[llvm] [AMDGPU] Enable kernarg preloading by default on gfx940 (PR #110691)

[Matt Arsenault via llvm-commits]

================
@@ -1014,12 +1014,49 @@ struct AAAMDGPUNoAGPR
 
 const char AAAMDGPUNoAGPR::ID = 0;
 
+static unsigned getMaxNumPreloadArgs(const Function &F, const DataLayout &DL,
+                                     const TargetMachine &TM) {
+  const GCNSubtarget &ST = TM.getSubtarget<GCNSubtarget>(F);
+  unsigned Offset = 0;
+  unsigned ArgsToPreload = 0;
+  for (const auto &Arg : F.args()) {
+    if (Arg.hasByRefAttr())
+      break;
+
+    Type *Ty = Arg.getType();
+    Align ArgAlign = DL.getABITypeAlign(Ty);
+    auto Size = DL.getTypeAllocSize(Ty);
----------------
arsenm wrote:

The allocation size doesn't directly map to number of registers. Really this should look at what ComputeValueVTs does to get the number of registers.

I think it would be better to be more precise (and maybe even make the inreg a hard requirement to respect) 

https://github.com/llvm/llvm-project/pull/110691