NVIDIA's GA106 GPU uses the Ampere architecture and is made using a 8 nm production process at Samsung. With a die size of 276 mm² and a transistor count of 12,000 million it is a medium-sized chip. GA106 supports DirectX 12 Ultimate (Feature Level 12_2). For GPU compute applications, OpenCL version 3.0 and CUDA 8.6 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 3840 shading units, 120 texture mapping units and 48 ROPs. Also included are 120 tensor cores which help improve the speed of machine learning applications. The GPU also contains 30 raytracing acceleration cores.