The same dicrepancy exists with most Matlab functions that do operations along rows or columns. Here is the same test replacing fft with sum,
data = single(rand(71, 110000));
for ichan = 1:size(data, 1)
dataX(ichan) = sum(data(ichan, :), 2);
alldataX = sum(data, 2);
max(abs(dataX(:) - alldataX(:)))/max(alldataX(:))*100
The reason for it is that Matlab's internal multi-threading splits the data up differently depending on the size of the array given as input to the function. This leads to summations being done in different orders and hence floating point discrepancies in the results.