diff --git a/src/backends/backendsCommon/test/BroadcastToEndToEndTestImpl.hpp b/src/backends/backendsCommon/test/BroadcastToEndToEndTestImpl.hpp
new file mode 100644
index 0000000..3b2c47f
--- /dev/null
+++ b/src/backends/backendsCommon/test/BroadcastToEndToEndTestImpl.hpp
@@ -0,0 +1,149 @@
+//
+// Copyright © 2023 Arm Ltd and Contributors. All rights reserved.
+// SPDX-License-Identifier: MIT
+//
+#pragma once
+#include "armnn/INetwork.hpp"
+#include "armnnUtils/QuantizeHelper.hpp"
+#include "ElementwiseBinaryEndToEndTestImpl.hpp"
+#include "Optimizer.hpp"
+#include <CommonTestUtils.hpp>
+#include <ResolveType.hpp>
+#include <doctest/doctest.h>
+
+namespace
+{
+    using namespace armnn;
+    armnn::INetworkPtr CreateBroadcastToNetwork(BroadcastToDescriptor& descriptor,
+                                                const armnn::TensorInfo& inputInfo,
+                                                const armnn::TensorInfo& outputInfo)
+    {
+        INetworkPtr network(INetwork::Create());
+        IConnectableLayer* inputLayer  = network->AddInputLayer(0, "input");
+        IConnectableLayer* broadcastLayer   = network->AddBroadcastToLayer(descriptor, "broadcast_to");
+        IConnectableLayer* outputLayer = network->AddOutputLayer(0, "output");
+        Connect(inputLayer,   broadcastLayer, inputInfo,  0, 0);
+        Connect(broadcastLayer, outputLayer,  outputInfo, 0, 0);
+        return network;
+    }
+
+    armnn::INetworkPtr CreateBroadcastToNetworkWithElementWiseBinary(BroadcastToDescriptor& descriptor,
+                                                                     const ElementwiseBinaryDescriptor&
+                                                                     elementWiseDescriptor,
+                                                                     const armnn::TensorInfo& inputInfo,
+                                                                     const armnn::TensorInfo& inputInfoElementWise,
+                                                                     const armnn::TensorInfo& outputInfo)
+    {
+        INetworkPtr network(INetwork::Create());
+        IConnectableLayer* inputLayer  = network->AddInputLayer(0, "input");
+        IConnectableLayer* inputLayerElementWise  = network->AddInputLayer(1, "inputElementWiseBinary");
+        IConnectableLayer* broadcastLayer   = network->AddBroadcastToLayer(descriptor, "broadcast_to");
+        IConnectableLayer* multiplicationLayer =
+                network->AddElementwiseBinaryLayer(elementWiseDescriptor,
+                                                   "multiplication");
+        IConnectableLayer* outputLayer = network->AddOutputLayer(0, "output");
+        Connect(inputLayer,   broadcastLayer, inputInfo,  0, 0);
+        Connect(inputLayerElementWise,   multiplicationLayer,
+                inputInfoElementWise,  0, 1);
+        Connect(broadcastLayer,   multiplicationLayer, inputInfo,  0, 0);
+        Connect(multiplicationLayer, outputLayer,  outputInfo, 0, 0);
+        return network;
+    }
+
+    template <armnn::DataType ArmnnType, typename T = armnn::ResolveType<ArmnnType>>
+    void BroadcastToEndToEnd(const std::vector<BackendId>& backends)
+    {
+        float   qScale  = 1.0f;
+        int32_t qOffset = 0;
+        bool    qConst  = true;
+
+        const TensorShape inputTensorShape =  { {1, 4} };
+        const TensorShape outputTensorShape = { {4, 4} };
+
+        TensorInfo inputInfo  (inputTensorShape, ArmnnType, qScale,
+                               qOffset, qConst);
+        TensorInfo outputInfo (outputTensorShape, ArmnnType,qScale,
+                               qOffset);
+
+        std::vector<T> inputData = armnnUtils::QuantizedVector<T>({
+                                                                          65, 144, 91, 161
+                                                                  }, qScale, qOffset);
+
+        std::vector<T> expectedOutputData = armnnUtils::QuantizedVector<T>({
+                                                                                   65, 144, 91, 161,
+                                                                                   65, 144, 91, 161,
+                                                                                   65, 144, 91, 161,
+                                                                                   65, 144, 91, 161
+                                                                           }, qScale, qOffset);
+
+        auto descriptor = armnn::BroadcastToDescriptor(armnn::TensorShape({ 4, 4 }));
+        CHECK(descriptor.m_BroadcastToShape == outputTensorShape);
+        INetworkPtr network = CreateBroadcastToNetwork(descriptor, inputInfo, outputInfo);
+
+        std::map<int, std::vector<T>> inputTensor          = { { 0, inputData  } };
+        std::map<int, std::vector<T>> expectedOutputTensor = { { 0, expectedOutputData } };
+        EndToEndLayerTestImpl<ArmnnType, ArmnnType>(std::move(network),inputTensor,
+                                                    expectedOutputTensor, backends);
+    }
+
+    template <armnn::DataType ArmnnType, typename T = armnn::ResolveType<ArmnnType>>
+    void BroadcastToEndToEndElementWiseBinary(const std::vector<BackendId>& backends)
+    {
+        float   qScale  = 1.0f;
+        int32_t qOffset = 0;
+        bool    qConst  = true;
+
+        const TensorShape inputTensorShape =  { {1, 4} };
+        const TensorShape outputTensorShape = { {4, 4} };
+
+        const TensorInfo inputInfo  (inputTensorShape, ArmnnType, qScale,
+                                    qOffset, qConst);
+        const TensorInfo inputInfoElementWise  (outputTensorShape, ArmnnType, qScale,
+                                                qOffset, qConst);
+        const TensorInfo outputInfo (outputTensorShape, ArmnnType,qScale,
+                                     qOffset);
+
+        std::vector<T> inputData = armnnUtils::QuantizedVector<T>({
+                                                                          65, 144, 91, 161
+                                                                  }, qScale, qOffset);
+
+        std::vector<T> inputDataElementWise = armnnUtils::QuantizedVector<T>({
+                                                                                   1, 1, 1, 1,
+                                                                                   1, 1, 1, 1,
+                                                                                   1, 1, 1, 1,
+                                                                                   1, 1, 1, 1
+                                                                           }, qScale, qOffset);
+
+        std::vector<T> expectedOutputData = armnnUtils::QuantizedVector<T>({
+                                                                                   65, 144, 91, 161,
+                                                                                   65, 144, 91, 161,
+                                                                                   65, 144, 91, 161,
+                                                                                   65, 144, 91, 161
+                                                                           }, qScale, qOffset);
+
+        auto descriptor = armnn::BroadcastToDescriptor(armnn::TensorShape({ 4, 4 }));
+        CHECK(descriptor.m_BroadcastToShape == outputTensorShape);
+        INetworkPtr network = CreateBroadcastToNetworkWithElementWiseBinary(descriptor,
+                                                                            BinaryOperation::Mul,
+                                                                            inputInfo,
+                                                                            inputInfoElementWise,
+                                                                            outputInfo);
+        // Create ArmNN runtime
+        IRuntimePtr run = IRuntime::Create(IRuntime::CreationOptions());
+
+        // Optimise ArmNN network
+        IOptimizedNetworkPtr optNet = Optimize(*network, {Compute::CpuRef},
+                                               run->GetDeviceSpec());
+
+        Graph& graph = GetGraphForTesting(optNet.get());
+
+        Optimizer::Pass(graph,
+                        armnn::MakeOptimizations(armnn::optimizations::BroadcastToOptimizationLayer()));
+
+        std::map<int, std::vector<T>> inputTensor          = { { 0, inputData  }, {1, inputDataElementWise} };
+        std::map<int, std::vector<T>> expectedOutputTensor = { { 0, expectedOutputData } };
+        EndToEndLayerTestImpl<ArmnnType, ArmnnType>(std::move(network),inputTensor,
+                                                    expectedOutputTensor, backends);
+    }
+
+} // anonymous namespace
\ No newline at end of file
diff --git a/src/backends/backendsCommon/test/CMakeLists.txt b/src/backends/backendsCommon/test/CMakeLists.txt
index 8f3a22d..ed95bcf 100644
--- a/src/backends/backendsCommon/test/CMakeLists.txt
+++ b/src/backends/backendsCommon/test/CMakeLists.txt
@@ -10,6 +10,7 @@
     BackendIdTests.cpp
     BackendProfilingTests.cpp
     BackendRegistryTests.cpp
+    BroadcastToEndToEndTestImpl.hpp
     ChannelShuffleEndToEndTestImpl.hpp
     ComparisonEndToEndTestImpl.hpp
     CompatibilityTests.cpp
@@ -79,6 +80,8 @@
     layerTests/BatchNormalizationTestImpl.cpp
     layerTests/BatchNormalizationTestImpl.hpp
     layerTests/BatchToSpaceNdTestImpl.hpp
+    layerTests/BroadcastToTestImpl.cpp
+    layerTests/BroadcastToTestImpl.hpp
     layerTests/CastTestImpl.cpp
     layerTests/CastTestImpl.hpp
     layerTests/ChannelShuffleTestImpl.cpp
diff --git a/src/backends/backendsCommon/test/ElementwiseUnaryEndToEndTestImpl.hpp b/src/backends/backendsCommon/test/ElementwiseUnaryEndToEndTestImpl.hpp
index 9586417..9d05a64 100644
--- a/src/backends/backendsCommon/test/ElementwiseUnaryEndToEndTestImpl.hpp
+++ b/src/backends/backendsCommon/test/ElementwiseUnaryEndToEndTestImpl.hpp
@@ -94,7 +94,7 @@
     std::map<int, std::vector<TInput>> inputTensorData    = {{ 0, qInputData }};
     std::map<int, std::vector<TInput>> expectedOutputData = {{ 0, qExpectedOutput }};
 
-    EndToEndLayerTestImpl<ArmnnInType, ArmnnInType>(move(net), inputTensorData, expectedOutputData, backends);
+    EndToEndLayerTestImpl<ArmnnInType, ArmnnInType>(std::move(net), inputTensorData, expectedOutputData, backends);
 }
 
 } // anonymous namespace
diff --git a/src/backends/backendsCommon/test/IsLayerSupportedTestImpl.hpp b/src/backends/backendsCommon/test/IsLayerSupportedTestImpl.hpp
index e8a2ec6..9f472e9 100644
--- a/src/backends/backendsCommon/test/IsLayerSupportedTestImpl.hpp
+++ b/src/backends/backendsCommon/test/IsLayerSupportedTestImpl.hpp
@@ -634,6 +634,8 @@
 
 DECLARE_LAYER_POLICY_2_PARAM(BatchToSpaceNd)
 
+DECLARE_LAYER_POLICY_2_PARAM(BroadcastTo)
+
 DECLARE_LAYER_POLICY_1_PARAM(Cast)
 
 DECLARE_LAYER_POLICY_2_PARAM(ChannelShuffle)
diff --git a/src/backends/backendsCommon/test/LayerTests.hpp b/src/backends/backendsCommon/test/LayerTests.hpp
index 3f8d045..015d25e 100644
--- a/src/backends/backendsCommon/test/LayerTests.hpp
+++ b/src/backends/backendsCommon/test/LayerTests.hpp
@@ -13,6 +13,7 @@
 #include <backendsCommon/test/layerTests/BatchMatMulTestImpl.hpp>
 #include <backendsCommon/test/layerTests/BatchNormalizationTestImpl.hpp>
 #include <backendsCommon/test/layerTests/BatchToSpaceNdTestImpl.hpp>
+#include <backendsCommon/test/layerTests/BroadcastToTestImpl.hpp>
 #include <backendsCommon/test/layerTests/CastTestImpl.hpp>
 #include <backendsCommon/test/layerTests/ChannelShuffleTestImpl.hpp>
 #include <backendsCommon/test/layerTests/ComparisonTestImpl.hpp>
@@ -79,3 +80,4 @@
 #include <backendsCommon/test/layerTests/TransposeConvolution2dTestImpl.hpp>
 #include <backendsCommon/test/layerTests/TransposeTestImpl.hpp>
 #include <backendsCommon/test/layerTests/UnidirectionalSequenceLstmTestImpl.hpp>
+
diff --git a/src/backends/backendsCommon/test/layerTests/BroadcastToTestImpl.cpp b/src/backends/backendsCommon/test/layerTests/BroadcastToTestImpl.cpp
new file mode 100644
index 0000000..b4e8a4c
--- /dev/null
+++ b/src/backends/backendsCommon/test/layerTests/BroadcastToTestImpl.cpp
@@ -0,0 +1,636 @@
+//
+// Copyright © 2023 Arm Ltd and Contributors. All rights reserved.
+// SPDX-License-Identifier: MIT
+//
+
+#include "BroadcastToTestImpl.hpp"
+#include <vector>
+
+#include <armnn/backends/IBackendInternal.hpp>
+#include <armnn/backends/Workload.hpp>
+#include <armnn/backends/WorkloadData.hpp>
+#include <armnn/backends/WorkloadFactory.hpp>
+
+#include <armnnTestUtils/WorkloadTestUtils.hpp>
+#include <armnnTestUtils/TensorCopyUtils.hpp>
+
+#include <armnn/BackendHelper.hpp>
+
+#include <armnnUtils/QuantizeHelper.hpp>
+#include <doctest/doctest.h>
+
+namespace
+{
+template<typename T, std::size_t NumDims>
+LayerTestResult<T, NumDims> BroadcastToTestImpl(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory,
+        armnn::BroadcastToDescriptor descriptor,
+        armnn::TensorInfo& inputInfo,
+        armnn::TensorInfo& outputInfo,
+        std::vector<T>& inputData,
+        std::vector<T>& expectedOutputData)
+{
+
+    CHECK(descriptor.m_BroadcastToShape == outputInfo.GetShape());
+
+    LayerTestResult<T, NumDims> result(outputInfo);
+    std::vector<T> outputActual(outputInfo.GetNumElements());
+
+    armnn::BroadcastToQueueDescriptor queueDescriptor;
+    queueDescriptor.m_Parameters = std::move(descriptor);
+    armnn::WorkloadInfo workloadInfo;
+
+    std::unique_ptr<armnn::ITensorHandle> inputHandle  = tensorHandleFactory.CreateTensorHandle(inputInfo);
+    std::unique_ptr<armnn::ITensorHandle> outputHandle = tensorHandleFactory.CreateTensorHandle(outputInfo);
+
+    AddInputToWorkload(queueDescriptor, workloadInfo, inputInfo, inputHandle.get());
+    AddOutputToWorkload(queueDescriptor, workloadInfo, outputInfo, outputHandle.get());
+
+    const armnn::BackendId& backend = workloadFactory.GetBackendId();
+    armnn::LayerSupportHandle handle = armnn::GetILayerSupportByBackendId(backend);
+
+    auto workload = workloadFactory.CreateWorkload(armnn::LayerType::BroadcastTo, queueDescriptor, workloadInfo);
+
+    inputHandle->Allocate();
+    outputHandle->Allocate();
+
+    CopyDataToITensorHandle(inputHandle.get(), inputData.data());
+
+    workload->PostAllocationConfigure();
+    ExecuteWorkload(*workload, memoryManager);
+
+    CopyDataFromITensorHandle(outputActual.data(), outputHandle.get());
+    return LayerTestResult<T, NumDims>(outputActual,
+                                       expectedOutputData,
+                                       outputHandle->GetShape(),
+                                       outputInfo.GetShape());
+}
+}
+
+template<armnn::DataType ArmnnType, typename T>
+LayerTestResult<T, 1> BroadcastTo1dTest(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory)
+{
+    auto descriptor = armnn::BroadcastToDescriptor(armnn::TensorShape( {1, 4} ));
+
+    float qScale = 1.0f;
+    int32_t qOffset = 0;
+
+    armnn::TensorShape inputShape  = { 1, 1 };
+    armnn::TensorShape outputShape = { 1, 4 };
+
+    armnn::TensorInfo inputInfo(inputShape, ArmnnType);
+    armnn::TensorInfo outputInfo(outputShape, ArmnnType);
+
+    std::vector<T> input = armnnUtils::QuantizedVector<T>(
+            {
+                    1.f
+            }, qScale, qOffset);
+
+    std::vector<T> expectedOutput = armnnUtils::QuantizedVector<T>(
+            {
+                    1.f, 1.f,
+                    1.f, 1.f
+            }, qScale, qOffset);
+
+    return BroadcastToTestImpl<T, 1>(workloadFactory,
+                              memoryManager,
+                              tensorHandleFactory,
+                              descriptor,
+                              inputInfo,
+                              outputInfo,
+                              input,
+                              expectedOutput);
+}
+
+template<armnn::DataType ArmnnType, typename T>
+LayerTestResult<T, 2> BroadcastTo2dAxis0Test(armnn::IWorkloadFactory& workloadFactory,
+                                             const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                             const armnn::ITensorHandleFactory& tensorHandleFactory)
+{
+    auto descriptor = armnn::BroadcastToDescriptor(armnn::TensorShape({ 4, 3 }));
+
+    float qScale = 1.0f;
+    int32_t qOffset = 0;
+
+    armnn::TensorShape inputShape  = { 1, 3 };
+    armnn::TensorShape outputShape = { 4, 3 };
+
+    armnn::TensorInfo inputInfo(inputShape, ArmnnType);
+    armnn::TensorInfo outputInfo(outputShape, ArmnnType);
+
+    std::vector<T> input = armnnUtils::QuantizedVector<T>(
+            {
+                    0.f, 1.f, 2.f
+            }, qScale, qOffset);
+
+
+    std::vector<T> expectedOutput = armnnUtils::QuantizedVector<T>(
+            {
+                    0.f, 1.f, 2.f,
+                    0.f, 1.f, 2.f,
+                    0.f, 1.f, 2.f,
+                    0.f, 1.f, 2.f
+            }, qScale, qOffset);
+
+    return BroadcastToTestImpl<T, 2>(workloadFactory,
+                              memoryManager,
+                              tensorHandleFactory,
+                              descriptor,
+                              inputInfo,
+                              outputInfo,
+                              input,
+                              expectedOutput);
+}
+
+template<armnn::DataType ArmnnType, typename T>
+LayerTestResult<T, 2> BroadcastTo2dAxis1Test(armnn::IWorkloadFactory& workloadFactory,
+                                             const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                             const armnn::ITensorHandleFactory& tensorHandleFactory)
+{
+    auto descriptor = armnn::BroadcastToDescriptor(armnn::TensorShape({ 3, 4 }));
+
+    float qScale = 1.0f;
+    int32_t qOffset = 0;
+
+    armnn::TensorShape inputShape  = { 3, 1 };
+    armnn::TensorShape outputShape = { 3, 4 };
+
+    armnn::TensorInfo inputInfo(inputShape, ArmnnType);
+    armnn::TensorInfo outputInfo(outputShape, ArmnnType);
+
+    std::vector<T> input = armnnUtils::QuantizedVector<T>(
+            {
+                    0.f, 1.f, 2.f
+            }, qScale, qOffset);
+
+
+    std::vector<T> expectedOutput = armnnUtils::QuantizedVector<T>(
+            {
+                    0.f, 0.f, 0.f, 0.f,
+                    1.f, 1.f, 1.f, 1.f,
+                    2.f, 2.f, 2.f, 2.f
+            }, qScale, qOffset);
+
+    return BroadcastToTestImpl<T, 2>(workloadFactory,
+                                     memoryManager,
+                                     tensorHandleFactory,
+                                     descriptor,
+                                     inputInfo,
+                                     outputInfo,
+                                     input,
+                                     expectedOutput);
+}
+
+template<armnn::DataType ArmnnType, typename T>
+LayerTestResult<T, 3> BroadcastTo3dAxis0Test(armnn::IWorkloadFactory& workloadFactory,
+                                        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                        const armnn::ITensorHandleFactory& tensorHandleFactory)
+{
+    auto descriptor = armnn::BroadcastToDescriptor(armnn::TensorShape({ 2, 1, 3 }));
+
+    float qScale = 1.0f;
+    int32_t qOffset = 0;
+
+    armnn::TensorShape inputShape  = { 1, 1, 3 };
+    armnn::TensorShape outputShape = { 2, 1, 3 };
+
+    armnn::TensorInfo inputInfo(inputShape, ArmnnType);
+    armnn::TensorInfo outputInfo(outputShape, ArmnnType);
+    std::vector<T> input = armnnUtils::QuantizedVector<T>(
+            {
+                    1.1f, 2.12f, 3.3f
+            }, qScale, qOffset);
+
+
+    std::vector<T> expectedOutput = armnnUtils::QuantizedVector<T>(
+            {
+                    1.1f, 2.12f, 3.3f,
+                    1.1f, 2.12f, 3.3f
+            }, qScale, qOffset);
+
+    return BroadcastToTestImpl<T, 3>(workloadFactory,
+                              memoryManager,
+                              tensorHandleFactory,
+                              descriptor,
+                              inputInfo,
+                              outputInfo,
+                              input,
+                              expectedOutput);
+}
+
+template<armnn::DataType ArmnnType, typename T>
+LayerTestResult<T, 3> BroadcastTo3dAxis1Test(armnn::IWorkloadFactory& workloadFactory,
+                                             const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                             const armnn::ITensorHandleFactory& tensorHandleFactory)
+{
+    auto descriptor = armnn::BroadcastToDescriptor(armnn::TensorShape({ 1, 3, 3 }));
+
+    float qScale = 1.0f;
+    int32_t qOffset = 0;
+
+    armnn::TensorShape inputShape  = { 1, 1, 3 };
+    armnn::TensorShape outputShape = { 1, 3, 3 };
+
+    armnn::TensorInfo inputInfo(inputShape, ArmnnType);
+    armnn::TensorInfo outputInfo(outputShape, ArmnnType);
+    std::vector<T> input = armnnUtils::QuantizedVector<T>(
+            {
+                    1.1f, 2.12f, 3.3f
+            }, qScale, qOffset);
+
+
+    std::vector<T> expectedOutput = armnnUtils::QuantizedVector<T>(
+            {
+                    1.1f, 2.12f, 3.3f,
+                    1.1f, 2.12f, 3.3f,
+                    1.1f, 2.12f, 3.3f
+            }, qScale, qOffset);
+
+    return BroadcastToTestImpl<T, 3>(workloadFactory,
+                                     memoryManager,
+                                     tensorHandleFactory,
+                                     descriptor,
+                                     inputInfo,
+                                     outputInfo,
+                                     input,
+                                     expectedOutput);
+}
+
+template<armnn::DataType ArmnnType, typename T>
+LayerTestResult<T, 3> BroadcastTo3dAxis2Test(armnn::IWorkloadFactory& workloadFactory,
+                                             const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                             const armnn::ITensorHandleFactory& tensorHandleFactory)
+{
+    auto descriptor = armnn::BroadcastToDescriptor(armnn::TensorShape({ 1, 3, 3 }));
+
+    float qScale = 1.0f;
+    int32_t qOffset = 0;
+
+    armnn::TensorShape inputShape  = { 1, 3, 1 };
+    armnn::TensorShape outputShape = { 1, 3, 3 };
+
+    armnn::TensorInfo inputInfo(inputShape, ArmnnType);
+    armnn::TensorInfo outputInfo(outputShape, ArmnnType);
+    std::vector<T> input = armnnUtils::QuantizedVector<T>(
+            {
+                    1.1f, 2.12f, 3.3f
+            }, qScale, qOffset);
+
+
+    std::vector<T> expectedOutput = armnnUtils::QuantizedVector<T>(
+            {
+                    1.1f, 1.1f, 1.1f,
+                    2.12f, 2.12f, 2.12f,
+                    3.3f, 3.3f, 3.3f
+            }, qScale, qOffset);
+
+    return BroadcastToTestImpl<T, 3>(workloadFactory,
+                                     memoryManager,
+                                     tensorHandleFactory,
+                                     descriptor,
+                                     inputInfo,
+                                     outputInfo,
+                                     input,
+                                     expectedOutput);
+}
+
+template<armnn::DataType ArmnnType, typename T>
+LayerTestResult<T, 4> BroadcastTo4dTest(armnn::IWorkloadFactory& workloadFactory,
+                                             const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                             const armnn::ITensorHandleFactory& tensorHandleFactory)
+{
+    auto descriptor = armnn::BroadcastToDescriptor(armnn::TensorShape({ 3, 1, 2, 3 }));
+
+    float qScale = 1.0f;
+    int32_t qOffset = 0;
+
+    armnn::TensorShape inputShape  = { 1, 1, 1, 3 };
+    armnn::TensorShape outputShape = { 3, 1, 2, 3 };
+
+    armnn::TensorInfo inputInfo(inputShape, ArmnnType);
+    armnn::TensorInfo outputInfo(outputShape, ArmnnType);
+
+    std::vector<T> input = armnnUtils::QuantizedVector<T>(
+            {
+                    0.f,  1.f,  2.f
+            }, qScale, qOffset);
+
+
+    std::vector<T> expectedOutput = armnnUtils::QuantizedVector<T>(
+            {
+                    0.f,  1.f,  2.f,
+                    0.f,  1.f,  2.f,
+                    0.f,  1.f,  2.f,
+                    0.f,  1.f,  2.f,
+                    0.f,  1.f,  2.f,
+                    0.f,  1.f,  2.f
+            }, qScale, qOffset);
+
+    return BroadcastToTestImpl<T, 4>(workloadFactory,
+                              memoryManager,
+                              tensorHandleFactory,
+                              descriptor,
+                              inputInfo,
+                              outputInfo,
+                              input,
+                              expectedOutput);
+}
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float32>, 1>
+BroadcastTo1dTest<armnn::DataType::Float32>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float32>, 2>
+BroadcastTo2dAxis0Test<armnn::DataType::Float32>(
+                      armnn::IWorkloadFactory& workloadFactory,
+                      const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                      const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float32>, 2>
+BroadcastTo2dAxis1Test<armnn::DataType::Float32>(
+                       armnn::IWorkloadFactory& workloadFactory,
+                       const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                       const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float32>, 3>
+BroadcastTo3dAxis0Test<armnn::DataType::Float32>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float32>, 3>
+BroadcastTo3dAxis1Test<armnn::DataType::Float32>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float32>, 3>
+BroadcastTo3dAxis2Test<armnn::DataType::Float32>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float32>, 4>
+BroadcastTo4dTest<armnn::DataType::Float32>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float16>, 1>
+BroadcastTo1dTest<armnn::DataType::Float16>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float16>, 2>
+BroadcastTo2dAxis0Test<armnn::DataType::Float16>(
+                       armnn::IWorkloadFactory& workloadFactory,
+                       const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                       const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float16>, 2>
+BroadcastTo2dAxis1Test<armnn::DataType::Float16>(
+                       armnn::IWorkloadFactory& workloadFactory,
+                       const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                       const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float16>, 3>
+BroadcastTo3dAxis0Test<armnn::DataType::Float16>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float16>, 3>
+BroadcastTo3dAxis1Test<armnn::DataType::Float16>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float16>, 3>
+BroadcastTo3dAxis2Test<armnn::DataType::Float16>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Float16>, 4>
+BroadcastTo4dTest<armnn::DataType::Float16>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmS8>, 1>
+BroadcastTo1dTest<armnn::DataType::QAsymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmS8>, 2>
+BroadcastTo2dAxis0Test<armnn::DataType::QAsymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmS8>, 2>
+BroadcastTo2dAxis1Test<armnn::DataType::QAsymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmS8>, 3>
+BroadcastTo3dAxis0Test<armnn::DataType::QAsymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmS8>, 3>
+BroadcastTo3dAxis1Test<armnn::DataType::QAsymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmS8>, 3>
+BroadcastTo3dAxis2Test<armnn::DataType::QAsymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmS8>, 4>
+BroadcastTo4dTest<armnn::DataType::QAsymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmU8>, 1>
+BroadcastTo1dTest<armnn::DataType::QAsymmU8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmU8>, 2>
+BroadcastTo2dAxis0Test<armnn::DataType::QAsymmU8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmU8>, 2>
+BroadcastTo2dAxis1Test<armnn::DataType::QAsymmU8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmU8>, 3>
+BroadcastTo3dAxis0Test<armnn::DataType::QAsymmU8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmU8>, 3>
+BroadcastTo3dAxis1Test<armnn::DataType::QAsymmU8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmU8>, 3>
+BroadcastTo3dAxis2Test<armnn::DataType::QAsymmU8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QAsymmU8>, 4>
+BroadcastTo4dTest<armnn::DataType::QAsymmU8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS8>, 1>
+BroadcastTo1dTest<armnn::DataType::QSymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS8>, 2>
+BroadcastTo2dAxis0Test<armnn::DataType::QSymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS8>, 2>
+BroadcastTo2dAxis1Test<armnn::DataType::QSymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS8>, 3>
+BroadcastTo3dAxis0Test<armnn::DataType::QSymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS8>, 3>
+BroadcastTo3dAxis1Test<armnn::DataType::QSymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS8>, 3>
+BroadcastTo3dAxis2Test<armnn::DataType::QSymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS8>, 4>
+BroadcastTo4dTest<armnn::DataType::QSymmS8>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS16>, 1>
+BroadcastTo1dTest<armnn::DataType::QSymmS16>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS16>, 2>
+BroadcastTo2dAxis0Test<armnn::DataType::QSymmS16>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS16>, 2>
+BroadcastTo2dAxis1Test<armnn::DataType::QSymmS16>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS16>, 3>
+BroadcastTo3dAxis0Test<armnn::DataType::QSymmS16>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS16>, 3>
+BroadcastTo3dAxis1Test<armnn::DataType::QSymmS16>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS16>, 3>
+BroadcastTo3dAxis2Test<armnn::DataType::QSymmS16>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::QSymmS16>, 4>
+BroadcastTo4dTest<armnn::DataType::QSymmS16>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Signed32>, 1>
+BroadcastTo1dTest<armnn::DataType::Signed32>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Signed32>, 2>
+BroadcastTo2dAxis0Test<armnn::DataType::Signed32>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Signed32>, 2>
+BroadcastTo2dAxis1Test<armnn::DataType::Signed32>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Signed32>, 3>
+BroadcastTo3dAxis0Test<armnn::DataType::Signed32>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Signed32>, 3>
+BroadcastTo3dAxis1Test<armnn::DataType::Signed32>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Signed32>, 3>
+BroadcastTo3dAxis2Test<armnn::DataType::Signed32>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template LayerTestResult<armnn::ResolveType<armnn::DataType::Signed32>, 4>
+BroadcastTo4dTest<armnn::DataType::Signed32>(
+        armnn::IWorkloadFactory& workloadFactory,
+        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+        const armnn::ITensorHandleFactory& tensorHandleFactory);
diff --git a/src/backends/backendsCommon/test/layerTests/BroadcastToTestImpl.hpp b/src/backends/backendsCommon/test/layerTests/BroadcastToTestImpl.hpp
new file mode 100644
index 0000000..d8d0df4
--- /dev/null
+++ b/src/backends/backendsCommon/test/layerTests/BroadcastToTestImpl.hpp
@@ -0,0 +1,46 @@
+//
+// Copyright © 2023 Arm Ltd and Contributors. All rights reserved.
+// SPDX-License-Identifier: MIT
+//
+
+#pragma once
+
+#include <armnnTestUtils/LayerTestResult.hpp>
+#include <armnn/backends/IBackendInternal.hpp>
+#include <armnn/backends/WorkloadFactory.hpp>
+#include "ResolveType.hpp"
+
+template<armnn::DataType ArmnnType, typename T = armnn::ResolveType<ArmnnType>>
+LayerTestResult<T, 4> BroadcastTo4dTest(armnn::IWorkloadFactory& workloadFactory,
+                                        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                        const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template<armnn::DataType ArmnnType, typename T = armnn::ResolveType<ArmnnType>>
+LayerTestResult<T, 3> BroadcastTo3dAxis0Test(armnn::IWorkloadFactory& workloadFactory,
+                                             const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                             const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template<armnn::DataType ArmnnType, typename T = armnn::ResolveType<ArmnnType>>
+LayerTestResult<T, 3> BroadcastTo3dAxis1Test(armnn::IWorkloadFactory& workloadFactory,
+                                             const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                             const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template<armnn::DataType ArmnnType, typename T = armnn::ResolveType<ArmnnType>>
+LayerTestResult<T, 3> BroadcastTo3dAxis2Test(armnn::IWorkloadFactory& workloadFactory,
+                                             const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                             const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template<armnn::DataType ArmnnType, typename T = armnn::ResolveType<ArmnnType>>
+LayerTestResult<T, 2> BroadcastTo2dAxis0Test(armnn::IWorkloadFactory& workloadFactory,
+                                            const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                            const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template<armnn::DataType ArmnnType, typename T = armnn::ResolveType<ArmnnType>>
+LayerTestResult<T, 2> BroadcastTo2dAxis1Test(armnn::IWorkloadFactory& workloadFactory,
+                                             const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                             const armnn::ITensorHandleFactory& tensorHandleFactory);
+
+template<armnn::DataType ArmnnType, typename T = armnn::ResolveType<ArmnnType>>
+LayerTestResult<T, 1> BroadcastTo1dTest(armnn::IWorkloadFactory& workloadFactory,
+                                        const armnn::IBackendInternal::IMemoryManagerSharedPtr& memoryManager,
+                                        const armnn::ITensorHandleFactory& tensorHandleFactory);
\ No newline at end of file