Accelerate the Most Demanding Visual Computing Workloads
- January 18, 2023
Emerging capabilities in graphics and AI are transforming 3D design and simulation workflows, fueling explosive growth in visual computing workload complexity and scale. Across industries, a transformation is underway thanks to an explosion of data, accelerated adoption of AI-augmented tools in existing workflows and demand for photo-realistic, real-time performance.
Embracing and enabling this transformation requires platforms equipped with accelerated hardware capabilities to meet the needs of a broad spectrum of visual computing use cases.
Delivering a platform with native support for visual computing applications and workloads starts with a performance-optimized infrastructure, flexible enough to support a range of needs across the business and its users.
The Dell PowerEdge server portfolio enables enterprises and businesses to harness the power of GPUs and significantly improve performance with visual computing solutions using the NVIDIA L40 GPU, which is supported in the R750xa, R750 and R7525 servers.
And with today’s announcement of the next generation of Dell’s PowerEdge systems based on the latest 4th Gen Intel® Xeon® Scalable Processor family, designers, developers and business users will be able to take visual computing performance to new heights with future configurations that include NVIDIA L40 GPUs, delivering a powerful platform with the agility, performance and scale to tackle the most demanding visual computing workloads.
Powered by the new Ada Lovelace architecture, the NVIDIA L40 GPU delivers breakthrough graphics, compute and AI performance for data center workloads. With the latest-generation RT Cores and Tensor Cores, coupled with 48GB of GDDR6 memory and new innovations within the Ada Lovelace architecture, the L40 GPU delivers a tremendous leap in performance and efficiency to accelerate large-scale, high-fidelity creative workflows, including AI-enabled, real-time interactive rendering, 3D design and physically accurate simulation.
Optimized to deploy at scale, the NVIDIA L40 GPU is tried, tested and certified for high-demand, 24/7 data center environments and includes enterprise-grade features like power-efficient hardware and Secure Boot with root of trust. Combining these capabilities with Dell’s next-generation PowerEdge systems delivers breakthrough performance, efficiency and scalability to accelerate a broad range of workloads, including:
With third-generation RTX ray-tracing technology and 209 teraflops of RT Core performance, the NVIDIA L40 brings up to 2X the real-time ray-tracing performance of the previous generation to accelerate professional graphics workflows such as real-time, full-fidelity, interactive rendering, 3D design and virtual production.
The L40 packs a powerful punch to conquer AI-enabled graphics, training and inference, high-performance computing, and simulation workloads. With fourth-generation Tensor Cores and over 90 TFLOPS of single-precision floating point (FP32) performance, the L40 provides high throughput across a broad range of precisions, including FP8.
The NVIDIA L40 takes streaming and video content workloads to the next level. With three encode and three decode engines, the addition of AV1 encoding and support for 8K video streaming at 60FPS, the L40 delivers higher performance and improved total cost of ownership for broadcast streaming, video production and transcription workflows.
The metaverse is ushering in the next era of industries and AI, transforming customer experiences and revolutionizing how enterprises design, simulate and optimize products and processes. NVIDIA Omniverse Enterprise includes the full suite of tools enterprises need to develop and operate metaverse applications and is optimized to take full advantage of the enhancements within Ada Lovelace architecture to accelerate the creation of physically accurate virtual worlds, large-scale simulations and digital twins.
The L40 GPU powers Omniverse Enterprise in the data center, delivering a multifold increase in performance for workflows like real-time ray-traced and path-traced rendering, physics simulation and the generation of physically accurate 3D data for training computer vision and robotic networks.
With visual computing, 3D models and performance graphics as catalysts to drive and transform the internet, the metaverse and other advanced innovations forward, businesses are actively looking to stay ahead of the performance demands, while optimizing investments and harnessing visual computing innovation to meet their business and end-user needs.
Purpose-built solutions for visual computing are essential foundations to keep up with the pace of innovation. With a powerful foundation of solutions from Dell and NVIDIA, including PowerEdge servers along with leading-edge NVIDIA accelerators such as the L40 GPU and the NVIDIA Omniverse platform, customers can build and deliver a curated, efficient and performance solution for metaverse and 3D world development, from data center to edge.