AMDGPU: Put inexpensive ops first in AMDGPUAnnotateUniformValues::visitLoadInst

[cfang]

Summary

This is in response to the review of https://reviews.llvm.org/D84873:
The expensive check should be reordered last

[arsenm]

llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp

137

Missing space

137

Why does this need to check isEntryFunc in both places? The answer is always no if it's not an entry function

[cfang]

1. Add a missing space;
2. Early exit when it is not an EntryFunction.

llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp

   if (!DA->isUniform(Ptr))
     return;
   auto isGlobalLoad = [&](LoadInst &Load)->bool {
     return Load.getPointerAddressSpace() == AMDGPUAS::GLOBAL_ADDRESS;
   };
   // We're tracking up to the Function boundaries, and cannot go beyond because
   // of FunctionPass restrictions. We can ensure that is memory not clobbered
   // for memory operations that are live in to entry points only.
-  bool NotClobbered = isEntryFunc && !isClobberedInFunction(&I);
   Instruction *PtrI = dyn_cast<Instruction>(Ptr);
-  if (!PtrI && NotClobbered && isGlobalLoad(I)) {
-    if (isa<Argument>(Ptr) || isa<GlobalValue>(Ptr)) {
+
+  if (!isEntryFunc) {
+    if (PtrI)
+      setUniformMetadata(PtrI);
+    return;
+  }
+
+  bool NotClobbered = false;
+  if (PtrI)
+    NotClobbered = !isClobberedInFunction(&I);
+  else if (isa<Argument>(Ptr) || isa<GlobalValue>(Ptr)) {
+    if (isGlobalLoad(I) && !isClobberedInFunction(&I)) {
+      NotClobbered = true;
       // Lookup for the existing GEP
       if (noClobberClones.count(Ptr)) {
         PtrI = noClobberClones[Ptr];
       } else {
         // Create GEP of the Value
         Function *F = I.getParent()->getParent();
         Value *Idx = Constant::getIntegerValue(
           Type::getInt32Ty(Ptr->getContext()), APInt(64, 0));