Changes

K2

232 bytes added, 00:38, 16 April 2018

→‎Assignment3

==Assignment3==

cudaMemcpy(HtoD) takes long time.

Use pinned memory instead of pageable memory

cudaHostAlloc();

"It will allocate pinned memory which is always stored in RAM and can be accessed by GPU's DMA(direct memory access) directly"

58

edits