[llvm] [AArch64] Update zero latency instructions in Neoverse scheduling tables (PR #165690)
Simon Wallis via llvm-commits
llvm-commits at lists.llvm.org
Tue Nov 18 03:15:00 PST 2025
================
@@ -1790,10 +1817,11 @@ def : InstRW<[N3Write_5c_1M0_1V], (instregex "^INDEX_(IR|RI|RR)_D$")>;
// Logical
def : InstRW<[N3Write_2c_1V],
(instregex "^(AND|EOR|ORR)_ZI",
- "^(AND|BIC|EOR|ORR)_ZZZ",
+ "^(AND|BIC|EOR)_ZZZ",
"^EOR(BT|TB)_ZZZ_[BHSD]",
"^(AND|BIC|EOR|NOT|ORR)_(ZPmZ|ZPZZ)_[BHSD]",
"^NOT_ZPmZ_[BHSD]")>;
+def : InstRW<[N3Write_0or2c_1V], (instregex "^ORR_ZZZ")>;
----------------
simonwallis2 wrote:
Done
https://github.com/llvm/llvm-project/pull/165690
More information about the llvm-commits
mailing list