diff --git a/arm_compute/core/CL/CLHelpers.h b/arm_compute/core/CL/CLHelpers.h
index 78427c3..16fe09f 100644
--- a/arm_compute/core/CL/CLHelpers.h
+++ b/arm_compute/core/CL/CLHelpers.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2018 ARM Limited.
+ * Copyright (c) 2016-2019 ARM Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -144,5 +144,14 @@
  * @return preferred vector width
  */
 size_t preferred_vector_width(const cl::Device &device, DataType dt);
+
+/** Helper function to check if "dummy work-items" are preferred to have a power of two NDRange
+ * In case dummy work-items is enabled, it is OpenCL kernel responsibility to check if the work-item is out-of range or not
+ *
+ * @param[in] device A CL device
+ *
+ * @return True if dummy work-items should be preferred to dispatch the NDRange
+ */
+bool preferred_dummy_work_items_support(const cl::Device &device);
 }
 #endif /* __ARM_COMPUTE_CLHELPERS_H__ */
diff --git a/arm_compute/core/CL/ICLKernel.h b/arm_compute/core/CL/ICLKernel.h
index f542358..590f892 100644
--- a/arm_compute/core/CL/ICLKernel.h
+++ b/arm_compute/core/CL/ICLKernel.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-2018 ARM Limited.
+ * Copyright (c) 2016-2019 ARM Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -308,14 +308,16 @@
  *
  * @note If kernel->kernel() is empty then the function will return without adding anything to the queue.
  *
- * @param[in,out] queue    OpenCL command queue.
- * @param[in]     kernel   Kernel to enqueue
- * @param[in]     window   Window the kernel has to process.
- * @param[in]     lws_hint Local workgroup size requested. Default is based on the device target.
+ * @param[in,out] queue                OpenCL command queue.
+ * @param[in]     kernel               Kernel to enqueue
+ * @param[in]     window               Window the kernel has to process.
+ * @param[in]     lws_hint             (Optional) Local workgroup size requested. Default is based on the device target.
+ * @param[in]     use_dummy_work_items (Optional) Use dummy work items in order to have two dimensional power of two NDRange. Default is false
+ *                                     Note: it is kernel responsibility to check if the work-item is out-of-range
  *
  * @note If any dimension of the lws is greater than the global workgroup size then no lws will be passed.
  */
-void enqueue(cl::CommandQueue &queue, ICLKernel &kernel, const Window &window, const cl::NDRange &lws_hint = CLKernelLibrary::get().default_ndrange());
+void enqueue(cl::CommandQueue &queue, ICLKernel &kernel, const Window &window, const cl::NDRange &lws_hint = CLKernelLibrary::get().default_ndrange(), bool use_dummy_work_items = false);
 
 /** Add the passed array's parameters to the object's kernel's arguments starting from the index idx.
  *
diff --git a/arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.h b/arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.h
index 1cf7236..d361236 100644
--- a/arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.h
@@ -81,6 +81,7 @@
     bool             _slide_matrix_b;
     bool             _reinterpret_output_as_3d;
     unsigned int     _k;
+    bool             _use_dummy_work_items;
 };
 } // namespace arm_compute
 #endif /*__ARM_COMPUTE_CLGEMMLOWPMATRIXMULTIPLYRESHAPEDKERNEL_H__*/
\ No newline at end of file
diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h
index cb23b96..b0d245f 100644
--- a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.h
@@ -84,6 +84,7 @@
     bool             _slide_matrix_b;
     bool             _reinterpret_output_as_3d;
     unsigned int     _k;
+    bool             _use_dummy_work_items;
 };
 } // namespace arm_compute
 #endif /*__ARM_COMPUTE_CLGEMMMATRIXMULTIPLYRESHAPEDKERNEL_H__*/
\ No newline at end of file
diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h
index 7471594..b3ee435 100644
--- a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.h
@@ -84,6 +84,7 @@
     bool             _slide_matrix_b;
     bool             _reinterpret_input_as_3d;
     bool             _reinterpret_output_as_3d;
+    bool             _use_dummy_work_items;
 };
 } // namespace arm_compute
 #endif /*__ARM_COMPUTE_CLGEMMMATRIXMULTIPLYRESHAPEDONLYRHSKERNEL_H__*/
\ No newline at end of file
diff --git a/arm_compute/core/Helpers.h b/arm_compute/core/Helpers.h
index 91d85be..c7c7110 100644
--- a/arm_compute/core/Helpers.h
+++ b/arm_compute/core/Helpers.h
@@ -756,6 +756,34 @@
 {
     return x >= 0 ? x % m : (x % m + m) % m;
 }
+
+/** Given an integer value, this function returns the next power of two
+ *
+ * @param[in] x Input value
+ *
+ * @return the next power of two
+ */
+inline unsigned int get_next_power_two(unsigned int x)
+{
+    // Decrement by 1
+    x--;
+
+    // Shift right by 1
+    x |= x >> 1u;
+    // Shift right by 2
+    x |= x >> 2u;
+    // Shift right by 4
+    x |= x >> 4u;
+    // Shift right by 8
+    x |= x >> 8u;
+    // Shift right by 16
+    x |= x >> 16u;
+
+    // Increment by 1
+    x++;
+
+    return x;
+}
 } // namespace arm_compute
 
 #include "arm_compute/core/Helpers.inl"