NVIDIA's TU106B GPU uses the Turing architecture and is made using a 12 nm production process at TSMC. With a die size of 445 mm² and a transistor count of 10,800 million it is a very big chip. TU106B supports DirectX 12 Ultimate (Feature Level 12_2). For GPU compute applications, OpenCL version 3.0 and CUDA 7.5 can be used. Additionally, the DirectX 12 Ultimate capability guarantees support for hardware-raytracing, variable-rate shading and more, in upcoming video games. It features 2304 shading units, 144 texture mapping units and 64 ROPs. Also included are 288 tensor cores which help improve the speed of machine learning applications. The GPU also contains 36 raytracing acceleration cores.