Changes

Jump to: navigation, search

GPU621/Analyzing False Sharing

187 bytes added, 15:52, 23 November 2022
no edit summary
We can see that the new block is already much faster than the Thread block, and even comparable to the Serial block is almost the same. But overall the Serial block is still the least time-consuming because the new block still needs to incur extra overhead for thread creation and scheduling.
 
We could try increasing sizeOfNumbers to 1000000 as well, which would allow the program to process more data, thus compensating for the extra overhead of thread creation and scheduling.
[[File:newBlockOutput1000000.jpg|400px]]<br />
[[File:newBlockOutput1000000(1).jpg|400px]]<br />
118
edits

Navigation menu