diff --git a/mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp b/mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp
--- a/mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp
+++ b/mlir/lib/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.cpp
@@ -667,6 +667,30 @@
   return bodyGenStatus;
 }
 
+/// Converts an OpenMP task construct into LLVM IR using OpenMPIRBuilder.
+static LogicalResult
+convertOmpTaskOp(omp::TaskOp &taskOp, llvm::IRBuilderBase &builder,
+                 LLVM::ModuleTranslation &moduleTranslation) {
+  using InsertPointTy = llvm::OpenMPIRBuilder::InsertPointTy;
+  LogicalResult bodyGenStatus = success();
+  if (taskOp.if_expr() || taskOp.final_expr() || taskOp.untiedAttr() ||
+      taskOp.mergeableAttr() || taskOp.in_reductions() || taskOp.priority() ||
+      !taskOp.allocate_vars().empty()) {
+    return taskOp.emitError("unhandled clauses for translation to LLVM IR");
+  }
+  auto bodyCB = [&](InsertPointTy allocaIP, InsertPointTy codegenIP,
+                    llvm::BasicBlock &continuationBB) {
+    convertOmpOpRegions(taskOp.region(), "omp.task.region",
+                        *codegenIP.getBlock(), continuationBB, builder,
+                        moduleTranslation, bodyGenStatus);
+  };
+  auto allocaIP = findAllocaInsertPoint(builder, moduleTranslation);
+  llvm::OpenMPIRBuilder::LocationDescription ompLoc(builder);
+  builder.restoreIP(moduleTranslation.getOpenMPBuilder()->createTask(
+      ompLoc, allocaIP, bodyCB));
+  return bodyGenStatus;
+}
+
 /// Converts an OpenMP workshare loop into LLVM IR using OpenMPIRBuilder.
 static LogicalResult
 convertOmpWsLoop(Operation &opInst, llvm::IRBuilderBase &builder,
@@ -1446,6 +1470,9 @@
       .Case([&](omp::SingleOp op) {
         return convertOmpSingle(op, builder, moduleTranslation);
       })
+      .Case([&](omp::TaskOp op) {
+        return convertOmpTaskOp(op, builder, moduleTranslation);
+      })
       .Case<omp::YieldOp, omp::TerminatorOp, omp::ReductionDeclareOp,
             omp::CriticalDeclareOp>([](auto op) {
         // `yield` and `terminator` can be just omitted. The block structure
diff --git a/mlir/test/Target/LLVMIR/openmp-llvm.mlir b/mlir/test/Target/LLVMIR/openmp-llvm.mlir
--- a/mlir/test/Target/LLVMIR/openmp-llvm.mlir
+++ b/mlir/test/Target/LLVMIR/openmp-llvm.mlir
@@ -2090,3 +2090,90 @@
 }
 
 llvm.mlir.global internal @_QFsubEx() : i32
+
+// -----
+
+// CHECK-LABEL: define void @omp_task
+// CHECK-SAME: (i32 %[[x:.+]], i32 %[[y:.+]], i32* %[[zaddr:.+]])
+llvm.func @omp_task(%x: i32, %y: i32, %zaddr: !llvm.ptr<i32>) {
+  // CHECK: %[[omp_global_thread_num:.+]] = call i32 @__kmpc_global_thread_num({{.+}})
+  // CHECK: %[[task_data:.+]] = call i8* @__kmpc_omp_task_alloc
+  // CHECK-SAME: (%{{.+}}* @1, i32 %[[omp_global_thread_num]], i32 1, i64 0,
+  // CHECK-SAME:  i64 0, i32 (i32, i8*)* bitcast (i32 (i32)* @[[wrapper_fn:.+]] to
+  // CHECK-SAME:  i32 (i32, i8*)*))
+  // CHECK: call i32 @__kmpc_omp_task(%{{.*}}, i32 %[[omp_global_thread_num]], i8* %[[task_data]])
+  omp.task {
+    %n = llvm.mlir.constant(1 : i64) : i64
+    %valaddr = llvm.alloca %n x i32 : (i64) -> !llvm.ptr<i32>
+    %val = llvm.load %valaddr : !llvm.ptr<i32>
+    %double = llvm.add %val, %val : i32
+    llvm.store %double, %valaddr : !llvm.ptr<i32>
+    omp.terminator
+  }
+  llvm.return
+}
+
+// CHECK: define internal void @[[outlined_fn:.+]]()
+// CHECK: task.alloca{{.*}}:
+// CHECK:   br label %[[task_body:[^, ]+]]
+// CHECK: [[task_body]]:
+// CHECK:   br label %[[task_region:[^, ]+]]
+// CHECK: [[task_region]]:
+// CHECK:   %[[val:.+]] = load i32, i32* %{{[^, ]+}}
+// CHECK:   %[[newval:.+]] = add i32 %[[val]], %[[val]]
+// CHECK:   store i32 %[[newval]], i32* %{{[^, ]+}}
+// CHECK:   br label %[[exit_stub:[^, ]+]]
+// CHECK: [[exit_stub]]:
+// CHECK:   ret void
+
+
+// CHECK: define i32 @[[wrapper_fn]](i32 %{{.+}}) {
+// CHECK:   call void @[[outlined_fn]]()
+// CHECK:   ret i32 0
+// CHECK: }
+
+// -----
+
+// CHECK-LABEL: define void @omp_task
+// CHECK-SAME: (i32 %[[x:.+]], i32 %[[y:.+]], i32* %[[zaddr:.+]])
+llvm.func @omp_task(%x: i32, %y: i32, %zaddr: !llvm.ptr<i32>) {
+  // CHECK: %[[diff:.+]] = sub i32 %[[x]], %[[y]],
+  %diff = llvm.sub %x, %y : i32
+  // CHECK: store i32 %[[diff]], i32* %2
+  llvm.store %diff, %zaddr : !llvm.ptr<i32>
+  // CHECK: %[[omp_global_thread_num:.+]] = call i32 @__kmpc_global_thread_num({{.+}})
+  // CHECK: %[[task_data:.+]] = call i8* @__kmpc_omp_task_alloc
+  // CHECK-SAME: (%{{.+}}, i32 %[[omp_global_thread_num]], i32 1, i64 16, i64 0,
+  // CHECK-SAME: i32 (i32, i8*)* bitcast (i32 (i32, { i32, i32, i32* }*)*
+  // CHECK-SAME: @[[wrapper_fn:.+]] to i32 (i32, i8*)*))
+  // CHECK: call void @llvm.memcpy.p0i8.p0i8.i64(i8* {{.+}} %[[task_data]], i8* {{.+}}, i64 16, i1 false)
+  // CHECK: call i32 @__kmpc_omp_task(%{{.*}}, i32 %[[omp_global_thread_num]], i8* %[[task_data]])
+  omp.task {
+    %z = llvm.add %x, %y : i32
+    llvm.store %z, %zaddr : !llvm.ptr<i32>
+    omp.terminator
+  }
+  // CHECK: %[[prod:.+]] = mul i32 %[[x]], %[[y]]
+  %b = llvm.mul %x, %y : i32
+  // CHECK: store i32 %[[prod]], i32* %[[zaddr]]
+  llvm.store %b, %zaddr : !llvm.ptr<i32>
+  llvm.return
+}
+
+// CHECK: define internal void @[[outlined_fn:.+]]({ i32, i32, i32* }* %[[task_data:.+]])
+// CHECK: task.alloca{{.*}}:
+// CHECK:   br label %[[task_body:[^, ]+]]
+// CHECK: [[task_body]]:
+// CHECK:   br label %[[task_region:[^, ]+]]
+// CHECK: [[task_region]]:
+// CHECK:   %[[sum:.+]] = add i32 %{{.+}}, %{{.+}}
+// CHECK:   store i32 %[[sum]], i32* %{{.+}}
+// CHECK:   br label %[[exit_stub:[^, ]+]]
+// CHECK: [[exit_stub]]:
+// CHECK:   ret void
+
+
+// CHECK: define i32 @[[wrapper_fn]](i32 %{{.+}}, { i32, i32, i32* }* %[[task_data:.+]]) {
+// CHECK:   call void @[[outlined_fn]]({ i32, i32, i32* }* %[[task_data]])
+// CHECK:   ret i32 0
+// CHECK: }