[llvm] Enable unaligned loads on x86 using cmpxchg (PR #142645)

[Craig Topper via llvm-commits]

================
@@ -137,6 +137,9 @@ X86TargetLowering::X86TargetLowering(const X86TargetMachine &TM,
 
   // Set up the TargetLowering object.
 
+  // X86 supports unaligned atomic memory accesses via cmpxchg8b and cmpxchg16b
----------------
topperc wrote:

Isn't cmpxchg16b documented to require 16 byte alignment?

https://github.com/llvm/llvm-project/pull/142645