Enterprise

Dell and AMD Unveil Expanded Generative AI Solution with AMD Instinct Accelerators

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

Newsletter | YouTube | Podcast iTunes/Spotify | Instagram | Twitter | TikTok | RSS Feed

Jordan Ranous

AI Specialist; navigating you through the world of Enterprise AI. Writer and Analyst for Storage Review, coming from a background of Financial Big Data Analytics, Datacenter Ops/DevOps, and CX Analytics. Pilot, Astrophotographer, LTO Tape Guru, and Battery/Solar Enthusiast.

Recent Posts

NVIDIA GTC 2024 set for March 18-21 2024

As the tech community gathers at GTC 2024, the event promises not just to showcase innovations but to inspire a…

16 hours ago

Supermicro Expands Portfolio Of AI Solutions For Edge Locations

These edge AI advancements by Supermicro represent a significant step in making AI more accessible and effective. (more…)

19 hours ago

HPE GreenLake For Block Storage Release 3 Is GA

HPE GreenLake For Block Storage Release 3 marks another step forward in simplicuty and performance for the onprem, cloud-managed service.…

1 week ago

On-Premises Azure Virtual Desktops Have (Finally) GA’ed!

On February 1, 2024, Microsoft announced  Azure Stack HCI with Azure Virtual Desktop is GA! Like many others, we have…

2 weeks ago

AI Alchemy: Cisco & NVIDIA’s Recipe for Innovation

Cisco and NVIDIA collaborate for streamlined AI infrastructure, integrating cloud and on-premise solutions. This partnership is a new chapter in…

2 weeks ago

Cost-Effective Data Management: Spectra’s On-Prem Glacier Validated for NetApp StorageGRID

Spectra Logic announced the successful validation of its On-Prem Glacier solutions for integration with NetApp StorageGRID object-based storage environments. (more…)

2 weeks ago