Description
Computational density and scale are key advantages a data center can offer for complex workloads, accelerating performance and improving total cost of ownership. A variety of professional visualization and AI use cases, including real-time rendering, physics simulation, AI training and inference, and virtual reality, require accelerated hardware capabilities.
Based on the new NVIDIA Ada Lovelace architecture, the NVIDIA L40 delivers high visual computing performance for visualization, rendering, virtualization, simulation, and AI workloads in the data center. The L40 includes 142 third-generation RT Cores that enhance real-time ray tracing capabilities and 568 fourth-generation Tensor Cores with FP8 data format support. These new features are combined with the latest generation CUDA Cores and 48 GB of graphics memory to accelerate visual computing workloads, from high-performance virtual workstation instances to large-scale digital twins in the NVIDIA Omniverse. Offering up to twice the performance of its predecessor at the same power consumption, the NVIDIA L40 is the ideal solution for delivering the visual computing and performance required by modern data centers.
Additional information
| Memory Type | GDDR6 |
|---|---|
| GPU Architecture | Ada Lovelace |
| DisplayPort Output | Yes |
| Card Types | SERVER |
Brand
NVIDIA
NVIDIA is a global leader in graphics processing technology, known for its cutting-edge GPUs, AI solutions, and innovations that power gaming, creative work, data centers, and autonomous systems.
