[AMDGPU] Fix AMDGPUPerfHint::isIndirectAccess test case

[foad]

Summary

As suggested in D83862, ignore loads from the constant address space,
otherwise all uses of kernel arguments will be treated as indirect
accesses.

[rampitec]

LGTM

llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.cpp

while (!WorkSet.empty()) {
     const Value *V = *WorkSet.begin();
     WorkSet.erase(*WorkSet.begin());
     if (!Visited.insert(V).second)
       continue;
     LLVM_DEBUG(dbgs() << "  check: " << *V << '\n');
 
     if (auto LD = dyn_cast<LoadInst>(V)) {
       auto M = LD->getPointerOperand();
-      if (isGlobalAddr(M) || isLocalAddr(M) || isConstantAddr(M)) {
+      if (isGlobalAddr(M) || isLocalAddr(M)) {
         LLVM_DEBUG(dbgs() << "    is IA\n");
         return true;
       }
       continue;
     }
 
     if (auto GEP = dyn_cast<GetElementPtrInst>(V)) {
       auto P = GEP->getPointerOperand();

llvm/test/CodeGen/AMDGPU/perfhint.ll

bb:
   %tmp18 = sext i32 %tmp17 to i64
   %tmp19 = getelementptr inbounds i32, i32 addrspace(1)* %arg, i64 %tmp18
   %tmp20 = load i32, i32 addrspace(1)* %tmp19, align 4
   store i32 %tmp20, i32 addrspace(1)* %tmp2, align 4
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_indirect_through_phi:
-; MemoryBound: 0
-; WaveLimiterHint : 0
+; GCN: MemoryBound: 0
+; GCN: WaveLimiterHint : 0
 define amdgpu_kernel void @test_indirect_through_phi(float addrspace(1)* %arg) {
 bb:
   %load = load float, float addrspace(1)* %arg, align 8
   %load.f = bitcast float %load to i32
   %n = tail call i32 @llvm.amdgcn.workitem.id.x()
   br label %bb1
 
 bb1:                                              ; preds = %bb1, %bb