Can you provide more details on how that would work? Given that the input is CSV rows and not an array of integers alone, and the fact that getting to the next row is dependent on finding the delimiter in the current row.
There isn't really a dependency there. You can scan for a bunch of delimiters and save a bunch of row start and end positions and process the rows from there.
If (unlike the solutions that won this challenge) you would like to use a hash that consumes all the bytes in the input, then scanning for all the delimiters and bucketizing strings by length also lets you avoid branch mispredictions caused by random lengths.
If (unlike the solutions that won this challenge) you would like to use a hash that consumes all the bytes in the input, then scanning for all the delimiters and bucketizing strings by length also lets you avoid branch mispredictions caused by random lengths.