diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -1081,6 +1081,12 @@
   case Intrinsic::amdgcn_flat_atomic_fadd:
   case Intrinsic::amdgcn_flat_atomic_fmax:
   case Intrinsic::amdgcn_flat_atomic_fmin: {
+    unsigned OldAS = OldV->getType()->getPointerAddressSpace();
+    unsigned NewAS = NewV->getType()->getPointerAddressSpace();
+    const GCNTargetMachine &TM =
+        static_cast<const GCNTargetMachine &>(getTLI()->getTargetMachine());
+    if (!TM.isNoopAddrSpaceCast(OldAS, NewAS))
+      return nullptr;
     Module *M = II->getParent()->getParent()->getParent();
     Type *DestTy = II->getType();
     Type *SrcTy = NewV->getType();
diff --git a/llvm/test/Transforms/InferAddressSpaces/AMDGPU/flat-fadd-fmin-fmax-intrinsics.ll b/llvm/test/Transforms/InferAddressSpaces/AMDGPU/flat-fadd-fmin-fmax-intrinsics.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/InferAddressSpaces/AMDGPU/flat-fadd-fmin-fmax-intrinsics.ll
@@ -0,0 +1,166 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
+; RUN: opt -S -mtriple=amdgcn-amd-amdhsa -passes=infer-address-spaces %s | FileCheck %s
+
+declare float @llvm.amdgcn.flat.atomic.fadd.f32.p0.f32(ptr %ptr, float %data)
+declare float @llvm.amdgcn.flat.atomic.fmax.f32.p0.f32(ptr %ptr, float %data)
+declare float @llvm.amdgcn.flat.atomic.fmin.f32.p0.f32(ptr %ptr, float %data)
+
+define amdgpu_kernel void @flat_atomic_fadd_f32_p1(ptr addrspace(1) %ptr, float %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f32_p1
+; CHECK-SAME: (ptr addrspace(1) [[PTR:%.*]], float [[DATA:%.*]]) {
+; CHECK-NEXT:    [[ADD:%.*]] = call float @llvm.amdgcn.flat.atomic.fadd.f32.p1.f32(ptr addrspace(1) [[PTR]], float [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call float @llvm.amdgcn.flat.atomic.fmax.f32.p1.f32(ptr addrspace(1) [[PTR]], float [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call float @llvm.amdgcn.flat.atomic.fmin.f32.p1.f32(ptr addrspace(1) [[PTR]], float [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(1) %ptr to ptr
+  %add = call float @llvm.amdgcn.flat.atomic.fadd.f32.p0.f32(ptr %cast, float %data)
+  %max = call float @llvm.amdgcn.flat.atomic.fmax.f32.p0.f32(ptr %cast, float %data)
+  %min = call float @llvm.amdgcn.flat.atomic.fmin.f32.p0.f32(ptr %cast, float %data)
+  ret void
+}
+
+define amdgpu_kernel void @flat_atomic_fadd_f32_p2(ptr addrspace(2) %ptr, float %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f32_p2
+; CHECK-SAME: (ptr addrspace(2) [[PTR:%.*]], float [[DATA:%.*]]) {
+; CHECK-NEXT:    [[CAST:%.*]] = addrspacecast ptr addrspace(2) [[PTR]] to ptr
+; CHECK-NEXT:    [[ADD:%.*]] = call float @llvm.amdgcn.flat.atomic.fadd.f32.p0.f32(ptr [[CAST]], float [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call float @llvm.amdgcn.flat.atomic.fmax.f32.p0.f32(ptr [[CAST]], float [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call float @llvm.amdgcn.flat.atomic.fmin.f32.p0.f32(ptr [[CAST]], float [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(2) %ptr to ptr
+  %add = call float @llvm.amdgcn.flat.atomic.fadd.f32.p0.f32(ptr %cast, float %data)
+  %max = call float @llvm.amdgcn.flat.atomic.fmax.f32.p0.f32(ptr %cast, float %data)
+  %min = call float @llvm.amdgcn.flat.atomic.fmin.f32.p0.f32(ptr %cast, float %data)
+  ret void
+}
+
+define amdgpu_kernel void @flat_atomic_fadd_f32_p3(ptr addrspace(3) %ptr, float %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f32_p3
+; CHECK-SAME: (ptr addrspace(3) [[PTR:%.*]], float [[DATA:%.*]]) {
+; CHECK-NEXT:    [[CAST:%.*]] = addrspacecast ptr addrspace(3) [[PTR]] to ptr
+; CHECK-NEXT:    [[ADD:%.*]] = call float @llvm.amdgcn.flat.atomic.fadd.f32.p0.f32(ptr [[CAST]], float [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call float @llvm.amdgcn.flat.atomic.fmax.f32.p0.f32(ptr [[CAST]], float [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call float @llvm.amdgcn.flat.atomic.fmin.f32.p0.f32(ptr [[CAST]], float [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(3) %ptr to ptr
+  %add = call float @llvm.amdgcn.flat.atomic.fadd.f32.p0.f32(ptr %cast, float %data)
+  %max = call float @llvm.amdgcn.flat.atomic.fmax.f32.p0.f32(ptr %cast, float %data)
+  %min = call float @llvm.amdgcn.flat.atomic.fmin.f32.p0.f32(ptr %cast, float %data)
+  ret void
+}
+
+define amdgpu_kernel void @flat_atomic_fadd_f32_p4(ptr addrspace(4) %ptr, float %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f32_p4
+; CHECK-SAME: (ptr addrspace(4) [[PTR:%.*]], float [[DATA:%.*]]) {
+; CHECK-NEXT:    [[ADD:%.*]] = call float @llvm.amdgcn.flat.atomic.fadd.f32.p4.f32(ptr addrspace(4) [[PTR]], float [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call float @llvm.amdgcn.flat.atomic.fmax.f32.p4.f32(ptr addrspace(4) [[PTR]], float [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call float @llvm.amdgcn.flat.atomic.fmin.f32.p4.f32(ptr addrspace(4) [[PTR]], float [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(4) %ptr to ptr
+  %add = call float @llvm.amdgcn.flat.atomic.fadd.f32.p0.f32(ptr %cast, float %data)
+  %max = call float @llvm.amdgcn.flat.atomic.fmax.f32.p0.f32(ptr %cast, float %data)
+  %min = call float @llvm.amdgcn.flat.atomic.fmin.f32.p0.f32(ptr %cast, float %data)
+  ret void
+}
+
+define amdgpu_kernel void @flat_atomic_fadd_f32_p5(ptr addrspace(5) %ptr, float %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f32_p5
+; CHECK-SAME: (ptr addrspace(5) [[PTR:%.*]], float [[DATA:%.*]]) {
+; CHECK-NEXT:    [[CAST:%.*]] = addrspacecast ptr addrspace(5) [[PTR]] to ptr
+; CHECK-NEXT:    [[ADD:%.*]] = call float @llvm.amdgcn.flat.atomic.fadd.f32.p0.f32(ptr [[CAST]], float [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call float @llvm.amdgcn.flat.atomic.fmax.f32.p0.f32(ptr [[CAST]], float [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call float @llvm.amdgcn.flat.atomic.fmin.f32.p0.f32(ptr [[CAST]], float [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(5) %ptr to ptr
+  %add = call float @llvm.amdgcn.flat.atomic.fadd.f32.p0.f32(ptr %cast, float %data)
+  %max = call float @llvm.amdgcn.flat.atomic.fmax.f32.p0.f32(ptr %cast, float %data)
+  %min = call float @llvm.amdgcn.flat.atomic.fmin.f32.p0.f32(ptr %cast, float %data)
+  ret void
+}
+
+declare double @llvm.amdgcn.flat.atomic.fadd.f64.p0.f64(ptr %ptr, double %data)
+declare double @llvm.amdgcn.flat.atomic.fmax.f64.p0.f64(ptr %ptr, double %data)
+declare double @llvm.amdgcn.flat.atomic.fmin.f64.p0.f64(ptr %ptr, double %data)
+
+define amdgpu_kernel void @flat_atomic_fadd_f64_p1(ptr addrspace(1) %ptr, double %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f64_p1
+; CHECK-SAME: (ptr addrspace(1) [[PTR:%.*]], double [[DATA:%.*]]) {
+; CHECK-NEXT:    [[ADD:%.*]] = call double @llvm.amdgcn.flat.atomic.fadd.f64.p1.f64(ptr addrspace(1) [[PTR]], double [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call double @llvm.amdgcn.flat.atomic.fmax.f64.p1.f64(ptr addrspace(1) [[PTR]], double [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call double @llvm.amdgcn.flat.atomic.fmin.f64.p1.f64(ptr addrspace(1) [[PTR]], double [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(1) %ptr to ptr
+  %add = call double @llvm.amdgcn.flat.atomic.fadd.f64.p0.f64(ptr %cast, double %data)
+  %max = call double @llvm.amdgcn.flat.atomic.fmax.f64.p0.f64(ptr %cast, double %data)
+  %min = call double @llvm.amdgcn.flat.atomic.fmin.f64.p0.f64(ptr %cast, double %data)
+  ret void
+}
+
+define amdgpu_kernel void @flat_atomic_fadd_f64_p2(ptr addrspace(2) %ptr, double %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f64_p2
+; CHECK-SAME: (ptr addrspace(2) [[PTR:%.*]], double [[DATA:%.*]]) {
+; CHECK-NEXT:    [[CAST:%.*]] = addrspacecast ptr addrspace(2) [[PTR]] to ptr
+; CHECK-NEXT:    [[ADD:%.*]] = call double @llvm.amdgcn.flat.atomic.fadd.f64.p0.f64(ptr [[CAST]], double [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call double @llvm.amdgcn.flat.atomic.fmax.f64.p0.f64(ptr [[CAST]], double [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call double @llvm.amdgcn.flat.atomic.fmin.f64.p0.f64(ptr [[CAST]], double [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(2) %ptr to ptr
+  %add = call double @llvm.amdgcn.flat.atomic.fadd.f64.p0.f64(ptr %cast, double %data)
+  %max = call double @llvm.amdgcn.flat.atomic.fmax.f64.p0.f64(ptr %cast, double %data)
+  %min = call double @llvm.amdgcn.flat.atomic.fmin.f64.p0.f64(ptr %cast, double %data)
+  ret void
+}
+
+define amdgpu_kernel void @flat_atomic_fadd_f64_p3(ptr addrspace(3) %ptr, double %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f64_p3
+; CHECK-SAME: (ptr addrspace(3) [[PTR:%.*]], double [[DATA:%.*]]) {
+; CHECK-NEXT:    [[CAST:%.*]] = addrspacecast ptr addrspace(3) [[PTR]] to ptr
+; CHECK-NEXT:    [[ADD:%.*]] = call double @llvm.amdgcn.flat.atomic.fadd.f64.p0.f64(ptr [[CAST]], double [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call double @llvm.amdgcn.flat.atomic.fmax.f64.p0.f64(ptr [[CAST]], double [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call double @llvm.amdgcn.flat.atomic.fmin.f64.p0.f64(ptr [[CAST]], double [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(3) %ptr to ptr
+  %add = call double @llvm.amdgcn.flat.atomic.fadd.f64.p0.f64(ptr %cast, double %data)
+  %max = call double @llvm.amdgcn.flat.atomic.fmax.f64.p0.f64(ptr %cast, double %data)
+  %min = call double @llvm.amdgcn.flat.atomic.fmin.f64.p0.f64(ptr %cast, double %data)
+  ret void
+}
+
+define amdgpu_kernel void @flat_atomic_fadd_f64_p4(ptr addrspace(4) %ptr, double %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f64_p4
+; CHECK-SAME: (ptr addrspace(4) [[PTR:%.*]], double [[DATA:%.*]]) {
+; CHECK-NEXT:    [[ADD:%.*]] = call double @llvm.amdgcn.flat.atomic.fadd.f64.p4.f64(ptr addrspace(4) [[PTR]], double [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call double @llvm.amdgcn.flat.atomic.fmax.f64.p4.f64(ptr addrspace(4) [[PTR]], double [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call double @llvm.amdgcn.flat.atomic.fmin.f64.p4.f64(ptr addrspace(4) [[PTR]], double [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(4) %ptr to ptr
+  %add = call double @llvm.amdgcn.flat.atomic.fadd.f64.p0.f64(ptr %cast, double %data)
+  %max = call double @llvm.amdgcn.flat.atomic.fmax.f64.p0.f64(ptr %cast, double %data)
+  %min = call double @llvm.amdgcn.flat.atomic.fmin.f64.p0.f64(ptr %cast, double %data)
+  ret void
+}
+
+define amdgpu_kernel void @flat_atomic_fadd_f64_p5(ptr addrspace(5) %ptr, double %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f64_p5
+; CHECK-SAME: (ptr addrspace(5) [[PTR:%.*]], double [[DATA:%.*]]) {
+; CHECK-NEXT:    [[CAST:%.*]] = addrspacecast ptr addrspace(5) [[PTR]] to ptr
+; CHECK-NEXT:    [[ADD:%.*]] = call double @llvm.amdgcn.flat.atomic.fadd.f64.p0.f64(ptr [[CAST]], double [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call double @llvm.amdgcn.flat.atomic.fmax.f64.p0.f64(ptr [[CAST]], double [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call double @llvm.amdgcn.flat.atomic.fmin.f64.p0.f64(ptr [[CAST]], double [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(5) %ptr to ptr
+  %add = call double @llvm.amdgcn.flat.atomic.fadd.f64.p0.f64(ptr %cast, double %data)
+  %max = call double @llvm.amdgcn.flat.atomic.fmax.f64.p0.f64(ptr %cast, double %data)
+  %min = call double @llvm.amdgcn.flat.atomic.fmin.f64.p0.f64(ptr %cast, double %data)
+  ret void
+}