Index: llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.cpp
@@ -209,13 +209,16 @@
   for (auto &B : F) {
     LastAccess = MemAccessInfo();
     for (auto &I : B) {
-      if (getMemoryInstrPtr(&I)) {
+      if (const Value *Ptr = getMemoryInstrPtr(&I)) {
         if (isIndirectAccess(&I))
           ++FI.IAMInstCount;
         if (isLargeStride(&I))
           ++FI.LSMInstCount;
-        ++FI.MemInstCount;
-        ++FI.InstCount;
+        unsigned Size = divideCeil(
+            Ptr->getType()->getPointerElementType()->getPrimitiveSizeInBits(),
+            32);
+        FI.MemInstCount += Size;
+        FI.InstCount += Size;
         continue;
       }
       if (auto *CB = dyn_cast<CallBase>(&I)) {
Index: llvm/test/CodeGen/AMDGPU/perfhint.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/perfhint.ll
+++ llvm/test/CodeGen/AMDGPU/perfhint.ll
@@ -16,16 +16,6 @@
   %tmp8 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp7, align 16
   %tmp9 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp6
   store <4 x i32> %tmp8, <4 x i32> addrspace(1)* %tmp9, align 16
-  %tmp10 = add nuw nsw i64 %tmp2, 2
-  %tmp11 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp10
-  %tmp12 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp11, align 16
-  %tmp13 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp10
-  store <4 x i32> %tmp12, <4 x i32> addrspace(1)* %tmp13, align 16
-  %tmp14 = add nuw nsw i64 %tmp2, 3
-  %tmp15 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg, i64 %tmp14
-  %tmp16 = load <4 x i32>, <4 x i32> addrspace(1)* %tmp15, align 16
-  %tmp17 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %arg1, i64 %tmp14
-  store <4 x i32> %tmp16, <4 x i32> addrspace(1)* %tmp17, align 16
   ret void
 }