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
What should the expected number of sets be? The total number of sets of non-conflicting (at the row level) addresses?
For example, on a dual channel system, with 2 ranks/DIMM and DDR4 (16 banks), does that lead to 2 * 2 * 16 = 64 sets? Based on the default value of 8, I'm guessing that's not correct...
The text was updated successfully, but these errors were encountered:
64, yes. The number of sets you specify is a minimum + you only need half of the sets to know all of them.Am 24.11.2018 23:55 schrieb travisdowns <notifications@github.com>:What should the expected number of sets be? The total number of sets of non-conflicting (at the row level) addresses?
For example, on a dual channel system, with 2 ranks/DIMM and DDR4 (16 banks), does that lead to 2 * 2 * 16 = 64 sets? Seems like too many if you have the default value at 8...
—You are receiving this because you are subscribed to this thread.Reply to this email directly, view it on GitHub, or mute the thread.
What should the expected number of sets be? The total number of sets of non-conflicting (at the row level) addresses?
For example, on a dual channel system, with 2 ranks/DIMM and DDR4 (16 banks), does that lead to 2 * 2 * 16 = 64 sets? Based on the default value of 8, I'm guessing that's not correct...
The text was updated successfully, but these errors were encountered: