Language Specification

NVIDIA CUDA Quantum is a programming model for heterogeneous quantum-classical computing available in C++ and Python. As such, the model provides primitive types, concepts, syntax, and semantics that enable the integration of quantum processors with existing NVIDIA multi-GPU parallel programming models and architectures.

CUDA Quantum is a library-based language extension that defines quantum code as typed callables in standard C++. These callables are meant to be compiled with standard C++ compilers and run via quantum computer simulators or physical quantum architectures. When annotated with a unique quantum function attribute, these functions can be enhanced with standard circuit optimization and transformation passes.

CUDA Quantum

• 1. Machine Model
• 2. Namespace
• 3. Quantum Types
• 4. Quantum Operators
• 5. Quantum Operations
• 6. Quantum Kernels
• 7. Sub-circuit Synthesis
• 8. Control Flow
• 9. Just-in-Time Kernel Creation
• 10. Quantum Patterns
• 11. Platform
• 12. Algorithmic Primitives
• 13. Example Programs