LLVM 17 Lands Arm Neoverse-V2 Scheduling Model

For helping to ensure optimal performance of AArch64 binaries generated by LLVM/Clang for the Neoverse-V2 processor cores, LLVM 17 Git has received a proper Neoverse-V2 scheduling model.

To this point the Neoverse-V2 targeting within LLVM has relied on using the Neoverse-N2 scheduling model while in Git as of yesterday a proper V2 scheduling model based on information from the Neoverse-V2 software optimization guide has been merged.

This commit adds the optimized Neoverse-V2 scheduling model so that LLVM can better cater to this Neoverse core to be found in various future SoCs.

Arm's Neoverse V-series is designed for maximum performance and optimal TCO. Arm announced the Neoverse-V2 last year and since then patches have begun flowing into the open-source compilers and other components to prepare for future Arm server hardware based on the Neoverse-V2 platform. Already within LLVM 16 and GCC 13 is the initial support while as shown by yesterday's work with the new dedicated scheduling model there are further refinements and optimizations to come.

The LLVM/Clang 17 stable compiler release should debut around September.