Index: flang/lib/Lower/OpenMP.cpp
===================================================================
--- flang/lib/Lower/OpenMP.cpp
+++ flang/lib/Lower/OpenMP.cpp
@@ -504,14 +504,19 @@
   if (eval.lowerAsUnstructured() && !outerCombined)
     createEmptyRegionBlocks(firOpBuilder, eval.getNestedEvaluations());
 
+  if constexpr (std::is_same_v<Op, omp::SingleOp>) {
+    // FIXME: Emit an implicit barrier at the end if no 'nowait' clause was
+    // specified and no 'copyprivate' clause.
+    if (!op.nowaitAttr())
+      firOpBuilder.create<mlir::omp::BarrierOp>(loc);
+  }
+
   // Insert the terminator.
   if constexpr (std::is_same_v<Op, omp::WsLoopOp> ||
-                std::is_same_v<Op, omp::SimdLoopOp>) {
-    mlir::ValueRange results;
-    firOpBuilder.create<mlir::omp::YieldOp>(loc, results);
-  } else {
+                std::is_same_v<Op, omp::SimdLoopOp>)
+    firOpBuilder.create<mlir::omp::YieldOp>(loc, mlir::ValueRange());
+  else
     firOpBuilder.create<mlir::omp::TerminatorOp>(loc);
-  }
 
   // Reset the insert point to before the terminator.
   resetBeforeTerminator(firOpBuilder, storeOp, block);
@@ -824,7 +829,8 @@
   } else if (blockDirective.v == llvm::omp::OMPD_single) {
     auto singleOp = firOpBuilder.create<mlir::omp::SingleOp>(
         currentLocation, allocateOperands, allocatorOperands, nowaitAttr);
-    createBodyOfOp<omp::SingleOp>(singleOp, converter, currentLocation, eval);
+    createBodyOfOp<omp::SingleOp>(singleOp, converter, currentLocation, eval,
+                                  &opClauseList);
   } else if (blockDirective.v == llvm::omp::OMPD_ordered) {
     auto orderedOp = firOpBuilder.create<mlir::omp::OrderedRegionOp>(
         currentLocation, /*simd=*/nullptr);
@@ -838,7 +844,7 @@
         allocatorOperands);
     createBodyOfOp(taskOp, converter, currentLocation, eval, &opClauseList);
   } else if (blockDirective.v == llvm::omp::OMPD_taskgroup) {
-      // TODO: Add task_reduction support
+    // TODO: Add task_reduction support
     auto taskGroupOp = firOpBuilder.create<mlir::omp::TaskGroupOp>(
         currentLocation, /*task_reduction_vars=*/ValueRange(),
         /*task_reductions=*/nullptr, allocateOperands, allocatorOperands);
Index: flang/test/Lower/OpenMP/default-clause.f90
===================================================================
--- flang/test/Lower/OpenMP/default-clause.f90
+++ flang/test/Lower/OpenMP/default-clause.f90
@@ -268,6 +268,7 @@
 !CHECK: omp.single {
 !CHECK: %[[temp:.*]] = fir.load %[[PRIVATE_Y]] : !fir.ref<i32>
 !CHECK: fir.store %[[temp]] to %[[PRIVATE_X]] : !fir.ref<i32>
+!CHECK: omp.barrier
 !CHECK: omp.terminator
 !CHECK: }
 !CHECK: omp.terminator
Index: flang/test/Lower/OpenMP/single.f90
===================================================================
--- flang/test/Lower/OpenMP/single.f90
+++ flang/test/Lower/OpenMP/single.f90
@@ -1,25 +1,26 @@
-!RUN: %flang_fc1 -emit-fir -fopenmp %s -o - | FileCheck %s --check-prefixes="FIRDialect,OMPDialect"
-!RUN: %flang_fc1 -emit-fir -fopenmp %s -o - | fir-opt --cfg-conversion | fir-opt --fir-to-llvm-ir | FileCheck %s --check-prefixes="LLVMDialect,OMPDialect"
+!RUN: %flang_fc1 -emit-fir -fopenmp %s -o - | FileCheck %s
+!RUN: bbc -emit-fir -fopenmp %s -o - | FileCheck %s
 
 !===============================================================================
 ! Single construct
 !===============================================================================
 
-!FIRDialect-LABEL: func @_QPomp_single
-!FIRDialect-SAME: (%[[x:.*]]: !fir.ref<i32> {fir.bindc_name = "x"})
+!CHECK-LABEL: func @_QPomp_single
+!CHECK-SAME: (%[[x:.*]]: !fir.ref<i32> {fir.bindc_name = "x"})
 subroutine omp_single(x)
   integer, intent(inout) :: x
-  !OMPDialect: omp.parallel
+  !CHECK: omp.parallel
   !$omp parallel
-  !OMPDialect: omp.single
+  !CHECK: omp.single
   !$omp single
-    !FIRDialect: %[[xval:.*]] = fir.load %[[x]] : !fir.ref<i32>
-    !FIRDialect: %[[res:.*]] = arith.addi %[[xval]], %{{.*}} : i32
-    !FIRDialect: fir.store %[[res]] to %[[x]] : !fir.ref<i32>
+    !CHECK: %[[xval:.*]] = fir.load %[[x]] : !fir.ref<i32>
+    !CHECK: %[[res:.*]] = arith.addi %[[xval]], %{{.*}} : i32
+    !CHECK: fir.store %[[res]] to %[[x]] : !fir.ref<i32>
     x = x + 12
-  !OMPDialect: omp.terminator
+  !CHECK: omp.barrier
+  !CHECK: omp.terminator
   !$omp end single
-  !OMPDialect: omp.terminator
+  !CHECK: omp.terminator
   !$omp end parallel
 end subroutine omp_single
 
@@ -27,21 +28,21 @@
 ! Single construct with nowait
 !===============================================================================
 
-!FIRDialect-LABEL: func @_QPomp_single_nowait
-!FIRDialect-SAME: (%[[x:.*]]: !fir.ref<i32> {fir.bindc_name = "x"})
+!CHECK-LABEL: func @_QPomp_single_nowait
+!CHECK-SAME: (%[[x:.*]]: !fir.ref<i32> {fir.bindc_name = "x"})
 subroutine omp_single_nowait(x)
   integer, intent(inout) :: x
-  !OMPDialect: omp.parallel
+  !CHECK: omp.parallel
   !$omp parallel
-  !OMPDialect: omp.single nowait
+  !CHECK: omp.single nowait
   !$omp single
-    !FIRDialect: %[[xval:.*]] = fir.load %[[x]] : !fir.ref<i32>
-    !FIRDialect: %[[res:.*]] = arith.addi %[[xval]], %{{.*}} : i32
-    !FIRDialect: fir.store %[[res]] to %[[x]] : !fir.ref<i32>
+    !CHECK: %[[xval:.*]] = fir.load %[[x]] : !fir.ref<i32>
+    !CHECK: %[[res:.*]] = arith.addi %[[xval]], %{{.*}} : i32
+    !CHECK: fir.store %[[res]] to %[[x]] : !fir.ref<i32>
     x = x + 12
-  !OMPDialect: omp.terminator
+  !CHECK: omp.terminator
   !$omp end single nowait
-  !OMPDialect: omp.terminator
+  !CHECK: omp.terminator
   !$omp end parallel
 end subroutine omp_single_nowait
 
@@ -49,21 +50,80 @@
 ! Single construct with allocate
 !===============================================================================
 
-!FIRDialect-LABEL: func @_QPsingle_allocate
+!CHECK-LABEL: func @_QPsingle_allocate
 subroutine single_allocate()
   use omp_lib
   integer :: x
-  !OMPDialect: omp.parallel {
+  !CHECK: omp.parallel {
   !$omp parallel
-  !OMPDialect: omp.single allocate(
-  !FIRDialect: %{{.+}} : i32 -> %{{.+}} : !fir.ref<i32>
-  !LLVMDialect: %{{.+}} : i32 -> %{{.+}} : !llvm.ptr<i32>
-  !OMPDialect: ) {
+  !CHECK: omp.single allocate(%{{.+}} : i32 -> %{{.+}} : !fir.ref<i32>) {
   !$omp single allocate(omp_high_bw_mem_alloc: x) private(x)
-  !FIRDialect: arith.addi
+  !CHECK: arith.addi
   x = x + 12
-  !OMPDialect: omp.terminator
+  !CHECK: omp.barrier
+  !CHECK: omp.terminator
   !$omp end single
-  !OMPDialect: omp.terminator
+  !CHECK: omp.terminator
   !$omp end parallel
 end subroutine single_allocate
+
+!===============================================================================
+! Single construct with private
+!===============================================================================
+!CHECK-LABEL: func @_QPsingle_private
+subroutine single_private
+  type mytype
+  integer :: x
+  end type mytype
+
+  !CHECK: %[[int_var:.+]] = fir.alloca i32
+  !CHECK: %[[mytype_var:.+]] = fir.alloca !fir.type<_QFsingle_privateTmytype{x:i32}>
+  integer :: int_var
+  type(mytype) :: mytype_var
+
+  !CHECK: fir.call @_QPbar(%[[int_var]], %[[mytype_var]]) : (!fir.ref<i32>, !fir.ref<!fir.type<_QFsingle_privateTmytype{x:i32}>>) -> ()
+  call bar(int_var, mytype_var)
+
+  !CHECK: omp.single {
+  !$omp single private(int_var, mytype_var)
+  !CHECK: %[[int_var_private:.+]] = fir.alloca i32
+  !CHECK: %[[mytype_var_private:.+]] = fir.alloca !fir.type<_QFsingle_privateTmytype{x:i32}>
+
+  !CHECK: fir.call @_QPbar(%[[int_var_private]], %[[mytype_var_private]]) : (!fir.ref<i32>, !fir.ref<!fir.type<_QFsingle_privateTmytype{x:i32}>>) -> ()
+  call bar(int_var, mytype_var)
+  !CHECK: omp.barrier
+  !CHECK: omp.terminator
+  !$omp end single
+end subroutine single_private
+
+!===============================================================================
+! Single construct with firstprivate
+!===============================================================================
+!CHECK-LABEL: func @_QPsingle_firstprivate
+subroutine single_firstprivate
+  type mytype
+  integer :: x
+  end type mytype
+
+  !CHECK: %[[int_var:.+]] = fir.alloca i32
+  !CHECK: %[[mytype_var:.+]] = fir.alloca !fir.type<_QFsingle_firstprivateTmytype{x:i32}>
+  integer :: int_var
+  type(mytype) :: mytype_var
+
+  !CHECK: fir.call @_QPbaz(%[[int_var]], %[[mytype_var]]) : (!fir.ref<i32>, !fir.ref<!fir.type<_QFsingle_firstprivateTmytype{x:i32}>>) -> ()
+  call baz(int_var, mytype_var)
+
+  !CHECK: omp.single {
+  !$omp single firstprivate(int_var, mytype_var)
+  !CHECK: %[[int_var_firstprivate:.+]] = fir.alloca i32
+  !CHECK: %[[int_var_load:.+]] = fir.load %[[int_var]] : !fir.ref<i32>
+  !CHECK: fir.store %[[int_var_load]] to %[[int_var_firstprivate]] : !fir.ref<i32>
+  !CHECK: %[[mytype_var_firstprivate:.+]] = fir.alloca !fir.type<_QFsingle_firstprivateTmytype{x:i32}>
+  !CHECK: %[[mytype_var_load:.+]] = fir.load %[[mytype_var]] : !fir.ref<!fir.type<_QFsingle_firstprivateTmytype{x:i32}>>
+  !CHECK: fir.store %[[mytype_var_load]] to %[[mytype_var_firstprivate]]
+  !CHECK: fir.call @_QPbaz(%[[int_var_firstprivate]], %[[mytype_var_firstprivate]]) : (!fir.ref<i32>, !fir.ref<!fir.type<_QFsingle_firstprivateTmytype{x:i32}>>) -> ()
+  call baz(int_var, mytype_var)
+  !CHECK: omp.barrier
+  !CHECK: omp.terminator
+  !$omp end single
+end subroutine single_firstprivate
Index: mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td
===================================================================
--- mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td
+++ mlir/include/mlir/Dialect/OpenMP/OpenMPOps.td
@@ -237,7 +237,8 @@
 // 2.8.2 Single Construct
 //===----------------------------------------------------------------------===//
 
-def SingleOp : OpenMP_Op<"single", [AttrSizedOperandSegments]> {
+def SingleOp : OpenMP_Op<"single", [AttrSizedOperandSegments,
+                                    OutlineableOpenMPOpInterface]> {
   let summary = "single directive";
   let description = [{
     The single construct specifies that the associated structured block is