[llvm] [X86] Support encoding compress from movberr to bwap (PR #79775)

[Shengchen Kan via llvm-commits]

================
@@ -225,8 +225,11 @@ static bool CompressEVEXImpl(MachineInstr &MI, const X86Subtarget &ST) {
   //
   // For AVX512 cases, EVEX prefix is needed in order to carry this information
   // thus preventing the transformation to VEX encoding.
-  bool IsND = X86II::hasNewDataDest(TSFlags);
-  if (TSFlags & X86II::EVEX_B)
+  // MOVBE*rr is special because it has sematic of NDD but not set EVEX_B.
----------------
KanRobert wrote:

semantic

https://github.com/llvm/llvm-project/pull/79775