Sample: UnifiedMemoryPerf
Minimum spec: SM 3.5

This sample demonstrates the performance comparision using matrix multiplication kernel of Unified Memory with/without hints and other types of memory like zero copy buffers, pageable, pagelocked memory performing synchronous and Asynchronous transfers on a single GPU.

Key concepts:
CUDA Systems Integration
Unified Memory
CUDA Streams and Events
Pinned System Paged Memory