| ▲ | cobbzilla 3 days ago | |
Very good point. It’s nontrivial but not impossible to determine this, I am very curious! One nightmare scenario is a 3-bit error being detected as a correctable 1-bit error upstream, resulting in data corruption. I agree it’d be really nice to know that could never happen! | ||
| ▲ | BobbyTables2 2 days ago | parent [-] | |
What about rowhammer attacks ? Wonder if they could be used to introduce “correctable” errors… | ||