Loading…
Develop Lightweight USD Runtimes Faster with AI Agents
NVIDIA Developer BlogMichelle Horton
Summary
Building custom Universal Scene Description (USD) implementations traditionally required adapting large existing codebases to meet specific memory footprints, application binary interfaces (ABIs), or performance requirements. The nanousd-labs project introduces an alternative approach by using AI agents to generate lightweight USD runtimes directly from the Alliance for OpenUSD machine-readable USD Core Specification. Agents parse the specification section by section, write conforming code, and validate output against specification-derived tests under engineer guidance. Written in C++ with a public C API, nanousd functions as an independent data layer that handles parsing, composition, queries, and writing without rendering pixels. This methodology enables developers to regenerate runtimes for varying deployment constraints while maintaining standard compliance through reusable workflows and skill graphs.
Context
Building a USD implementation traditionally required adapting a large codebase, which posed challenges for physical AI teams needing specific memory footprints, ABIs, or performance characteristics.
Approach / What changed
Directing AI agents to read the USD Core Specification as a contract, generate runtime code section by section, and iterate against a specification-derived test suite, while human engineers handle architectural decisions and performance trade-offs.
Takeaways
- nanousd is a C++ runtime data layer with a stable public C API that parses, composes, queries, and writes USD scenes without handling rendering.
- AI agents generate code for parsing, composition, and value resolution against the USD Core Specification, while engineers oversee architecture and performance.
- Human directions for spec-compliant generation can be captured into reusable skill graphs containing structured recipes, prompts, and tests.
Related reading
Optimizing a Neural Reconstruction Pipeline Using NVIDIA Nsight Developer Tools
NVIDIA Omniverse NuRec reconstructs dynamic 3D environments from camera and lidar sensor data for autonomous vehicle simulation workflows, but high computational demands historically caused long reconstruction times. Engineers used NVIDIA Nsight Systems and Nsight Compute to systematically profile the PyTorch-based training pipeline and optimize its underlying CUDA kernels. Nsight Systems revealed GPU underutilization caused by numerous small kernels and blocking synchronization calls, leading to a fused interpolate kernel that accelerated execution from 4.184 milliseconds to 83.81 microseconds. Profiling with Nsight Compute uncovered resource mismatch in the renderBackward kernel, prompting the team to split it into dedicated camera and lidar implementations with tuned register and shared memory allocations. These adjustments raised kernel occupancy from approximately 15% to between 30% and 50% while decreasing the longest lidar kernel runtime from 31 milliseconds to 18 milliseconds.
Tanya Lenz