Patrick McGinn’s Post

CoolIT Systems proudly announces the highest density CDUs in the world. This new line of three CDUs includes: AHx240. The industry’s highest capacity liquid-to-air CDU. ➡ 240 kW @ 15°C approach in two-rack footprint. ➡ High 1.5 LPM / kW flow-to-heat ratio. ➡ Cool 4 x NVIDIA® GB200 NVL72 racks. AHx180. Airflow-optimized high-capacity liquid-to-air CDU. ➡ 180 kW @ 15°C approach within standard data center airflow range. ➡1.5 LPM / kW pressure delivery. ➡ Cool 2 x NVIDIA GB200 NVL72 racks. CHx500.  The industry’s first modular, high-density liquid-to-liquid CDU ➡ Scale from 500 kW to 2 MW @ 5.5 °C in a single rack. ➡ Cool fifty-eight (58) enterprise racks or 1,218 direct liquid cooled (DLC) 2U servers with two Intel® Xeon® Gen 4 (Sapphire Rapids) CPUs each. Units are in production and shipping now! See press release: https://lnkd.in/g4BuMdQN Place an order: sales@coolitsystems.com #Directliquidcooling #AcceleratedCompute #AI #ML #GenerativeAI #Artificialintelligence #Liquidcooling #Highdensity #DataCenters #HPC #CoolIT #CoolITSystems #CoolingTechnology #HighPerformanceComputing #Coolthefuture #DLC

Highest density CDUs…IN THE WORLD! #Coolinsights #Directliquidcooling #AcceleratedCompute #AI #ML #GenerativeAI #Artificialintelligence #Liquidcooling #Highdensity #DataCenters #HPC #CoolIT #CoolITSystems #CoolingTechnology #HighPerformanceComputing #Coolthefuture #DLC

EIZO Rugged Solutions Blog: Using Embedded SoMs for AI At-the-Edge Computing in Mission Systems The Eizo Rugged Solutions NVIDIA® Jetson AGX Orin™ SoM features an NVIDIA Ampere GPU with 2048 CUDA cores and 64 Tensor Cores. This GPU architecture delivers up to 275 TOPS (trillion operations per second) of AI performance, enabling real-time inference for AI applications. The Jetson AGX Orin SoC features twelve Arm Cortex-A78AE CPUs specifically designed for high-performance embedded applications. This high-bandwidth memory enables efficient data transfer between the CPU, GPU, and other processing units. https://lnkd.in/eYEzBBEy #nvidia #gpu #gpgpu #som #rugged #ai #edge #sarsen #technology #jetson #orin #cuda #arm #cortex #embedded #vpx #openvpx #sosa

🌟Gooxi Intel Eagle Stream platform 4U 8-GPU server is designed for large-scale AI training and inference, featuring modular design, supporting 8TB memory capacity, and a maximum of 16 PCIe 5.0 expansion slots. 📍Leading architecture, exceptional performance: The 4U server is equipped with 2 latest Eagle Stream platform CPUs internally, with built-in AMX accelerators, deeply optimized for deep learning training and inference workloads. With a maximum power of 350W and utilizing the latest PCIe and DDR5 technologies, it maximizes processor performance. 📍Flexible topology, unlocking potential: The CPU-GPU connection of the Gooxi Intel Eagle Stream platform 4U 8-GPU server supports both direct pass-through and switch options, easily meeting the workload requirements of various data centers and enterprise applications. It can provide industry-leading data centers and remote enterprise environments with more secure, scalable, and reliable requirements for deep learning inference and training scenarios. 📩 If you would like to get more about Gooxi, please contact us by Email: marketing_global@gooxi.com #server #datacenter #computer #tech #ithardware #GPU #AI #computing #cloud #HPC #ServerTech #Intel #CPU

🚀 How Will This New Chiplet Revolutionize Tech? 🚀 Alphawave Semi has partnered with Arm to develop a cutting-edge compute chiplet based on Arm's Neoverse Compute Subsystems (CSS). This innovative chiplet is designed to power the next generation of AI, high-performance computing, data centers, and 5G/6G networks. Key features include: 🔹 Arm Neoverse N3 CPU core 🔹 High-speed connectivity with PCIe Gen 6.0 and 7.0, Universal Chiplet Express (UCIe), and 112/224G Ethernet 🔹 Efficient networking through the Arm Coherent Mesh Network (CMN) 🔹 Customizable design for rapid development and deployment This collaboration combines Alphawave Semi's expertise in high-speed connectivity and advanced packaging with Arm's powerful computing technology, aiming to accelerate the development of high-performance digital infrastructure. What applications do you think will benefit most from this new technology? #TechInnovation #AI #HPC #5G #6G #AlphawaveSemi #Arm #ComputeChiplet #HighSpeedConnectivity

The importance of chips and GPUs in clustered systems 🌐 In the latest episode of #theCUBEpod we hear from John Furrier and David Vellante on how clustered systems are mainstreaming supercomputing initiatives, and the role of GPUs and chips for these systems. “The supercomputing market is now mainstream because of clusters. We are seeing clustered systems. Monolithic is not a bug, it's a feature. So if you have a workload, you run it on a cluster that's going to service that workload. So, the collection of clusters is a distributed computing paradigm,” said Furrier. “Even Charlie Kawwas, the president at Broadcom, said the word ‘superclusters’ yesterday. I asked him, ‘Why does AI need all these chips?’ It's not just GPUs; it's a combination of GPUs and chips around it. So, GPUs will be one element in the clustered system management,” he added. 📺 Watch the full episode: https://lnkd.in/gybUfwCb #MWC24 #theCUBEResearch MWC Barcelona

Faster, Longer Lasting SSD Performance: How Graid Technology is Changing the Game with GPU-Accelerated RAID 🌐 "Since launching in 2021, Graid Technology has experienced explosive expansion, projecting over 475% year-over-year revenue growth from 2022 to 2023. Strong customer interest across verticals like media and entertainment, telecom, oil and gas, finance, healthcare, and more validate SupremeRAID™’s game-changing value proposition." Curious how we're transforming the industry?💡💎 SupremeRAID™, designed to eliminate storage bottlenecks and unleash the full potential of high-speed NVMe SSDs, achieves unprecedented performance by offloading intensive parity calculations from the CPU to the GPU. Learn how in the full article from VMblog: https://zurl.co/eNH6 #VMBlog #media #RAID #GPU #storage #SMCI #NVMe #NVMEeoF #SSD

You're so right Vikram Sharma Mailthody... The most overlooked fact of this chart is 2 GPU Nodes out perform 200 CPU nodes at 10TB and 30TB. Not only are the GPU clusters cheaper per hour AND faster... it's significantly less data center space and energy consumption. When you have a tight SLA for workloads, and you have to scale out to meet those time constraints... CPUs get extremely expensive.

🚀 𝙀𝙭𝙘𝙞𝙩𝙞𝙣𝙜 𝙒𝙝𝙞𝙩𝙚 𝙋𝙖𝙥𝙚𝙧 𝙛𝙤𝙧 𝙎𝙚𝙧𝙫𝙚𝙧 𝘾𝙪𝙨𝙩𝙤𝙢𝙚𝙧𝙨 𝙖𝙣𝙙 𝙀𝙣𝙩𝙝𝙪𝙨𝙞𝙖𝙨𝙩𝙨! 🚀 Are you ready to unlock unparalleled performance for varied workloads? 💡 Dell's next-gen PowerEdge servers powered by AMD CPUs are here, and I'm thrilled to share some key configuration recommendations and insights from extensive testing performed in the last few weeks. 🔑 𝗞𝗲𝘆 𝗖𝗼𝗻𝗳𝗶𝗴𝘂𝗿𝗮𝘁𝗶𝗼𝗻 𝗥𝗲𝗰𝗼𝗺𝗺𝗲𝗻𝗱𝗮𝘁𝗶𝗼𝗻𝘀: 𝗖𝗵𝗼𝗼𝘀𝗲 𝘁𝗵𝗲 𝗥𝗶𝗴𝗵𝘁 𝗔𝗠𝗗 𝗘𝗣𝗬𝗖 𝗖𝗣𝗨: Select a CPU from the AMD EPYC series that aligns with your workload demands. Pay attention to core count, clock speed, and cache size for optimal performance. 𝗠𝗲𝗺𝗼𝗿𝘆 𝗠𝗮𝘁𝘁𝗲𝗿𝘀: Leverage the power of AMD EPYC's memory channels. Configure memory to match the CPU's capabilities, enhancing memory bandwidth and overall performance. 𝗥𝗲𝗺𝗼𝘁𝗲 𝗠𝗮𝗻𝗮𝗴𝗲𝗺𝗲𝗻𝘁 𝗘𝘅𝗰𝗲𝗹𝗹𝗲𝗻𝗰𝗲: Keep control at your fingertips with Integrated Dell Remote Access Controller (iDRAC). Ensure the server model includes the right iDRAC version for your management needs. 🔍 𝗘𝘅𝘁𝗲𝗻𝘀𝗶𝘃𝗲 𝗧𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗶𝗻𝗱𝗶𝗻𝗴𝘀: This summer, I rigorously tested these PowerEdge servers with AMD CPUs across various workloads. From data-intensive analytics to AI training, these servers demonstrate impressive performance gains, enabling quicker insights and decision-making. The AMD architecture showcases its prowess in multi-threaded workloads, making it an excellent choice for modern data centers. Excited to Learn More? Find more about this on: https://lnkd.in/gAPKPnqD #NextGenServers #AMD #PowerEdge #DataCenter #PerformanceMatters #delltechnologies #ddr5 #databasemanagement #3dmodeling #finance #ai

Just released: our next video providing a quick look at another HPC-suited server model. It's straightforward, giving you key specs and features. 📋 For deeper details or guidance, we're here to help. #QuickGuide #TechInsight