Index: include/llvm/IR/IntrinsicsAMDGPU.td
===================================================================
--- include/llvm/IR/IntrinsicsAMDGPU.td
+++ include/llvm/IR/IntrinsicsAMDGPU.td
@@ -392,6 +392,14 @@
   GCCBuiltin<"__builtin_amdgcn_lerp">,
   Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty], [IntrNoMem]>;
 
+def int_amdgcn_readfirstlane :
+  GCCBuiltin<"__builtin_amdgcn_readfirstlane">,
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem, IntrConvergent]>;
+
+def int_amdgcn_readlane :
+  GCCBuiltin<"__builtin_amdgcn_readlane">,
+  Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty], [IntrNoMem, IntrConvergent]>;
+
 //===----------------------------------------------------------------------===//
 // CI+ Intrinsics
 //===----------------------------------------------------------------------===//
Index: lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.h
===================================================================
--- lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.h
+++ lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.h
@@ -56,6 +56,7 @@
 
     MCOperand decodeOperand_VGPR_32(unsigned Val) const;
     MCOperand decodeOperand_VS_32(unsigned Val) const;
+    MCOperand decodeOperand_VM0_32(unsigned Val) const;
     MCOperand decodeOperand_VS_64(unsigned Val) const;
 
     MCOperand decodeOperand_VReg_64(unsigned Val) const;
Index: lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.cpp
===================================================================
--- lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.cpp
+++ lib/Target/AMDGPU/Disassembler/AMDGPUDisassembler.cpp
@@ -61,6 +61,7 @@
 
 DECODE_OPERAND(VGPR_32)
 DECODE_OPERAND(VS_32)
+DECODE_OPERAND(VM0_32)
 DECODE_OPERAND(VS_64)
 
 DECODE_OPERAND(VReg_64)
@@ -230,6 +231,10 @@
   return decodeSrcOp(OPW32, Val);
 }
 
+MCOperand AMDGPUDisassembler::decodeOperand_VM0_32(unsigned Val) const {
+  return decodeSrcOp(OPW32, Val);
+}
+
 MCOperand AMDGPUDisassembler::decodeOperand_VS_64(unsigned Val) const {
   return decodeSrcOp(OPW64, Val);
 }
Index: lib/Target/AMDGPU/SIInstructions.td
===================================================================
--- lib/Target/AMDGPU/SIInstructions.td
+++ lib/Target/AMDGPU/SIInstructions.td
@@ -1220,9 +1220,9 @@
 def V_READFIRSTLANE_B32 : VOP1 <
   0x00000002,
   (outs SReg_32:$vdst),
-  (ins VS_32:$src0),
+  (ins VM0_32:$src0),
   "v_readfirstlane_b32 $vdst, $src0",
-  []
+  [(set i32:$vdst, (int_amdgcn_readfirstlane i32:$src0))]
 > {
   let isConvergent = 1;
 }
@@ -1593,8 +1593,9 @@
   vop3 <0x001, 0x289>,
   "v_readlane_b32",
   (outs SReg_32:$vdst),
-  (ins VS_32:$src0, SCSrc_32:$src1),
-  "v_readlane_b32 $vdst, $src0, $src1"
+  (ins VM0_32:$src0, SCSrc_32:$src1),
+  "v_readlane_b32 $vdst, $src0, $src1",
+  [(set i32:$vdst, (int_amdgcn_readlane i32:$src0, i32:$src1))]
 >;
 
 defm V_WRITELANE_B32 : VOP2SI_3VI_m <
Index: lib/Target/AMDGPU/SIRegisterInfo.td
===================================================================
--- lib/Target/AMDGPU/SIRegisterInfo.td
+++ lib/Target/AMDGPU/SIRegisterInfo.td
@@ -380,6 +380,10 @@
 
 def VS_32 : RegisterClass<"AMDGPU", [i32, f32], 32, (add VGPR_32, SReg_32)>;
 
+def VM0_32 : RegisterClass<"AMDGPU", [i32, f32], 32, (add VGPR_32, M0)> {
+  let isAllocatable = 0;
+}
+
 def VS_64 : RegisterClass<"AMDGPU", [i64, f64], 32, (add VReg_64, SReg_64)> {
   let CopyCost = 2;
 }
Index: test/CodeGen/AMDGPU/llvm.amdgcn.readfirstlane.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/llvm.amdgcn.readfirstlane.ll
@@ -0,0 +1,36 @@
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck %s
+
+declare i32 @llvm.amdgcn.readfirstlane(i32) #0
+
+; CHECK-LABEL: {{^}}test_readfirstlane:
+; CHECK: v_readfirstlane_b32 s{{[0-9]+}}, v{{[0-9]+}}
+define void @test_readfirstlane(i32 addrspace(1)* %out, i32 %src) #1 {
+  %readfirstlane = call i32 @llvm.amdgcn.readfirstlane(i32 %src)
+  store i32 %readfirstlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: {{^}}test_readfirstlane_imm:
+; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], 32
+; CHECK: v_readfirstlane_b32 s{{[0-9]+}}, [[VVAL]]
+define void @test_readfirstlane_imm(i32 addrspace(1)* %out) #1 {
+  %readfirstlane = call i32 @llvm.amdgcn.readfirstlane(i32 32)
+  store i32 %readfirstlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; TODO: m0 should be folded.
+; CHECK-LABEL: {{^}}test_readfirstlane_m0:
+; CHECK: s_mov_b32 m0, -1
+; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], m0
+; CHECK: v_readfirstlane_b32 s{{[0-9]+}}, [[VVAL]]
+define void @test_readfirstlane_m0(i32 addrspace(1)* %out) #1 {
+  %m0 = call i32 asm "s_mov_b32 m0, -1", "={M0}"()
+  %readfirstlane = call i32 @llvm.amdgcn.readfirstlane(i32 %m0)
+  store i32 %readfirstlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+attributes #0 = { nounwind readnone convergent }
+attributes #1 = { nounwind }
+
Index: test/CodeGen/AMDGPU/llvm.amdgcn.readlane.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/llvm.amdgcn.readlane.ll
@@ -0,0 +1,43 @@
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck %s
+
+declare i32 @llvm.amdgcn.readlane(i32, i32) #0
+
+; CHECK-LABEL: {{^}}test_readlane_sreg:
+; CHECK: v_readlane_b32 s{{[0-9]+}}, v{{[0-9]+}}, s{{[0-9]+}}
+define void @test_readlane_sreg(i32 addrspace(1)* %out, i32 %src0, i32 %src1) #1 {
+  %readlane = call i32 @llvm.amdgcn.readlane(i32 %src0, i32 %src1)
+  store i32 %readlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: {{^}}test_readlane_imm_sreg:
+; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], 32
+; CHECK: v_readlane_b32 s{{[0-9]+}}, [[VVAL]], s{{[0-9]+}}
+define void @test_readlane_imm_sreg(i32 addrspace(1)* %out, i32 %src1) #1 {
+  %readlane = call i32 @llvm.amdgcn.readlane(i32 32, i32 %src1)
+  store i32 %readlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; TODO: m0 should be folded.
+; CHECK-LABEL: {{^}}test_readlane_m0_sreg:
+; CHECK: s_mov_b32 m0, -1
+; CHECK: v_mov_b32_e32 [[VVAL:v[0-9]]], m0
+; CHECK: v_readlane_b32 s{{[0-9]+}}, [[VVAL]], s{{[0-9]+}}
+define void @test_readlane_m0_sreg(i32 addrspace(1)* %out, i32 %src1) #1 {
+  %m0 = call i32 asm "s_mov_b32 m0, -1", "={M0}"()
+  %readlane = call i32 @llvm.amdgcn.readlane(i32 %m0, i32 %src1)
+  store i32 %readlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+; CHECK-LABEL: {{^}}test_readlane_imm:
+; CHECK: v_readlane_b32 s{{[0-9]+}}, v{{[0-9]+}}, 32
+define void @test_readlane_imm(i32 addrspace(1)* %out, i32 %src0) #1 {
+  %readlane = call i32 @llvm.amdgcn.readlane(i32 %src0, i32 32) #0
+  store i32 %readlane, i32 addrspace(1)* %out, align 4
+  ret void
+}
+
+attributes #0 = { nounwind readnone convergent }
+attributes #1 = { nounwind }