[llvm] ff2e878 - [AArch64] Add FeatureFuseAdrpAdd for Ampere1/1A (#81293)

[via llvm-commits]

Author: Philipp Tomsich
Date: 2024-02-09T15:31:30-08:00
New Revision: ff2e8788d277cbb8c47fa2a8ea87dec7e06307aa

URL: https://github.com/llvm/llvm-project/commit/ff2e8788d277cbb8c47fa2a8ea87dec7e06307aa
DIFF: https://github.com/llvm/llvm-project/commit/ff2e8788d277cbb8c47fa2a8ea87dec7e06307aa.diff

LOG: [AArch64] Add FeatureFuseAdrpAdd for Ampere1/1A (#81293)

Both Ampere1 and Ampere1A support fusion of ADRP+ADD.
This adds the missing feature to enable fusion-aware scheduling for this
case.

Added: 
    

Modified: 
    llvm/lib/Target/AArch64/AArch64.td

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AArch64/AArch64.td b/llvm/lib/Target/AArch64/AArch64.td
index 8f8cc154528096..5098dd85c7cd3b 100644
--- a/llvm/lib/Target/AArch64/AArch64.td
+++ b/llvm/lib/Target/AArch64/AArch64.td
@@ -1349,6 +1349,7 @@ def TuneAmpere1 : SubtargetFeature<"ampere1", "ARMProcFamily", "Ampere1",
                                    "Ampere Computing Ampere-1 processors", [
                                    FeaturePostRAScheduler,
                                    FeatureFuseAES,
+                                   FeatureFuseAdrpAdd,
                                    FeatureAddrLSLFast,
                                    FeatureALULSLFast,
                                    FeatureAggressiveFMA,
@@ -1364,6 +1365,7 @@ def TuneAmpere1A : SubtargetFeature<"ampere1a", "ARMProcFamily", "Ampere1A",
                                     "Ampere Computing Ampere-1A processors", [
                                     FeaturePostRAScheduler,
                                     FeatureFuseAES,
+                                    FeatureFuseAdrpAdd,
                                     FeatureAddrLSLFast,
                                     FeatureALULSLFast,
                                     FeatureAggressiveFMA,