[maxhou]

In the real world, the slow part of "parsing" a CSV file is IO: reading the file content from disk to memory, and from memory to CPU cache.

You would avoid reading the file content more than once if you had to parse it.

> The first line counts the number of lines in a buffer (assuming that file is read into memory and copied to gpu buffer d_readbuff).

but this is what is done here, first search to find all \n, then multi-core GPU stuff for each line content.

[azurezyq]

Things have been changed in a world of SSDs and machines w/ much memory. Actually, parsing a CSV in a single thread will never reach several hundred megabytes per second.