“I’m pleased to share today that the Intel Xe architecture roadmap for data center optimized rendering includes ray tracing hardware acceleration support for the Intel Rendering Framework family of API’s and libraries,” stated Jim Jeffers, Sr. Principal Engineer and Sr. Director of Intel’s Advanced Rendering and Visualization workforce. Intel didn’t go into technical particulars of the {hardware} itself. NVIDIA demonstrated that you just want two main elements on a contemporary GPU to realize real-time raytracing: 1. a fixed-function {hardware} that computes intersection of rays with triangles or surfaces (which in NVIDIA’s case are the RT cores), and a pair of. an “inexpensive” de-noiser. NVIDIA took the AI route to realize the latter, by deploying tensor cores (matrix-multiplication models), which speed up AI DNN constructing and coaching. Both these duties are achievable with out fixed-function {hardware}, utilizing programmable unified shaders, however at nice efficiency value. Intel developed a CPU-based de-noiser that may leverage AVX-512.