Advanced Ray Tracing APIs Proposed for the oneAPI Specification
“Write Once” High-Fidelity Ray Tracing across Multiple Vendors’ Accelerators
I’m pleased to announce that a set of Advanced Ray Tracing APIs are being made available for comment and inclusion in the oneAPI specification. The rapid growth of ray tracing compute across film, scientific visualization, design, and gaming suggests that adding these APIs to the oneAPI specification for XPU architectures will help foster robust and efficient development in this area.
By introducing ray tracing capabilities to the oneAPI specification, software developers across the industry will have the ability to “write once” for high-fidelity ray-traced computations across multiple vendors’ systems and accelerators. Standardizing these interfaces will provide well-designed, tried and true APIs and options for broad compute and rendering infrastructure development. The functionality is subdivided into several domains:
- Geometric ray tracing computations
- Volumetric computation and rendering
- Image denoising
- Scalable rendering and visualization infrastructure
Open source implementations of the ray tracing APIs are in active use via the Intel® oneAPI Rendering Toolkit. The libraries are used in a wide variety of software applications’ 3D graphics computations for film and television photorealistic visual effects and animation, scientific visualization, high-performance computing computations, computer-aided design, architectural engineering, gaming, and more.
The ray tracing libraries recommended for the oneAPI specification include:
- Academy Award*-winning Intel® Embree — geometric ray tracing
- Intel® Open Volume Kernel Library (Open VKL) — volumetric processing
- Intel® Open Image Denoise — AI-based denoiser
- Intel® OSPRay — scalable middleware rendering API
The specification review process and robust community feedback on these ray tracing APIs’ features and functionality, recent adoption by Apple and others on ARM-based processors, and Intel’s own development preparation for future Intel® Iris® Xe graphics confirm these ray tracing APIs are cross-architecture and industry-standard ready. The ease of integration and benefits the APIs provide for developers are well known by open source community partners, and make this a logical next step in delivering the benefits of an open, community-driven, cross-platform, ray tracing ecosystem.
I invite developer feedback and collaboration to further extend these APIs for application development. Contribute to the oneAPI specification through this GitHub repository.