Skip to content

Help, how to support cross page hardware L2 prefetch in ARM core? [ARM][Prefetcher][TLB] #1028

Answered by giactra
xfbingshan asked this question in Q&A
Discussion options

You must be logged in to vote

Hi @xfbingshan. Thanks for reporting this.

A bit of history is required.
gem5 didn't use to employ the concept of a MMU until 2020-2021. Whenever a translation was needed from the CPU (to translate virtual address), the cpu was calling translateAtomic/translatingTiming methods of the appropriate TLB (the DTLB for data accesses and the ITLB for instruction accesses) directly.
The need for being able to model a hierarchichal TLB setup (e.g. with a shared L2) required us to move most of the translation logic into the new MMU class 1, and to stop the CPU from interfacing directly with the TLB. Instead the CPU would hold a reference to the archietctural MMU object which would then be the trans…

Replies: 3 comments 4 replies

Comment options

You must be logged in to vote
1 reply
@xfbingshan
Comment options

Comment options

You must be logged in to vote
0 replies
Comment options

You must be logged in to vote
3 replies
@xfbingshan
Comment options

@giactra
Comment options

@xfbingshan
Comment options

Answer selected by xfbingshan
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Category
Q&A
Labels
None yet
4 participants