If all DCD is doing is ripping bytes from disk without any processing then I wouldn't expect much dependence on parallelism at all. It should be entirely determined by the I/O bandwidth to the CPUs.
That's exactly what the data show.
Maybe it is not clear that we would like to avoid any I/O cost and we would like to get our performance (reduced time to solution) by working on the compute problem in parallel. Make clearer in intro.
mkhoshle
commented
7 years ago
That's exactly what the data show.
Maybe it is not clear that we would like to avoid any I/O cost and we would like to get our performance (reduced time to solution) by working on the compute problem in parallel. Make clearer in intro.