Turing-based GPUs feature a new streaming multiprocessor (SM) architecture that supports up to 16 trillion floating-point operations in parallel with 16 trillion integer operations per second. Developers can take advantage of up to 4,608 CUDA cores with NVIDIA CUDA 10, FleX, and PhysX software development kits (SDKs) to create complex simulations, such as particle or fluid dynamics for scientific visualisation, virtual environments, and special effects.