Changes

Jump to: navigation, search

K2

209 bytes added, 20:20, 16 April 2018
→‎Assignment3
The bitonic sorting algorithm is devised for the input length n being a power of 2.
To check the noticeable time gap, we put 2^1516, 2^20, 2^2524.
<source>
void bitonicSort(int* array, int N){
Below is the comparison between bitonic sort using GPU, quick sort using CPU, bitonic sort using CPU.
[[File:BitonicGraph.jpg|500px|thumb|left|sorting algorithms comparison result]]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
==Assignment3==
While working on the project, we discovered that cudaMemcpy(HtoD) and (DtoH) takes long time.​ so, we decided to use pinned memory instead of pageable memory​ to improve its performance.
Use "cudaHostAlloc() will allocate pinned memory instead of pageable memory​ cudaHostAllocwhich is always stored in RAM and can be accessed by GPU's DMA(direct memory access);​directly"
"It will allocate [[File:Resultone.png|500px|thumb|left|pinned memory which is always stored in RAM and can be accessed by GPU's DMA(direct vs pageable memory access) directly"]]
[[File:Resultone.png|500px|thumb|left|                         using pinned memory vs is 2 times faster than pageable memory]]
Ykim185
44
edits
Retrieved from "https://wiki.cdot.senecapolytechnic.ca/wiki/Special:MobileDiff/133551...133600"

Navigation menu