On 4/6/2018 1:32 AM, Barbora Murinová wrote:
I've been running se.py with the arguments --caches --cacheline_size=8 on a
int a = 42;
int *p = &a;
*a = 10;
And trying to understand the data cache output for this piece of code. For every access, the data
cache claims to have a hit, although the first two are supposed to be cold misses. No prefetching is
enabled as far as I'm aware. Do you know what could be causing this?
There is a lot of library setup and so on going on before, but that shouldn't
Of course it can! It gets the stack region into the cache.
Regards - Eliot Moss
gem5-users mailing list