[AArch64] Prioritize STNP patterns for !nontemporal (#174138) This patch prioritizes lowering using STNP patterns over temporal store patterns for store instructions marked `!nontemporal`. We should generally prioritize STNP lowering for non-temporal stores, here it costs extra instructions for address calculation, but its explicitly hinted by the developer so the gain from the memory subsystem should be more significant. It adds test cases for register offset stores where the mixed lowering has been observed. The `AArch64stnp` pattern is sinked under `isLE` but it doesnt change functionality because it is only matched when the custom lowering code in `AArch64ISelLowering.cpp` prepares for it and its guarded by `isLittleEndian()` check. Haven't observe a significant compile time impact that could have stem from matching more failed patterns for each store.
Welcome to the LLVM project!
This repository contains the source code for LLVM, a toolkit for the construction of highly optimized compilers, optimizers, and run-time environments.
The LLVM project has multiple components. The core of the project is itself called “LLVM”. This contains all of the tools, libraries, and header files needed to process intermediate representations and convert them into object files. Tools include an assembler, disassembler, bitcode analyzer, and bitcode optimizer.
C-like languages use the Clang frontend. This component compiles C, C++, Objective-C, and Objective-C++ code into LLVM bitcode -- and from there into object files, using LLVM.
Other components include: the libc++ C++ standard library, the LLD linker, and more.
Consult the Getting Started with LLVM page for information on building and running LLVM.
For information on how to contribute to the LLVM project, please take a look at the Contributing to LLVM guide.
Join the LLVM Discourse forums, Discord chat, LLVM Office Hours or Regular sync-ups.
The LLVM project has adopted a code of conduct for participants to all modes of communication within the project.