What is Pinned memory?
Memory locked so the OS will not move or evict its physical pages. The GPU can access it directly by DMA, speeding transfers and enabling asynchronous copies.
Field: GPU Programming
Pinned memory in the explanations
Using pinned memory from the start removes that extra copy and also allows asynchronous transfers that overlap with CPU work.
Why does pinning (page-locking) CPU memory before transferr…
Questions that mention Pinned memory (1)
Related terms
GPU DMA (direct memory access) Bank conflict Constant memory CUDA GPU kernel GPU occupancy GPU shared memory Grid-stride loop Latency hiding