Dell is building the perfect beast to support Generative AI solutions, adding eight MI300X GPUs, 192GB of 5.3 TB/s High Bandwidth Memory (HBM3) per GPU for a total coherent HBM3 capacity of 1.5 TB per server, and over 21 petaflops of FP16 performance.
Dell and AMD have announced an expansion to the Dell Generative AI Solutions portfolio, which aims to accelerate advanced workloads and provide businesses with more options to continue their unique GenAI journeys. This new technology emphasizes the critical role played by open ecosystems and silicon diversity in empowering customers with simple, trusted, and tailored solutions to bring AI to their data.
GenAI is huge right now, with 78 percent of IT folks excited about its impact on their organization. It’s all about boosting productivity, streamlining, and saving cash. Getting GenAI right is key to staying competitive. Dell and AMD ensure companies have the muscle to power their AI dreams. More choices for AI and GenAI workloads are on the table now.
PowerEdge XE9680: The Muscle to Power AI Dreams
That muscle comes in the form of the Dell PowerEdge XE9680, the fastest ramping solution in Dell’s history and an absolute favorite of the Storagereview team. It will soon support the newly announced AMD Instinct MI300X accelerator, offering customers more choices regarding AI performance.
The PowerEdge XE9680 with AMD Instinct MI300X provides high-performance capabilities for enterprises seeking to unlock the value of their data and differentiate their business with customized large language models (LLMs). This server is equipped with eight MI300X GPUs, 192GB of 5.3 TB/s High Bandwidth Memory (HBM3) per GPU, for a total coherent HBM3 capacity of 1.5 TB per server, and over 21 petaflops of FP16 performance. By offering this technology, the PowerEdge XE9680 with MI300X is poised to further democratize access to GenAI for enterprises eager to train larger models, reduce data center footprints, lower TCO, and gain a competitive edge.
Releasing the Beast
The Dell PowerEdge XE9680 is a beast in terms of performance, security, and ease of use. It’s got Dell Open Manage Enterprise for quick GenAI setup and CloudIQ for smart, remote automation. Plus, it’s super secure with cyber recovery and Zero Trust.
Dell is also rolling out the next phase of Dell Generative AI Solutions. This includes the new Dell Validated Design for GenAI with AMD, making trustworthy GenAI deployment a breeze. Expect to see it next year with AMD ROCm-powered AI frameworks and will feature open-source LLMs. AMD ROCm is a complete package of open-source tools for AMD Instinct accelerators. Dell is making it easy to build GenAI platforms that fit specific needs.
The PowerEdge XE9680, with the AMD Instinct Platform, offers great scaling and low latency for GenAI training and inferencing. It connects GPUs across PowerEdge servers for a solid AI network.
As part of the Ultra Ethernet Consortium, Dell is pushing for standard networking. They’re in a unique spot to leverage an open approach across their entire GenAI solution – compute, fabric, and storage. The Dell PowerEdge XE9680 with AMD Instinct MI300X accelerators and the new GenAI design will hit the market in the first half 2024.
Engage with StorageReview