NVIDIA's GA103 GPU uses the Ampere architecture and is made using a 8 nm production process at Samsung. With a die size of 496 mm² and a transistor count of 22,000 million it is a very big chip. GA103 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 7680 shading units, 240 texture mapping units and 96 ROPs. Also included are 240 tensor cores which help improve the speed of machine learning applications. The GPU also contains 60 raytracing acceleration cores.