Index: lib/Target/AMDGPU/AMDGPUISelLowering.h
===================================================================
--- lib/Target/AMDGPU/AMDGPUISelLowering.h
+++ lib/Target/AMDGPU/AMDGPUISelLowering.h
@@ -280,7 +280,9 @@
   MUL_LOHI_I24,
   MUL_LOHI_U24,
   TEXTURE_FETCH,
-  EXPORT,
+  EXPORT, // exp on SI+
+  EXPORT_DONE, // exp on SI+ with done bit set
+  R600_EXPORT,
   CONST_ADDRESS,
   REGISTER_LOAD,
   REGISTER_STORE,
Index: lib/Target/AMDGPU/AMDGPUISelLowering.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUISelLowering.cpp
+++ lib/Target/AMDGPU/AMDGPUISelLowering.cpp
@@ -2998,6 +2998,8 @@
   NODE_NAME_CASE(MAD_I24)
   NODE_NAME_CASE(TEXTURE_FETCH)
   NODE_NAME_CASE(EXPORT)
+  NODE_NAME_CASE(EXPORT_DONE)
+  NODE_NAME_CASE(R600_EXPORT)
   NODE_NAME_CASE(CONST_ADDRESS)
   NODE_NAME_CASE(REGISTER_LOAD)
   NODE_NAME_CASE(REGISTER_STORE)
Index: lib/Target/AMDGPU/AMDGPUInstrInfo.td
===================================================================
--- lib/Target/AMDGPU/AMDGPUInstrInfo.td
+++ lib/Target/AMDGPU/AMDGPUInstrInfo.td
@@ -265,9 +265,35 @@
                       SDTypeProfile<1, 4, [SDTCisFP<0>]>,
                       [SDNPInGlue]>;
 
+
 def AMDGPUkill : SDNode<"AMDGPUISD::KILL", AMDGPUKillSDT,
   [SDNPHasChain, SDNPSideEffect]>;
 
+// SI+ export
+def AMDGPUExportOp : SDTypeProfile<0, 8, [
+  SDTCisInt<0>, // i8 en
+  SDTCisInt<1>, // i1 vm
+  // skip done
+  SDTCisInt<2>, // i8 tgt
+  SDTCisSameAs<3, 1>, // i1 compr
+  SDTCisFP<4>,        // f32 src0
+  SDTCisSameAs<5, 4>, // f32 src1
+  SDTCisSameAs<6, 4>, // f32 src2
+  SDTCisSameAs<7, 4>  // f32 src3
+]>;
+
+def AMDGPUexport: SDNode<"AMDGPUISD::EXPORT", AMDGPUExportOp,
+  [SDNPHasChain, SDNPMayStore]>;
+
+def AMDGPUexport_done: SDNode<"AMDGPUISD::EXPORT_DONE", AMDGPUExportOp,
+  [SDNPHasChain, SDNPMayLoad, SDNPMayStore]>;
+
+
+def R600ExportOp : SDTypeProfile<0, 7, [SDTCisFP<0>, SDTCisInt<1>]>;
+
+def R600_EXPORT: SDNode<"AMDGPUISD::R600_EXPORT", R600ExportOp,
+  [SDNPHasChain, SDNPSideEffect]>;
+
 //===----------------------------------------------------------------------===//
 // Flow Control Profile Types
 //===----------------------------------------------------------------------===//
Index: lib/Target/AMDGPU/R600ISelLowering.cpp
===================================================================
--- lib/Target/AMDGPU/R600ISelLowering.cpp
+++ lib/Target/AMDGPU/R600ISelLowering.cpp
@@ -443,7 +443,7 @@
         DAG.getConstant(2, DL, MVT::i32), // SWZ_Z
         DAG.getConstant(3, DL, MVT::i32) // SWZ_W
       };
-      return DAG.getNode(AMDGPUISD::EXPORT, DL, Op.getValueType(), Args);
+      return DAG.getNode(AMDGPUISD::R600_EXPORT, DL, Op.getValueType(), Args);
     }
 
     // default for switch(IntrinsicID)
@@ -1882,7 +1882,7 @@
     return SDValue();
   }
 
-  case AMDGPUISD::EXPORT: {
+  case AMDGPUISD::R600_EXPORT: {
     SDValue Arg = N->getOperand(1);
     if (Arg.getOpcode() != ISD::BUILD_VECTOR)
       break;
@@ -1898,7 +1898,7 @@
       N->getOperand(7) // SWZ_W
     };
     NewArgs[1] = OptimizeSwizzle(N->getOperand(1), &NewArgs[4], DAG, DL);
-    return DAG.getNode(AMDGPUISD::EXPORT, DL, N->getVTList(), NewArgs);
+    return DAG.getNode(AMDGPUISD::R600_EXPORT, DL, N->getVTList(), NewArgs);
   }
   case AMDGPUISD::TEXTURE_FETCH: {
     SDValue Arg = N->getOperand(1);
Index: lib/Target/AMDGPU/R600Instructions.td
===================================================================
--- lib/Target/AMDGPU/R600Instructions.td
+++ lib/Target/AMDGPU/R600Instructions.td
@@ -436,11 +436,6 @@
 // Export Instructions
 //===----------------------------------------------------------------------===//
 
-def ExportType : SDTypeProfile<0, 7, [SDTCisFP<0>, SDTCisInt<1>]>;
-
-def EXPORT: SDNode<"AMDGPUISD::EXPORT", ExportType,
-  [SDNPHasChain, SDNPSideEffect]>;
-
 class ExportWord0 {
   field bits<32> Word0;
 
@@ -486,7 +481,7 @@
 }
 
 multiclass ExportPattern<Instruction ExportInst, bits<8> cf_inst> {
-  def : Pat<(EXPORT (v4f32 R600_Reg128:$src), (i32 imm:$base), (i32 imm:$type),
+  def : Pat<(R600_EXPORT (v4f32 R600_Reg128:$src), (i32 imm:$base), (i32 imm:$type),
     (i32 imm:$swz_x), (i32 imm:$swz_y), (i32 imm:$swz_z), (i32 imm:$swz_w)),
         (ExportInst R600_Reg128:$src, imm:$type, imm:$base,
         imm:$swz_x, imm:$swz_y, imm:$swz_z, imm:$swz_w, cf_inst, 0)
Index: lib/Target/AMDGPU/SIISelLowering.cpp
===================================================================
--- lib/Target/AMDGPU/SIISelLowering.cpp
+++ lib/Target/AMDGPU/SIISelLowering.cpp
@@ -2672,6 +2672,29 @@
     SDValue Cast = DAG.getNode(ISD::BITCAST, DL, MVT::i32, Src);
     return DAG.getNode(AMDGPUISD::KILL, DL, MVT::Other, Chain, Cast);
   }
+  case AMDGPUIntrinsic::SI_export: {
+    const ConstantSDNode *En = cast<ConstantSDNode>(Op.getOperand(2));
+    const ConstantSDNode *VM = cast<ConstantSDNode>(Op.getOperand(3));
+    const ConstantSDNode *Done = cast<ConstantSDNode>(Op.getOperand(4));
+    const ConstantSDNode *Tgt = cast<ConstantSDNode>(Op.getOperand(5));
+    const ConstantSDNode *Compr = cast<ConstantSDNode>(Op.getOperand(6));
+
+    const SDValue Ops[] = {
+      Chain,
+      DAG.getTargetConstant(En->getZExtValue(), DL, MVT::i8),
+      DAG.getTargetConstant(VM->getZExtValue(), DL, MVT::i1),
+      DAG.getTargetConstant(Tgt->getZExtValue(), DL, MVT::i8),
+      DAG.getTargetConstant(Compr->getZExtValue(), DL, MVT::i1),
+      Op.getOperand(7), // src0
+      Op.getOperand(8), // src1
+      Op.getOperand(9), // src2
+      Op.getOperand(10) // src3
+    };
+
+    unsigned Opc = Done->isNullValue() ?
+      AMDGPUISD::EXPORT : AMDGPUISD::EXPORT_DONE;
+    return DAG.getNode(Opc, DL, Op->getVTList(), Ops);
+  }
   default:
     return SDValue();
   }
Index: lib/Target/AMDGPU/SIInsertSkips.cpp
===================================================================
--- lib/Target/AMDGPU/SIInsertSkips.cpp
+++ lib/Target/AMDGPU/SIInsertSkips.cpp
@@ -159,16 +159,15 @@
   MachineBasicBlock::iterator Insert = SkipBB->begin();
 
   // Exec mask is zero: Export to NULL target...
-  BuildMI(*SkipBB, Insert, DL, TII->get(AMDGPU::EXP))
-    .addImm(0)
+  BuildMI(*SkipBB, Insert, DL, TII->get(AMDGPU::EXP_DONE))
     .addImm(0x09) // V_008DFC_SQ_EXP_NULL
-    .addImm(0)
-    .addImm(1)
-    .addImm(1)
     .addReg(AMDGPU::VGPR0, RegState::Undef)
     .addReg(AMDGPU::VGPR0, RegState::Undef)
     .addReg(AMDGPU::VGPR0, RegState::Undef)
-    .addReg(AMDGPU::VGPR0, RegState::Undef);
+    .addReg(AMDGPU::VGPR0, RegState::Undef)
+    .addImm(1)  // vm
+    .addImm(0)  // compr
+    .addImm(0); // en
 
   // ... and terminate wavefront.
   BuildMI(*SkipBB, Insert, DL, TII->get(AMDGPU::S_ENDPGM));
Index: lib/Target/AMDGPU/SIInsertWaits.cpp
===================================================================
--- lib/Target/AMDGPU/SIInsertWaits.cpp
+++ lib/Target/AMDGPU/SIInsertWaits.cpp
@@ -195,8 +195,7 @@
   Result.Named.VM = !!(TSFlags & SIInstrFlags::VM_CNT);
 
   // Only consider stores or EXP for EXP_CNT
-  Result.Named.EXP = !!(TSFlags & SIInstrFlags::EXP_CNT &&
-      (MI.getOpcode() == AMDGPU::EXP || MI.getDesc().mayStore()));
+  Result.Named.EXP = !!(TSFlags & SIInstrFlags::EXP_CNT) && MI.mayStore();
 
   // LGKM may uses larger values
   if (TSFlags & SIInstrFlags::LGKM_CNT) {
@@ -340,7 +339,8 @@
 
   // Remember which export instructions we have seen
   if (Increment.Named.EXP) {
-    ExpInstrTypesSeen |= I->getOpcode() == AMDGPU::EXP ? 1 : 2;
+    ExpInstrTypesSeen |=
+      (I->getOpcode() == AMDGPU::EXP ||  I->getOpcode() == AMDGPU::EXP_DONE) ? 1 : 2;
   }
 
   for (unsigned i = 0, e = I->getNumOperands(); i != e; ++i) {
Index: lib/Target/AMDGPU/SIInstrFormats.td
===================================================================
--- lib/Target/AMDGPU/SIInstrFormats.td
+++ lib/Target/AMDGPU/SIInstrFormats.td
@@ -232,6 +232,16 @@
   let hasSideEffects = 0;
 }
 
+class EXPCommon<dag outs, dag ins, string asm, list<dag> pattern> :
+  InstSI<outs, ins, asm, pattern> {
+  let EXP_CNT = 1;
+  let mayLoad = 0; // Set to 1 if done bit is set.
+  let mayStore = 1;
+  let UseNamedOperandTable = 1;
+  let Uses = [EXEC];
+  let SchedRW = [WriteExport];
+}
+
 } // End Uses = [EXEC]
 
 class MIMG <dag outs, dag ins, string asm, list<dag> pattern> :
Index: lib/Target/AMDGPU/SIInstrInfo.td
===================================================================
--- lib/Target/AMDGPU/SIInstrInfo.td
+++ lib/Target/AMDGPU/SIInstrInfo.td
@@ -518,32 +518,39 @@
 // EXP classes
 //===----------------------------------------------------------------------===//
 
-class EXPCommon : InstSI<
+class EXP_Helper<bit done, SDPatternOperator node = null_frag> : EXPCommon<
   (outs),
-  (ins i32imm:$en, i32imm:$tgt, i32imm:$compr, i32imm:$done, i32imm:$vm,
-       VGPR_32:$src0, VGPR_32:$src1, VGPR_32:$src2, VGPR_32:$src3),
-  "exp $en, $tgt, $compr, $done, $vm, $src0, $src1, $src2, $src3",
-  [] > {
-
-  let EXP_CNT = 1;
-  let Uses = [EXEC];
-  let SchedRW = [WriteExport];
-}
-
-multiclass EXP_m {
-
-  let isPseudo = 1, isCodeGenOnly = 1 in {
-    def "" : EXPCommon, SIMCInstr <"exp", SIEncodingFamily.NONE> ;
-  }
-
-  def _si : EXPCommon, SIMCInstr <"exp", SIEncodingFamily.SI>, EXPe {
-    let DecoderNamespace="SICI";
-    let DisableDecoder = DisableSIDecoder;
-  }
+  (ins i8imm:$tgt, VGPR_32:$src0, VGPR_32:$src1, VGPR_32:$src2, VGPR_32:$src3,
+       i1imm:$vm, i1imm:$compr, i8imm:$en),
+  "exp $en, $tgt, $compr, "#!if(done, "1", "0")#", $vm, $src0, $src1, $src2, $src3",
+  [(node (i8 timm:$en), (i1 timm:$vm), (i8 timm:$tgt), (i1 timm:$compr),
+         f32:$src0, f32:$src1, f32:$src2, f32:$src3)]
+>;
 
-  def _vi : EXPCommon, SIMCInstr <"exp", SIEncodingFamily.VI>, EXPe_vi {
-    let DecoderNamespace="VI";
-    let DisableDecoder = DisableVIDecoder;
+// Split EXP instruction into EXP and EXP_DONE so we can set
+// mayLoad for done=1.
+multiclass EXP_m<bit done, SDPatternOperator node> {
+  let mayLoad = done in {
+    let isPseudo = 1, isCodeGenOnly = 1 in {
+      def "" : EXP_Helper<done, node>,
+               SIMCInstr <"exp"#!if(done, "_done", ""), SIEncodingFamily.NONE>;
+    }
+
+    let done = done in {
+      def _si : EXP_Helper<done>,
+                SIMCInstr <"exp"#!if(done, "_done", ""), SIEncodingFamily.SI>,
+                EXPe {
+        let DecoderNamespace = "SICI";
+        let DisableDecoder = DisableSIDecoder;
+      }
+
+      def _vi : EXP_Helper<done>,
+                SIMCInstr <"exp"#!if(done, "_done", ""), SIEncodingFamily.VI>,
+                EXPe_vi {
+        let DecoderNamespace = "VI";
+        let DisableDecoder = DisableVIDecoder;
+      }
+    }
   }
 }
 
Index: lib/Target/AMDGPU/SIInstructions.td
===================================================================
--- lib/Target/AMDGPU/SIInstructions.td
+++ lib/Target/AMDGPU/SIInstructions.td
@@ -37,7 +37,8 @@
 // EXP Instructions
 //===----------------------------------------------------------------------===//
 
-defm EXP : EXP_m;
+defm EXP : EXP_m<0, AMDGPUexport>;
+defm EXP_DONE : EXP_m<1, AMDGPUexport_done>;
 
 //===----------------------------------------------------------------------===//
 // VINTRP Instructions
@@ -388,13 +389,6 @@
   (SI_KILL (i32 0xbf800000))
 >;
 
-def : Pat <
-  (int_SI_export imm:$en, imm:$vm, imm:$done, imm:$tgt, imm:$compr,
-                 f32:$src0, f32:$src1, f32:$src2, f32:$src3),
-  (EXP imm:$en, imm:$tgt, imm:$compr, imm:$done, imm:$vm,
-       $src0, $src1, $src2, $src3)
->;
-
 //===----------------------------------------------------------------------===//
 // VOP1 Patterns
 //===----------------------------------------------------------------------===//
Index: lib/Target/AMDGPU/SIIntrinsics.td
===================================================================
--- lib/Target/AMDGPU/SIIntrinsics.td
+++ lib/Target/AMDGPU/SIIntrinsics.td
@@ -15,7 +15,20 @@
 
 let TargetPrefix = "SI", isTarget = 1 in {
   def int_SI_packf16 : Intrinsic <[llvm_i32_ty], [llvm_float_ty, llvm_float_ty], [IntrNoMem]>;
-  def int_SI_export : Intrinsic <[], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty, llvm_float_ty], []>;
+
+  def int_SI_export : Intrinsic <[],
+    [llvm_i32_ty,   // en
+    llvm_i32_ty,    // vm   (FIXME: should be i1)
+    llvm_i32_ty,    // done (FIXME: should be i1)
+    llvm_i32_ty,    // tgt
+    llvm_i32_ty,    // compr (FIXME: should be i1)
+    llvm_float_ty,  // src0
+    llvm_float_ty,  // src1
+    llvm_float_ty,  // src2
+    llvm_float_ty], // src3
+    []
+  >;
+
   def int_SI_load_const : Intrinsic <[llvm_float_ty], [llvm_anyint_ty, llvm_i32_ty], [IntrNoMem]>;
   def int_SI_vs_load_input : Intrinsic <[llvm_v4f32_ty], [llvm_anyint_ty, llvm_i16_ty, llvm_i32_ty], [IntrNoMem]> ;
 
Index: test/CodeGen/AMDGPU/ret.ll
===================================================================
--- test/CodeGen/AMDGPU/ret.ll
+++ test/CodeGen/AMDGPU/ret.ll
@@ -6,7 +6,7 @@
 ; GCN-LABEL: {{^}}vgpr:
 ; GCN: v_mov_b32_e32 v1, v0
 ; GCN-DAG: v_add_f32_e32 v0, 1.0, v1
-; GCN-DAG: exp 15, 0, 1, 1, 1, v1, v1, v1, v1
+; GCN-DAG: exp 15, 0, -1, 1, -1, v1, v1, v1, v1
 ; GCN: s_waitcnt expcnt(0)
 ; GCN-NOT: s_endpgm
 define amdgpu_vs {float, float} @vgpr([9 x <16 x i8>] addrspace(2)* byval, i32 inreg, i32 inreg, float) {
@@ -19,7 +19,7 @@
 
 ; GCN-LABEL: {{^}}vgpr_literal:
 ; GCN: v_mov_b32_e32 v4, v0
-; GCN: exp 15, 0, 1, 1, 1, v4, v4, v4, v4
+; GCN: exp 15, 0, -1, 1, -1, v4, v4, v4, v4
 ; GCN-DAG: v_mov_b32_e32 v0, 1.0
 ; GCN-DAG: v_mov_b32_e32 v1, 2.0
 ; GCN-DAG: v_mov_b32_e32 v2, 4.0
@@ -209,7 +209,7 @@
 
 ; GCN-LABEL: {{^}}both:
 ; GCN: v_mov_b32_e32 v1, v0
-; GCN-DAG: exp 15, 0, 1, 1, 1, v1, v1, v1, v1
+; GCN-DAG: exp 15, 0, -1, 1, -1, v1, v1, v1, v1
 ; GCN-DAG: v_add_f32_e32 v0, 1.0, v1
 ; GCN-DAG: s_add_i32 s0, s3, 2
 ; GCN-DAG: s_mov_b32 s1, s2
@@ -231,7 +231,7 @@
 
 ; GCN-LABEL: {{^}}structure_literal:
 ; GCN: v_mov_b32_e32 v3, v0
-; GCN: exp 15, 0, 1, 1, 1, v3, v3, v3, v3
+; GCN: exp 15, 0, -1, 1, -1, v3, v3, v3, v3
 ; GCN-DAG: v_mov_b32_e32 v0, 1.0
 ; GCN-DAG: s_mov_b32 s0, 2
 ; GCN-DAG: s_mov_b32 s1, 3
Index: test/CodeGen/MIR/AMDGPU/movrels-bug.mir
===================================================================
--- test/CodeGen/MIR/AMDGPU/movrels-bug.mir
+++ test/CodeGen/MIR/AMDGPU/movrels-bug.mir
@@ -25,7 +25,7 @@
     %m0 = S_MOV_B32 undef %sgpr0
     %vgpr1 = V_MOVRELS_B32_e32 undef %vgpr1, implicit %m0, implicit %exec, implicit killed %vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8
     %vgpr4 = V_MAC_F32_e32 undef %vgpr0, undef %vgpr0, undef %vgpr4, implicit %exec
-    EXP 15, 12, 0, 1, 0, undef %vgpr0, killed %vgpr1, killed %vgpr4, undef %vgpr0, implicit %exec
+    EXP_DONE 15, undef %vgpr0, killed %vgpr1, killed %vgpr4, undef %vgpr0, 0, 0, 12, implicit %exec
     S_ENDPGM
 
 ...