AMDGPU: Add read_exec_lo/hi builtins

[kzhuravl]

LGTM.

[arsenm]

r315238

include/clang/Basic/BuiltinsAMDGPU.def

 //===----------------------------------------------------------------------===//
 
 TARGET_BUILTIN(__builtin_amdgcn_fmed3h, "hhhh", "nc", "gfx9-insts")
 
 //===----------------------------------------------------------------------===//
 // Special builtins.
 //===----------------------------------------------------------------------===//
 BUILTIN(__builtin_amdgcn_read_exec, "LUi", "nc")
+BUILTIN(__builtin_amdgcn_read_exec_lo, "Ui", "nc")
+BUILTIN(__builtin_amdgcn_read_exec_hi, "Ui", "nc")
 
 //===----------------------------------------------------------------------===//
 // R600-NI only builtins.
 //===----------------------------------------------------------------------===//
 
 BUILTIN(__builtin_r600_implicitarg_ptr, "Uc*7", "nc")
 
 BUILTIN(__builtin_r600_read_tgid_x, "Ui", "nc")

lib/CodeGen/CGBuiltin.cpp

Value *CodeGenFunction::EmitAMDGPUBuiltinExpr(unsigned BuiltinID,
   case AMDGPU::BI__builtin_amdgcn_fmed3h:
     return emitTernaryBuiltin(*this, E, Intrinsic::amdgcn_fmed3);
   case AMDGPU::BI__builtin_amdgcn_read_exec: {
     CallInst *CI = cast<CallInst>(
       EmitSpecialRegisterBuiltin(*this, E, Int64Ty, Int64Ty, true, "exec"));
     CI->setConvergent();
     return CI;
   }
+  case AMDGPU::BI__builtin_amdgcn_read_exec_lo:
+  case AMDGPU::BI__builtin_amdgcn_read_exec_hi: {
+    StringRef RegName = BuiltinID == AMDGPU::BI__builtin_amdgcn_read_exec_lo ?
+      "exec_lo" : "exec_hi";
+    CallInst *CI = cast<CallInst>(
+      EmitSpecialRegisterBuiltin(*this, E, Int32Ty, Int32Ty, true, RegName));
+    CI->setConvergent();
+    return CI;
+  }
 
   // amdgcn workitem
   case AMDGPU::BI__builtin_amdgcn_workitem_id_x:
     return emitRangedBuiltin(*this, Intrinsic::amdgcn_workitem_id_x, 0, 1024);
   case AMDGPU::BI__builtin_amdgcn_workitem_id_y:
     return emitRangedBuiltin(*this, Intrinsic::amdgcn_workitem_id_y, 0, 1024);
   case AMDGPU::BI__builtin_amdgcn_workitem_id_z:
     return emitRangedBuiltin(*this, Intrinsic::amdgcn_workitem_id_z, 0, 1024);

test/CodeGenOpenCL/builtins-amdgcn.cl

 // CHECK-LABEL: @test_read_exec(
 // CHECK: call i64 @llvm.read_register.i64(metadata ![[EXEC:[0-9]+]]) #[[READ_EXEC_ATTRS:[0-9]+]]
 void test_read_exec(global ulong* out) {
   *out = __builtin_amdgcn_read_exec();
 }
 
 // CHECK: declare i64 @llvm.read_register.i64(metadata) #[[NOUNWIND_READONLY:[0-9]+]]
 
+// CHECK-LABEL: @test_read_exec_lo(
+// CHECK: call i32 @llvm.read_register.i32(metadata ![[EXEC_LO:[0-9]+]]) #[[READ_EXEC_ATTRS]]
+void test_read_exec_lo(global uint* out) {
+  *out = __builtin_amdgcn_read_exec_lo();
+}
+
+// CHECK-LABEL: @test_read_exec_hi(
+// CHECK: call i32 @llvm.read_register.i32(metadata ![[EXEC_HI:[0-9]+]]) #[[READ_EXEC_ATTRS]]
+void test_read_exec_hi(global uint* out) {
+  *out = __builtin_amdgcn_read_exec_hi();
+}
+
 // CHECK-LABEL: @test_dispatch_ptr
 // CHECK: call i8 addrspace(2)* @llvm.amdgcn.dispatch.ptr()
 void test_dispatch_ptr(__attribute__((address_space(2))) unsigned char ** out)
 {
   *out = __builtin_amdgcn_dispatch_ptr();
 }
 
 // CHECK-LABEL: @test_kernarg_segment_ptr

 {
   *out = __builtin_amdgcn_s_getpc();
 }
 
 // CHECK-DAG: [[WI_RANGE]] = !{i32 0, i32 1024}
 // CHECK-DAG: attributes #[[NOUNWIND_READONLY:[0-9]+]] = { nounwind readonly }
 // CHECK-DAG: attributes #[[READ_EXEC_ATTRS]] = { convergent }
 // CHECK-DAG: ![[EXEC]] = !{!"exec"}
+// CHECK-DAG: ![[EXEC_LO]] = !{!"exec_lo"}
+// CHECK-DAG: ![[EXEC_HI]] = !{!"exec_hi"}