Re:ECCploit is the first Rowhammer attack to defeat error-co...
by kingosticks on Friday November 23, 2018 @04:14AM
(#18515313)
Yeh I realised afterwards that at these high clock speeds maybe they do need some extra cycles to do the correction. I don't see why you must do it in hardware to avoid timing side-channels. You just need to provide a constant latency i.e. The cpu ucode does some nops when correction is not necessary.
[ Parent
| on HN ]
Re:ECCploit is the first Rowhammer attack to defeat error-co...
by avianes on Friday November 23, 2018 @10:52AM
(#18517107)
I mean, as long as your ECC is built directly into the silicon
Re:ECCploit is the first Rowhammer attack to defeat error-co...
by kingosticks on Friday November 23, 2018 @11:01AM
(#18517160)
In that case you need to do the exact opposite i.e. avoid the obvious optimisation of returning data early if no correction is required.