← Back to context Comment by oakwhiz 2 days ago No, the Quarks did not have the f00f bug, that would have been funny though. 2 comments oakwhiz Reply numpad0 2 days ago Didn't they have issues with `LOCK CMPXCHG`(not the 8B)? This is out of my depth and I am not sure, but it sounds similar to the f00f bug.1: https://en.wikipedia.org/wiki/Intel_Quark#Segfault_bug neerajsi 1 day ago Yes, they did have the bug with the lock prefix. IOT people at Microsoft got NT booting on the Quark and we ran into that problem. I wound up writing a small tool to patch out all the lock prefixes.
numpad0 2 days ago Didn't they have issues with `LOCK CMPXCHG`(not the 8B)? This is out of my depth and I am not sure, but it sounds similar to the f00f bug.1: https://en.wikipedia.org/wiki/Intel_Quark#Segfault_bug neerajsi 1 day ago Yes, they did have the bug with the lock prefix. IOT people at Microsoft got NT booting on the Quark and we ran into that problem. I wound up writing a small tool to patch out all the lock prefixes.
neerajsi 1 day ago Yes, they did have the bug with the lock prefix. IOT people at Microsoft got NT booting on the Quark and we ran into that problem. I wound up writing a small tool to patch out all the lock prefixes.
Didn't they have issues with `LOCK CMPXCHG`(not the 8B)? This is out of my depth and I am not sure, but it sounds similar to the f00f bug.
1: https://en.wikipedia.org/wiki/Intel_Quark#Segfault_bug
Yes, they did have the bug with the lock prefix. IOT people at Microsoft got NT booting on the Quark and we ran into that problem. I wound up writing a small tool to patch out all the lock prefixes.