You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I think PCM read bandwidth and write bandwidth should be different.
Because PCM cell has an asymmetric read/write latency and is nonvolatile.
If the row buffer data doesn't change, it is not needed to write row buffer to cell array.
However, when I simulated PCM with two test memory traces, the bandwidth was same.
one memory trace is only read and the other one is only write to random memory addresses.
To make this sense, I think ramulator always rewrite the row buffer to cell array when the row is closed.
Does PCM model of ramulaor close the row differently when row buffer isn't changed?
The text was updated successfully, but these errors were encountered:
I think PCM read bandwidth and write bandwidth should be different.
Because PCM cell has an asymmetric read/write latency and is nonvolatile.
If the row buffer data doesn't change, it is not needed to write row buffer to cell array.
However, when I simulated PCM with two test memory traces, the bandwidth was same.
one memory trace is only read and the other one is only write to random memory addresses.
To make this sense, I think ramulator always rewrite the row buffer to cell array when the row is closed.
Does PCM model of ramulaor close the row differently when row buffer isn't changed?
The text was updated successfully, but these errors were encountered: