Preview of the NC RTX PRO 6000 BSE v6 series, powered by the NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs. The NCv6 series represents a generational leap in Azure’s visual compute portfolio, designed to be the dual engine for both Industrial Digitalization and cost-effective LLM inference. By leveraging NVIDIA Multi-Instance GPU (MIG) capabilities, the NCv6 platform offers affordable sizing options similar to our legacy NCv3 and NVv5 series. This provides a seamless upgrade path to Blackwell performance, enabling customers to run complex NVIDIA Omniverse simulations and multimodal AI agents with greater efficiency. Why Choose Azure NCv6? While traditional GPU instances often force a choice between "compute" (AI) and "graphics" (visualization) optimizations, the NCv6 breaks this silo. Built on the NVIDIA Blackwell architecture, it provides a "right-sized" acceleration platform for workloads that demand both ray-traced fidelity and Tensor Core performance. As outlined in our product documentation, these VMs are ideal for converged AI and visual computing workloads, including: Real-time digital twin and NVIDIA Omniverse simulation. LLM Inference and RAG (Retrieval-Augmented Generation) on small to medium AI models. High-fidelity 3D rendering, product design, and video streaming. Agentic AI application development and deployment. Scientific visualization and High-Performance Computing (HPC). Key Features of the NCv6 Platform The Power of NVIDIA Blackwell At the heart of the NCv6 is the NVIDIA RTX PRO 6000 Blackwell Server Edition GPU. This powerhouse delivers breakthrough performance featuring 96 GB of ultra-fast GDDR7 memory. This massive frame buffer allows for the handling of complex multimodal AI models and high-resolution textures that previous generations simply could not fit. Host Performance: Intel Granite Rapids To ensure your workloads aren't bottlenecked by the CPU, the VM host is equipped with Intel Xeon Granite Rapids processors. These provide an all-core turbo frequency of up to 4.2 GHz, ensuring that demanding pre- and post-processing steps—common in rendering and physics simulations—are handled efficiently. Optimized Sizing for Every Workflow We understand that one size does not fit all. The NCv6 series introduces three distinct sizing categories to match your specific unit economics: General Purpose: Balanced CPU-to-GPU ratios (up to 320 vCPUs) for diverse workloads. Compute Optimized: Higher vCPU density for heavy simulation and physics tasks. Memory Optimized: Massive memory footprints (up to 1,280 GB RAM) for data-intensive applications. Crucially, for smaller inference jobs or VDI, we will also offer fractional GPU options, allowing you to right-size your infrastructure and optimize costs. NCv6 Technical Specifications Specification Details GPU NVIDIA RTX PRO 6000 Blackwell Server Edition (96 GB GDDR7) Processor Intel Xeon Granite Rapids (up to 4.2 GHz Turbo) vCPUs 16 – 320 vCPUs (Scalable across GP, Compute, and Memory optimized sizes) System Memory 64 GB – 1,280 GB DDR5 Network Up to 200,000 Mbps (200 Gbps) Azure Accelerated Networking Storage Up to 2TB local temp storage; Support for Premium SSD v2 & Ultra Disk Real-World Applications The NCv6 is built for versatility, powering everything from pixel-perfect rendering to high-throughput language reasoning: Production Generative AI & Inference: Deploy self-hosted LLMs and RAG pipelines with optimized unit economics. The NCv6 is ideal for serving ranking models, recommendation engines, and content generation agents where low latency and cost-efficiency are paramount. Automotive & Manufacturing: Validate autonomous driving sensors (LiDAR/Radar) and train physical AI models in high-fidelity simulation environments before they ever touch the real world. Next-Gen VDI & Azure Virtual Desktop: Modernize remote workstations with NVIDIA RTX Virtual Workstation capabilities. By leveraging fractional GPU options, organizations can deliver high-fidelity, accelerated desktop experiences to distributed teams—offering a superior, high-density alternative to legacy NVv5 deployments. Media & Entertainment: Accelerate render farms for VFX studios requiring burst capacity, while simultaneously running generative AI tools for texture creation and scene optimization. Conclusion: The Engine for the Era of Converged AI The Azure NCv6 series redefines the boundaries of cloud infrastructure. By combining the raw power of NVIDIA’s Blackwell architecture with the high-frequency performance of Intel Granite Rapids, we are moving beyond just "visual computing." Innovators can now leverage a unified platform to build the industrial metaverse, deploy intelligent agents, and scale production AI—all with the enterprise-grade security and hybrid reach of Azure. Ready to experience the next generation? Sign up for the NCv6 Public Preview here.Azure CycleCloud 8.8 and CCWS 1.2 at SC25 and Ignite
Azure CycleCloud 8.8: Advancing HPC & AI Workloads with Smarter Health Checks Azure CycleCloud continues to evolve as the backbone for orchestrating high-performance computing (HPC) and AI workloads in the cloud. With the release of CycleCloud 8.8, users gain access to a suite of new features designed to streamline cluster management, enhance health monitoring, and future-proof their HPC environments. Key Features in CycleCloud 8.8 1. ARM64 HPC Support The platform expands its hardware compatibility with ARM64 HPC support, opening new possibilities for energy-efficient and cost-effective compute clusters. This includes access to the newer generation of GB200 VMs as well as general ARM64 support, enabling new AI workloads at a scale never possible before 2. Slurm Topology-Aware Scheduling The integration of topology-aware scheduling for Slurm clusters allows CycleCloud users to optimize job placement based on network and hardware topology. This leads to improved performance for tightly coupled HPC workloads and better utilization of available resources. 3. Nvidia MNNVL and IMEX Support With expanded support for Nvidia MNNVL and IMEX, CycleCloud 8.8 ensures compatibility with the latest GPU technologies. This enables users to leverage cutting-edge hardware for AI training, inference, and scientific simulations. 4. HealthAgent: Event-Driven Health Monitoring and Alerting A standout feature in this release is the enhanced HealthAgent, which delivers event-driven health monitoring and alerting. CycleCloud now proactively detects issues across clusters, nodes, and interconnects, providing real-time notifications and actionable insights. This improvement is a game-changer for maintaining uptime and reliability in large-scale HPC deployments. Node Healthagent supports both impactful healthchecks which can only run while nodes are idle as well as non-impactful healthchecks that can run throughout the lifecycle of a job. This allows CycleCloud to alert on issues that not only happen while nodes are starting, but also issues that may result from failures for long-running nodes. Later releases of CycleCloud will also include automatic remediation for common failures, so stay tuned! 5. Enterprise Linux 9 and Ubuntu 24 support One common request has been wider support for the various Enterprise Linux (EL) 9 variants, including RHEL9, AlmaLinux 9, and Rocky Linux 9. CycleCloud 8.8 introduces support for those distributions as well as the latest Ubuntu HPC release. Why These Features Matter The CycleCloud 8.8 release marks a significant leap forward for organizations running HPC and AI workloads in Azure. The improved health check support—anchored by HealthAgent and automated remediation—means less downtime, faster troubleshooting, and greater confidence in cloud-based research and innovation. Whether you’re managing scientific simulations, AI model training, or enterprise analytics, CycleCloud’s latest features help you build resilient, scalable, and future-ready HPC environments. Key Features in CycleCloud Workspace for Slurm 1.2 Along with the release of CycleCloud 8.8 comes a new CycleCloud Workspace for Slurm (CCWS) release. This release includes the General Availability of features that were previously in preview, such as Open OnDemand, Cendio ThinLinc, and managed Grafana monitoring capabilities. In addition to previously announced features, CCWS 1.2 also includes support for a new Hub and Spoke deployment model. This allows customers to retain a central hub of shared resources that can be re-used between cluster deployments with "disposable" spoke clusters that branch from the hub. Hub and Spoke deployments enable customers who need to re-deploy clusters in order to upgrade their operating system, deploy new versions of software, or even reconfigure the overall architecture of Slurm clusters. Come visit us at SC25 and MS Ignite To learn more about these features, come visit us at the Microsoft booth at #SC25 in St. Louis, MO and #Microsoft #Ignite in San Francisco this week!
