Index: lib/Transforms/Scalar/InferAddressSpaces.cpp
===================================================================
--- lib/Transforms/Scalar/InferAddressSpaces.cpp
+++ lib/Transforms/Scalar/InferAddressSpaces.cpp
@@ -308,6 +308,14 @@
       }
     } else if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(&I)) {
       collectRewritableIntrinsicOperands(II, &PostorderStack, &Visited);
+    } else if (ICmpInst *Cmp = dyn_cast<ICmpInst>(&I)) {
+      // FIXME: Handle vectors of pointers
+      if (Cmp->getOperand(0)->getType()->isPointerTy()) {
+        appendsGenericAddressExpressionToPostorderStack(
+          Cmp->getOperand(0), &PostorderStack, &Visited);
+        appendsGenericAddressExpressionToPostorderStack(
+          Cmp->getOperand(1), &PostorderStack, &Visited);
+      }
     }
   }
 
@@ -730,7 +738,26 @@
       if (handleComplexPtrUse(*CurUser, V, NewV))
         continue;
 
-      if (isa<Instruction>(U.getUser())) {
+      if (isa<Instruction>(CurUser)) {
+        if (ICmpInst *Cmp = dyn_cast<ICmpInst>(CurUser)) {
+          int SrcIdx = U.getOperandNo();
+          int OtherIdx = (SrcIdx == 0) ? 1 : 0;
+          Value *OtherSrc = Cmp->getOperand(OtherIdx);
+
+          if (Value *OtherNewV = ValueWithNewAddrSpace.lookup(OtherSrc)) {
+            Cmp->setOperand(OtherIdx, OtherNewV);
+            Cmp->setOperand(SrcIdx, NewV);
+            continue;
+          }
+
+          if (auto *KOtherSrc = dyn_cast<Constant>(OtherSrc)) {
+            Cmp->setOperand(SrcIdx, NewV);
+            Cmp->setOperand(OtherIdx,
+              ConstantExpr::getAddrSpaceCast(KOtherSrc, NewV->getType()));
+            continue;
+          }
+        }
+
         // Otherwise, replaces the use with generic(NewV).
         // TODO: Some optimization opportunities are missed. For example, in
         //   %0 = icmp eq float* %p, %q
Index: test/Transforms/InferAddressSpaces/AMDGPU/icmp.ll
===================================================================
--- /dev/null
+++ test/Transforms/InferAddressSpaces/AMDGPU/icmp.ll
@@ -0,0 +1,76 @@
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -infer-address-spaces %s | FileCheck %s
+
+; CHECK-LABEL: @icmp_flat_cmp_self(
+; CHECK: %cmp = icmp eq i32 addrspace(3)* %group.ptr.0, %group.ptr.0
+define i1 @icmp_flat_cmp_self(i32 addrspace(3)* %group.ptr.0) #0 {
+  %cast0 = addrspacecast i32 addrspace(3)* %group.ptr.0 to i32 addrspace(4)*
+  %cmp = icmp eq i32 addrspace(4)* %cast0, %cast0
+  ret i1 %cmp
+}
+
+; CHECK-LABEL: @icmp_flat_flat_from_group(
+; CHECK: %cmp = icmp eq i32 addrspace(3)* %group.ptr.0, %group.ptr.1
+define i1 @icmp_flat_flat_from_group(i32 addrspace(3)* %group.ptr.0, i32 addrspace(3)* %group.ptr.1) #0 {
+  %cast0 = addrspacecast i32 addrspace(3)* %group.ptr.0 to i32 addrspace(4)*
+  %cast1 = addrspacecast i32 addrspace(3)* %group.ptr.1 to i32 addrspace(4)*
+  %cmp = icmp eq i32 addrspace(4)* %cast0, %cast1
+  ret i1 %cmp
+}
+
+ ; CHECK-LABEL: @icmp_flat_group_flat(
+; CHECK: %1 = addrspacecast i32 addrspace(3)* %group.ptr.0 to i32 addrspace(4)*
+; CHECK: %cmp = icmp eq i32 addrspace(4)* %1, %flat.ptr.1
+define i1 @icmp_flat_group_flat(i32 addrspace(3)* %group.ptr.0, i32 addrspace(4)* %flat.ptr.1) #0 {
+  %cast0 = addrspacecast i32 addrspace(3)* %group.ptr.0 to i32 addrspace(4)*
+  %cmp = icmp eq i32 addrspace(4)* %cast0, %flat.ptr.1
+  ret i1 %cmp
+}
+
+; CHECK-LABEL: @icmp_flat_flat_group(
+; CHECK: %1 = addrspacecast i32 addrspace(3)* %group.ptr.1 to i32 addrspace(4)*
+; CHECK: %cmp = icmp eq i32 addrspace(4)* %flat.ptr.0, %1
+define i1 @icmp_flat_flat_group(i32 addrspace(4)* %flat.ptr.0, i32 addrspace(3)* %group.ptr.1) #0 {
+  %cast1 = addrspacecast i32 addrspace(3)* %group.ptr.1 to i32 addrspace(4)*
+  %cmp = icmp eq i32 addrspace(4)* %flat.ptr.0, %cast1
+  ret i1 %cmp
+}
+
+; Keeping as cmp addrspace(3)* is better
+; CHECK-LABEL: @icmp_flat_to_group_cmp(
+; CHECK: %cast0 = addrspacecast i32 addrspace(4)* %flat.ptr.0 to i32 addrspace(3)*
+; CHECK: %cast1 = addrspacecast i32 addrspace(4)* %flat.ptr.1 to i32 addrspace(3)*
+; CHECK: %cmp = icmp eq i32 addrspace(3)* %cast0, %cast1
+define i1 @icmp_flat_to_group_cmp(i32 addrspace(4)* %flat.ptr.0, i32 addrspace(4)* %flat.ptr.1) #0 {
+  %cast0 = addrspacecast i32 addrspace(4)* %flat.ptr.0 to i32 addrspace(3)*
+  %cast1 = addrspacecast i32 addrspace(4)* %flat.ptr.1 to i32 addrspace(3)*
+  %cmp = icmp eq i32 addrspace(3)* %cast0, %cast1
+  ret i1 %cmp
+}
+
+; CHECK-LABEL: @icmp_group_flat_cmp_null(
+; CHECK: %cmp = icmp eq i32 addrspace(3)* %group.ptr.0, addrspacecast (i32 addrspace(4)* null to i32 addrspace(3)*)
+define i1 @icmp_group_flat_cmp_null(i32 addrspace(3)* %group.ptr.0) #0 {
+  %cast0 = addrspacecast i32 addrspace(3)* %group.ptr.0 to i32 addrspace(4)*
+  %cmp = icmp eq i32 addrspace(4)* %cast0, null
+  ret i1 %cmp
+}
+
+; CHECK-LABEL: @icmp_group_flat_cmp_undef(
+; CHECK: %cmp = icmp eq i32 addrspace(3)* %group.ptr.0, undef
+define i1 @icmp_group_flat_cmp_undef(i32 addrspace(3)* %group.ptr.0) #0 {
+  %cast0 = addrspacecast i32 addrspace(3)* %group.ptr.0 to i32 addrspace(4)*
+  %cmp = icmp eq i32 addrspace(4)* %cast0, undef
+  ret i1 %cmp
+}
+
+; TODO: Should be handled
+; CHECK-LABEL: @icmp_flat_flat_from_group_vector(
+; CHECK: %cmp = icmp eq <2 x i32 addrspace(4)*> %cast0, %cast1
+define <2 x i1> @icmp_flat_flat_from_group_vector(<2 x i32 addrspace(3)*> %group.ptr.0, <2 x i32 addrspace(3)*> %group.ptr.1) #0 {
+  %cast0 = addrspacecast <2 x i32 addrspace(3)*> %group.ptr.0 to <2 x i32 addrspace(4)*>
+  %cast1 = addrspacecast <2 x i32 addrspace(3)*> %group.ptr.1 to <2 x i32 addrspace(4)*>
+  %cmp = icmp eq <2 x i32 addrspace(4)*> %cast0, %cast1
+  ret <2 x i1> %cmp
+}
+
+attributes #0 = { nounwind }
Index: test/Transforms/InferAddressSpaces/AMDGPU/infer-address-space.ll
===================================================================
--- test/Transforms/InferAddressSpaces/AMDGPU/infer-address-space.ll
+++ test/Transforms/InferAddressSpaces/AMDGPU/infer-address-space.ll
@@ -106,8 +106,7 @@
 ; CHECK-LABEL: @loop(
 
 ; CHECK: %p = bitcast [10 x float] addrspace(3)* @array to float addrspace(3)*
-; CHECK: %0 = addrspacecast float addrspace(3)* %p to float addrspace(4)*
-; CHECK: %end = getelementptr float, float addrspace(4)* %0, i64 10
+; CHECK: %end = getelementptr float, float addrspace(3)* %p, i64 10
 ; CHECK: br label %loop
 
 ; CHECK: loop:                                             ; preds = %loop, %entry
@@ -115,8 +114,8 @@
 ; CHECK: %v = load float, float addrspace(3)* %i
 ; CHECK: call void @use(float %v)
 ; CHECK: %i2 = getelementptr float, float addrspace(3)* %i, i64 1
-; CHECK: %1 = addrspacecast float addrspace(3)* %i2 to float addrspace(4)*
-; CHECK: %exit_cond = icmp eq float addrspace(4)* %1, %end
+; CHECK: %exit_cond = icmp eq float addrspace(3)* %i2, %end
+
 ; CHECK: br i1 %exit_cond, label %exit, label %loop
 define void @loop() #0 {
 entry: