[llvm] [X86][NewPM] Port X86LowerAMXType to NewPM (PR #165084)

[Aiden Grossman via llvm-commits]

================
@@ -1432,8 +1434,58 @@ bool X86LowerAMXCast::transformAllAMXCast() {
   return Change;
 }
 
+bool lowerAmxType(Function &F, const TargetMachine *TM,
+                  TargetLibraryInfo *TLI) {
+  // Performance optimization: most code doesn't use AMX, so return early if
+  // there are no instructions that produce AMX values. This is sufficient, as
+  // AMX arguments and constants are not allowed -- so any producer of an AMX
+  // value must be an instruction.
+  // TODO: find a cheaper way for this, without looking at all instructions.
+  if (!containsAMXCode(F))
+    return false;
+
+  bool C = false;
+  ShapeCalculator SC(TM);
+  X86LowerAMXCast LAC(F, &SC);
+  C |= LAC.combineAMXcast(TLI);
+  // There might be remaining AMXcast after combineAMXcast and they should be
+  // handled elegantly.
+  C |= LAC.transformAllAMXCast();
+
+  X86LowerAMXType LAT(F, &SC);
+  C |= LAT.visit();
+
+  // Prepare for fast register allocation at O0.
----------------
boomanaiden154 wrote:

Agreed. But it's existing and this patch only attempts to make this pass work with the NewPM, not fix and potentially latent problems.

https://github.com/llvm/llvm-project/pull/165084