[llvm] [HWASAN] Use sign extension in memToShadow() and untagPointer() (PR #103727)

[Thurston Dang via llvm-commits]

thurstond wrote:

I'm curious if there's any benchmarks or intuition on the performance impact for AArch64?

The commit message mentions that two shifts can be folded together in the backend, but the new LLVM IR is longer (e.g., llvm/test/Instrumentation/HWAddressSanitizer/RISCV/alloca-with-calls.ll replaces an 'and' with 'shl' and 'ashr'), so it sounds like the overall AArch64 instruction count is unchanged; it's not clear to me whether the old or new AArch64 instructions will run faster.




https://github.com/llvm/llvm-project/pull/103727