Vector compress API with subword types have large performance gap on SVE with X86. Seems the current SVE codegen still have optimization opportunity. We have to do the optimization to shorten the performance gap.
-
Xiaohong Gong
-
Xiaohong Gong
- Votes:
-
0 Vote for this issue
- Watchers:
-
1 Start watching this issue
- Created:
- Updated: