perf: Consider explicitly defining TARGET_CPU with +crc32 for ARM maxperf builds #1627
Labels
No labels
Blocked
Bug
Changelog
Added
Changelog
Missing
Changelog
None
Cherry-picking
Database
Dependencies
Dependencies/Renovate
Difficulty
Easy
Difficulty
Hard
Difficulty
Medium
Documentation
Enhancement
Good first issue
Help wanted
Inherited
Matrix/Administration
Matrix/Appservices
Matrix/Auth
Matrix/Client
Matrix/Core
Matrix/E2EE
Matrix/Federation
Matrix/Hydra
Matrix/MSC
Matrix/Media
Matrix/T&S
Merge
Merge/Manual
Merge/Squash
Meta
Meta/CI
Meta/Packaging
Priority
Blocking
Priority
High
Priority
Low
Security
Status
Confirmed
Status
Duplicate
Status
Invalid
Status
Needs Investigation
Support
Wont fix
old/ci/cd
old/rust
No milestone
No project
No assignees
2 participants
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
continuwuation/continuwuity#1627
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Following discussion in dev room, it seems like
TARGET_CPU=armv8-awould be a good baseline target for maxperf builds (see GCC docs). Furthermore, there seems to be wide support for crc32 and simd instructions, so it could be nice to also add that in.For reference, my RPi4B's
/proc/cpuinfois as below:If this is accepted, I guess the flag could be experimentally enabled first in the Docker build. My suggestions would be
armv8-a+crc. I could try testing these maxperf variants, but sadly don't have the knowhows or infrastructure to build them yet.Change here would be adding the target CPU to
https://forgejo.ellis.link/continuwuation/continuwuity/src/branch/main/.forgejo/workflows/release-image.yml#L129
Can be locally tested by setting the
TARGET_CPUbuild arg on the docker image along with theRUST_PROFILE=release-max-perfarg