Phenomenally detailed article, as expected from Anandtech. I had the misfortune of getting caught reading comments but found, as a comparison, this comment from the articles author particularly interesting:
"It strikes me as bizarre how little we know about Apple CPUs even after two years.
The basic numbers (logical registers, window, ROB size) seem to about match Intel these days, and the architecture seems to be 6-wide with two functional clusters. There appears to be a loop buffer (but how large?) But that's about it.
How well does the branch prediction work and where does it fail?
What prefetchers are provided? (at I1, D1, L2. L3)
Do the caches do anything smart (like dead block prediction) for either performance or power?
Does the memory manager do anything smart (like virtual write queue in the L3)?
etc etc etc"
I wish that Samsung would either give up on software, or put significantly more effort into it. They've had two self-inflicted security catastrophes in the past month.
[+] [-] nthnclrk|10 years ago|reply
"It strikes me as bizarre how little we know about Apple CPUs even after two years. The basic numbers (logical registers, window, ROB size) seem to about match Intel these days, and the architecture seems to be 6-wide with two functional clusters. There appears to be a loop buffer (but how large?) But that's about it. How well does the branch prediction work and where does it fail? What prefetchers are provided? (at I1, D1, L2. L3) Do the caches do anything smart (like dead block prediction) for either performance or power? Does the memory manager do anything smart (like virtual write queue in the L3)? etc etc etc"
[+] [-] fr0styMatt2|10 years ago|reply
[+] [-] bashinator|10 years ago|reply
http://www.theguardian.com/technology/2015/jun/24/samsung-di...
http://arstechnica.com/security/2015/06/new-exploit-turns-sa...
Why do hardware manufacturers suck so badly at decent software?
[+] [-] rasz_pl|10 years ago|reply