Alliance for OpenUSD

AI APPLICATION FRAMEWORK VOICE NVIDIA's Accelerated Computing Platform Full-stack innovation across silicon, systems and software MODULUS MONAI RIVA MAXINE NEMO MERLIN CUOPT MORPHEUS TOKKIO AVATAR DRIVE ISAAC PLATFORMS cuNumeric NVIDIA HPC CV-CUDA cuQuantum NVIDIA AI Parabricks Sionna Jetpack IGX NVIDIA Omniverse BUS VAN AN MOTORBIKE BUS PEDESTRI CYCLIST METROPOLIS HOLOSCAN With nearly three decades of a singular focus, NVIDIA is expert at accelerating software and scaling compute by a Million-X, going well beyond Moore's law. Accelerated computing is a full-stack challenge, demanding deep understanding of the problem domain, optimizing across every layer of computing, and all three chips GPU, CPU, and DPU. Scaling across multi-GPUs and multi-nodes is a data center-scale challenge and requires treating the network and storage as part of the computing fabric. Our platform extends from PCs to supercomputing centers, enterprise data centers, cloud and edge environments. ACCELERATION LIBRARIES RAPIDS Spark cuDNN cuGraph TensorRT Triton Deepstream Flare CLOUD-TO-EDGE DATACENTER-TO- ROBOTIC SYSTEMS 3-CHIPS DOCA Mag 10 Aerial RTX DGX HGX EGX OVX Super POD AGX GPU CPU DPU NVIDIA

View entire presentation