Index: lib/Target/AMDGPU/AMDGPUISelLowering.h
===================================================================
--- lib/Target/AMDGPU/AMDGPUISelLowering.h
+++ lib/Target/AMDGPU/AMDGPUISelLowering.h
@@ -326,6 +326,8 @@
   ATOMIC_INC,
   ATOMIC_DEC,
   SBUFFER_LOAD,
+  BUFFER_LOAD,
+  BUFFER_LOAD_FORMAT,
   LAST_AMDGPU_ISD_NUMBER
 };
 
Index: lib/Target/AMDGPU/AMDGPUISelLowering.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -3036,6 +3036,8 @@
   NODE_NAME_CASE(ATOMIC_INC)
   NODE_NAME_CASE(ATOMIC_DEC)
   NODE_NAME_CASE(SBUFFER_LOAD)
+  NODE_NAME_CASE(BUFFER_LOAD)
+  NODE_NAME_CASE(BUFFER_LOAD_FORMAT)
   case AMDGPUISD::LAST_AMDGPU_ISD_NUMBER: break;
   }
   return nullptr;
Index: lib/Target/AMDGPU/BUFInstructions.td
===================================================================
--- lib/Target/AMDGPU/BUFInstructions.td
+++ lib/Target/AMDGPU/BUFInstructions.td
@@ -759,12 +759,12 @@
   >;
 }
 
-defm : MUBUF_LoadIntrinsicPat<int_amdgcn_buffer_load_format, f32, "BUFFER_LOAD_FORMAT_X">;
-defm : MUBUF_LoadIntrinsicPat<int_amdgcn_buffer_load_format, v2f32, "BUFFER_LOAD_FORMAT_XY">;
-defm : MUBUF_LoadIntrinsicPat<int_amdgcn_buffer_load_format, v4f32, "BUFFER_LOAD_FORMAT_XYZW">;
-defm : MUBUF_LoadIntrinsicPat<int_amdgcn_buffer_load, f32, "BUFFER_LOAD_DWORD">;
-defm : MUBUF_LoadIntrinsicPat<int_amdgcn_buffer_load, v2f32, "BUFFER_LOAD_DWORDX2">;
-defm : MUBUF_LoadIntrinsicPat<int_amdgcn_buffer_load, v4f32, "BUFFER_LOAD_DWORDX4">;
+defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format, f32, "BUFFER_LOAD_FORMAT_X">;
+defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format, v2f32, "BUFFER_LOAD_FORMAT_XY">;
+defm : MUBUF_LoadIntrinsicPat<SIbuffer_load_format, v4f32, "BUFFER_LOAD_FORMAT_XYZW">;
+defm : MUBUF_LoadIntrinsicPat<SIbuffer_load, f32, "BUFFER_LOAD_DWORD">;
+defm : MUBUF_LoadIntrinsicPat<SIbuffer_load, v2f32, "BUFFER_LOAD_DWORDX2">;
+defm : MUBUF_LoadIntrinsicPat<SIbuffer_load, v4f32, "BUFFER_LOAD_DWORDX4">;
 
 multiclass MUBUF_StoreIntrinsicPat<SDPatternOperator name, ValueType vt,
                                    string opcode> {
Index: lib/Target/AMDGPU/SIISelLowering.cpp
===================================================================
--- lib/Target/AMDGPU/SIISelLowering.cpp
+++ lib/Target/AMDGPU/SIISelLowering.cpp
@@ -2693,6 +2693,7 @@
 SDValue SITargetLowering::LowerINTRINSIC_W_CHAIN(SDValue Op,
                                                  SelectionDAG &DAG) const {
   unsigned IntrID = cast<ConstantSDNode>(Op.getOperand(1))->getZExtValue();
+  SDLoc DL(Op);
   switch (IntrID) {
   case Intrinsic::amdgcn_atomic_inc:
   case Intrinsic::amdgcn_atomic_dec: {
@@ -2708,6 +2709,31 @@
     return DAG.getMemIntrinsicNode(Opc, SDLoc(Op), M->getVTList(), Ops,
                                    M->getMemoryVT(), M->getMemOperand());
   }
+  case Intrinsic::amdgcn_buffer_load:
+  case Intrinsic::amdgcn_buffer_load_format: {
+    SDValue Ops[] = {
+      Op.getOperand(0), // Chain
+      Op.getOperand(2), // rsrc
+      Op.getOperand(3), // vindex
+      Op.getOperand(4), // offset
+      Op.getOperand(5), // glc
+      Op.getOperand(6), // slc
+    };
+    MachineFunction &MF = DAG.getMachineFunction();
+    SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
+
+    unsigned Opc = (IntrID == Intrinsic::amdgcn_buffer_load) ?
+        AMDGPUISD::BUFFER_LOAD : AMDGPUISD::BUFFER_LOAD_FORMAT;
+    EVT VT = Op.getValueType();
+    EVT IntVT = VT.changeTypeToInteger();
+
+    MachineMemOperand *MMO = MF.getMachineMemOperand(
+      MachinePointerInfo(MFI->getBufferPSV()),
+      MachineMemOperand::MOLoad,
+      VT.getStoreSize(), VT.getStoreSize());
+
+    return DAG.getMemIntrinsicNode(Opc, DL, Op->getVTList(), Ops, IntVT, MMO);
+  }
   default:
     return SDValue();
   }
Index: lib/Target/AMDGPU/SIInstrInfo.td
===================================================================
--- lib/Target/AMDGPU/SIInstrInfo.td
+++ lib/Target/AMDGPU/SIInstrInfo.td
@@ -53,6 +53,19 @@
   [SDNPMayStore, SDNPMemOperand, SDNPHasChain]
 >;
 
+def SDTBufferLoad : SDTypeProfile<1, 5,
+    [                    // vdata
+     SDTCisVT<1, v4i32>, // rsrc
+     SDTCisVT<2, i32>,   // vindex
+     SDTCisVT<3, i32>,   // offset
+     SDTCisVT<4, i1>,    // glc
+     SDTCisVT<5, i1>]>;  // slc
+
+def SIbuffer_load : SDNode <"AMDGPUISD::BUFFER_LOAD", SDTBufferLoad,
+                            [SDNPMemOperand, SDNPHasChain, SDNPMayLoad]>;
+def SIbuffer_load_format : SDNode <"AMDGPUISD::BUFFER_LOAD_FORMAT", SDTBufferLoad,
+                            [SDNPMemOperand, SDNPHasChain, SDNPMayLoad]>;
+
 def SIload_input : SDNode<"AMDGPUISD::LOAD_INPUT",
   SDTypeProfile<1, 3, [SDTCisVT<0, v4f32>, SDTCisVT<1, v4i32>, SDTCisVT<2, i16>,
                        SDTCisVT<3, i32>]>
Index: lib/Target/AMDGPU/SIMachineFunctionInfo.h
===================================================================
--- lib/Target/AMDGPU/SIMachineFunctionInfo.h
+++ lib/Target/AMDGPU/SIMachineFunctionInfo.h
@@ -47,6 +47,29 @@
   }
 };
 
+class AMDGPUBufferPseudoSourceValue : public PseudoSourceValue {
+public:
+  explicit AMDGPUBufferPseudoSourceValue() :
+    PseudoSourceValue(PseudoSourceValue::TargetCustom) { }
+
+  bool isConstant(const MachineFrameInfo *) const override {
+    // This should probably be true for most images, but we will start by being
+    // conservative.
+    return false;
+  }
+
+  bool isAliased(const MachineFrameInfo *) const override {
+    // FIXME: If we ever change image intrinsics to accept fat pointers, then
+    // this could be true for some cases.
+    return false;
+  }
+
+  bool mayAlias(const MachineFrameInfo*) const override {
+    // FIXME: If we ever change image intrinsics to accept fat pointers, then
+    // this could be true for some cases.
+    return false;
+  }
+};
 
 /// This class keeps track of the SPI_SP_INPUT_ADDR config register, which
 /// tells the hardware which interpolation parameters to load.
@@ -98,6 +121,7 @@
   // Stack object indices for work item IDs.
   std::array<int, 3> DebuggerWorkItemIDStackObjectIndices;
 
+  std::unique_ptr<AMDGPUBufferPseudoSourceValue> BufferPSV;
   std::unique_ptr<AMDGPUImagePseudoSourceValue> ImagePSV;
 
 public:
@@ -462,6 +486,10 @@
     llvm_unreachable("unexpected dimension");
   }
 
+  AMDGPUBufferPseudoSourceValue *getBufferPSV() {
+    return BufferPSV.get();
+  }
+
   AMDGPUImagePseudoSourceValue *getImagePSV() {
     return ImagePSV.get();
   }
Index: lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
===================================================================
--- lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
+++ lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
@@ -52,6 +52,7 @@
     WavesPerEU(0, 0),
     DebuggerWorkGroupIDStackObjectIndices({{0, 0, 0}}),
     DebuggerWorkItemIDStackObjectIndices({{0, 0, 0}}),
+    BufferPSV(llvm::make_unique<AMDGPUBufferPseudoSourceValue>()),
     ImagePSV(llvm::make_unique<AMDGPUImagePseudoSourceValue>()),
     LDSWaveSpillSize(0),
     PSInputEna(0),
Index: test/CodeGen/AMDGPU/llvm.amdgcn.buffer.load.ll
===================================================================
--- test/CodeGen/AMDGPU/llvm.amdgcn.buffer.load.ll
+++ test/CodeGen/AMDGPU/llvm.amdgcn.buffer.load.ll
@@ -112,6 +112,20 @@
   ret <4 x float> %data
 }
 
+; SI won't merge ds memory operations, because of the signed offset bug, so
+; we only have check lines for VI.
+; VI-LABEL: buffer_load_mmo
+; VI: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0
+; VI: ds_write2_b32 v{{[0-9]+}}, [[ZERO]], [[ZERO]] offset1:4
+define amdgpu_ps float @buffer_load_mmo(<4 x i32> inreg %rsrc, float addrspace(3)* %lds) {
+entry:
+  store float 0.0, float addrspace(3)* %lds
+  %val = call float @llvm.amdgcn.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 0, i1 0, i1 0)
+  %tmp2 = getelementptr float, float addrspace(3)* %lds, i32 4
+  store float 0.0, float addrspace(3)* %tmp2
+  ret float %val
+}
+
 declare float @llvm.amdgcn.buffer.load.f32(<4 x i32>, i32, i32, i1, i1) #0
 declare <2 x float> @llvm.amdgcn.buffer.load.v2f32(<4 x i32>, i32, i32, i1, i1) #0
 declare <4 x float> @llvm.amdgcn.buffer.load.v4f32(<4 x i32>, i32, i32, i1, i1) #0