What you should know: CoreWeave is adding thousands of the powerful new NVIDIA A40 GPUs to their already wide selection of specialized offerings.
Why it matters: The NVIDIA A40 is the world’s most powerful data center GPU for visual computing, giving VFX studios, data scientists, and engineering teams the ability to render, process, and analyze faster than ever.
The details: There are GPUs and then there’s the NVIDIA A40. NVIDIA’s newest hardware accelerates rendering performance by 2x and AI training performance by 3x over the previous generation, and CoreWeave now offers the largest inventory of these in North America.
“At a time when computing resources are at a premium and studios are demanding more from their hardware, it’s incredibly exciting for us to be able to offer our clients a tool as powerful as the NVIDIA A40,” says Brian Venturo, CTO at CoreWeave. “This adds to our already wide selection of NVIDIA GPU offerings that are purpose-built for our clients’ machine learning and visual effects needs.”
* Structural sparsity enabled
** A40 is configured for virtualization by default with physical display connectors disabled. The display outputs can be enabled via management software tools.
Combining the latest NVIDIA Ampere architecture RT Cores, Tensor Cores, and CUDA Cores with 48 GB of graphics memory, the A40 is one of the most advanced GPUs on the market. It provides significant performance gains in graphics and compute workflows - bringing massive speedups and capabilities for photorealistic rendering, professional graphic applications, large-scale display experiences, virtual sets, VR, broadcast-grade streaming, and more. For data scientists and engineers, the expanded memory to work with massive datasets and workloads and third-generation Tensor Cores accelerates AI and data science model training without any code changes.
You can find additional details and the full performance specs here.
As NVIDIA’s first Elite Cloud Services Provider for Compute, CoreWeave leverages the latest generation of NVIDIA GPUs that enable customers to run compute-intensive workloads. “CoreWeave is a valued partner that has only strengthened its relationship as it brings A40 GPUs to customers across the media and entertainment, machine learning, and data science industries,” says Matthew McGrigg, Director of Global Business Development for Cloud and Strategic Partners at NVIDIA.
With CoreWeave’s new West Coast data center opening up, studios and firms on the West Coast will also be able to fully take advantage of:
- The industry’s broadest selection of NVIDIA GPUs
- Easily switching between different GPU types on the fly, to match the complexity of the project
- Ultra low-latency virtual workstations
- Reduced CapEx and offloading new hardware management needs to CoreWeave
- Freeing up staff time normally spent on IT and Devops
“CoreWeave owns and operates all our own hardware,” says CoreWeave’s Venturo. “Unlike many other cloud providers who repackage hardware from other providers, our array of GPUs and other hardware is our own.”
Interested in taking advantage of CoreWeave’s new selection of NVIDIA A40 GPUs? Schedule a consultation today.