Skip to content

Commit

Permalink
Add Zicclsm feature name for misaligned load/stores.
Browse files Browse the repository at this point in the history
  • Loading branch information
kasanovic committed Apr 26, 2022
1 parent bdd9b6d commit fecf162
Showing 1 changed file with 8 additions and 6 deletions.
14 changes: 8 additions & 6 deletions profiles.adoc
Original file line number Diff line number Diff line change
Expand Up @@ -573,12 +573,13 @@ NOTE: Za128rs is a new extension name capturing this feature. The
minimum reservation set size is effectively determined by the size of
atomic accesses in the A extension.

- Misaligned loads and stores to main memory regions with both the
- *Zicclsm* Misaligned loads and stores to main memory regions with both the
cacheability and coherence PMAs must be supported.

NOTE: Even when supported, misaligned loads and stores might execute
extremely slowly. Standard software distributions should assume their
existence only for correctness, not for performance.
NOTE: This introduces a new extension name for this feature. Even
though mandated, misaligned loads and stores might execute extremely
slowly. Standard software distributions should assume their existence
only for correctness, not for performance.

- Within main-memory regions, fetching a naturally aligned instruction of
up to four bytes must be atomic.
Expand Down Expand Up @@ -800,10 +801,11 @@ retroactively add to the 2020 and 2022 profiles as an exception.

- Main memory regions with both the cacheability and coherence PMAs must
support instruction fetch, AMOArithmetic, and RsrvEventual.
- Misaligned loads and stores to main memory regions with both the

- *Zicclsm* Misaligned loads and stores to main memory regions with both the
cacheability and coherence PMAs must be supported.

NOTE: Even when supported, misaligned loads and stores might execute
NOTE: Even though mandated, misaligned loads and stores might execute
extremely slowly. Standard software distributions should assume their
existence only for correctness, not for performance.

Expand Down

0 comments on commit fecf162

Please sign in to comment.