[AMDGPU][InferAddressSpaces] Only rewrite address-spaces that can be trivially casted...

The intrinsic @llvm.amdgcn.flat.atomic.{fadd,fmax,fmin} can only be
selected for flat address spaces (constant, flat and global).

This patch restricts the cases over which GCNTTIImpl::rewriteIntrinsicWithAddressSpace
rewrites the intrinsic.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D149938

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
index 291a5a4..e4b5eac 100644 (file)
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -1082,9 +1082,12 @@ Value *GCNTTIImpl::rewriteIntrinsicWithAddressSpace(IntrinsicInst *II,
   case Intrinsic::amdgcn_flat_atomic_fadd:
   case Intrinsic::amdgcn_flat_atomic_fmax:
   case Intrinsic::amdgcn_flat_atomic_fmin: {
-    Module *M = II->getParent()->getParent()->getParent();
     Type *DestTy = II->getType();
     Type *SrcTy = NewV->getType();
+    unsigned NewAS = SrcTy->getPointerAddressSpace();
+    if (!AMDGPU::isExtendedGlobalAddrSpace(NewAS))
+      return nullptr;
+    Module *M = II->getModule();
     Function *NewDecl = Intrinsic::getDeclaration(M, II->getIntrinsicID(),
                                                   {DestTy, SrcTy, DestTy});
     II->setArgOperand(0, NewV);

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 (file)
index 0000000..b05caa4
--- /dev/null
+++ b/llvm/test/Transforms/InferAddressSpaces/AMDGPU/flat-fadd-fmin-fmax-intrinsics.ll
@@ -0,0 +1,258 @@
+; 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
+}
+
+define amdgpu_kernel void @flat_atomic_fadd_f32_p6(ptr addrspace(6) %ptr, float %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f32_p6
+; CHECK-SAME: (ptr addrspace(6) [[PTR:%.*]], float [[DATA:%.*]]) {
+; CHECK-NEXT:    [[ADD:%.*]] = call float @llvm.amdgcn.flat.atomic.fadd.f32.p6.f32(ptr addrspace(6) [[PTR]], float [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call float @llvm.amdgcn.flat.atomic.fmax.f32.p6.f32(ptr addrspace(6) [[PTR]], float [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call float @llvm.amdgcn.flat.atomic.fmin.f32.p6.f32(ptr addrspace(6) [[PTR]], float [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(6) %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_p7(ptr addrspace(7) %ptr, float %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f32_p7
+; CHECK-SAME: (ptr addrspace(7) [[PTR:%.*]], float [[DATA:%.*]]) {
+; CHECK-NEXT:    [[CAST:%.*]] = addrspacecast ptr addrspace(7) [[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(7) %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_p99(ptr addrspace(99) %ptr, float %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f32_p99
+; CHECK-SAME: (ptr addrspace(99) [[PTR:%.*]], float [[DATA:%.*]]) {
+; CHECK-NEXT:    [[ADD:%.*]] = call float @llvm.amdgcn.flat.atomic.fadd.f32.p99.f32(ptr addrspace(99) [[PTR]], float [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call float @llvm.amdgcn.flat.atomic.fmax.f32.p99.f32(ptr addrspace(99) [[PTR]], float [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call float @llvm.amdgcn.flat.atomic.fmin.f32.p99.f32(ptr addrspace(99) [[PTR]], float [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(99) %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
+}
+
+define amdgpu_kernel void @flat_atomic_fadd_f64_p6(ptr addrspace(6) %ptr, double %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f64_p6
+; CHECK-SAME: (ptr addrspace(6) [[PTR:%.*]], double [[DATA:%.*]]) {
+; CHECK-NEXT:    [[ADD:%.*]] = call double @llvm.amdgcn.flat.atomic.fadd.f64.p6.f64(ptr addrspace(6) [[PTR]], double [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call double @llvm.amdgcn.flat.atomic.fmax.f64.p6.f64(ptr addrspace(6) [[PTR]], double [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call double @llvm.amdgcn.flat.atomic.fmin.f64.p6.f64(ptr addrspace(6) [[PTR]], double [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(6) %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_p7(ptr addrspace(7) %ptr, double %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f64_p7
+; CHECK-SAME: (ptr addrspace(7) [[PTR:%.*]], double [[DATA:%.*]]) {
+; CHECK-NEXT:    [[CAST:%.*]] = addrspacecast ptr addrspace(7) [[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(7) %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_p99(ptr addrspace(99) %ptr, double %data) {
+; CHECK-LABEL: define amdgpu_kernel void @flat_atomic_fadd_f64_p99
+; CHECK-SAME: (ptr addrspace(99) [[PTR:%.*]], double [[DATA:%.*]]) {
+; CHECK-NEXT:    [[ADD:%.*]] = call double @llvm.amdgcn.flat.atomic.fadd.f64.p99.f64(ptr addrspace(99) [[PTR]], double [[DATA]])
+; CHECK-NEXT:    [[MAX:%.*]] = call double @llvm.amdgcn.flat.atomic.fmax.f64.p99.f64(ptr addrspace(99) [[PTR]], double [[DATA]])
+; CHECK-NEXT:    [[MIN:%.*]] = call double @llvm.amdgcn.flat.atomic.fmin.f64.p99.f64(ptr addrspace(99) [[PTR]], double [[DATA]])
+; CHECK-NEXT:    ret void
+;
+  %cast = addrspacecast ptr addrspace(99) %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
+}