diff --git a/scripts/get_compute_library.sh b/scripts/get_compute_library.sh
index 0a8f86a..ee45f6c 100755
--- a/scripts/get_compute_library.sh
+++ b/scripts/get_compute_library.sh
@@ -10,7 +10,7 @@
 #DEFAULT_CLFRAMEWORKREVISION="branches/arm_compute_19_08" # Release 19.08
 #
 # For pinning to a revision use this:
-DEFAULT_CLFRAMEWORKREVISION="79f88e6d825402388bb79fc123ee2dfe01985bda" #COMPMID-2313: Implement CL INSTANCE_NORMALIZATION function
+DEFAULT_CLFRAMEWORKREVISION="94e0cf960ea6116eb57fa88d9b951f859b52c602" #COMPMID-2690 Extend Doxygen documents to include GEMM Tuner
 
 usage() {
     echo "Usage: $CMD (Use the default clframework SHA)"
diff --git a/src/backends/backendsCommon/test/IsLayerSupportedTestImpl.hpp b/src/backends/backendsCommon/test/IsLayerSupportedTestImpl.hpp
index 82430b1..12d7143 100644
--- a/src/backends/backendsCommon/test/IsLayerSupportedTestImpl.hpp
+++ b/src/backends/backendsCommon/test/IsLayerSupportedTestImpl.hpp
@@ -203,6 +203,8 @@
     DummyConvolutionLayer()
     {
         typename ConvolutionLayerType::DescriptorType desc;
+        desc.m_StrideX = 1;
+        desc.m_StrideY = 1;
         m_Layer = dummyGraph.AddLayer<ConvolutionLayerType>(desc, "");
         m_Layer->m_Weight = std::make_unique<armnn::ScopedCpuTensorHandle>(
             armnn::TensorInfo(armnn::TensorShape({1,1,1,1}), armnn::DataType::Float32));
diff --git a/src/backends/cl/ClContextControl.cpp b/src/backends/cl/ClContextControl.cpp
index 2ffece4..7013b8a 100644
--- a/src/backends/cl/ClContextControl.cpp
+++ b/src/backends/cl/ClContextControl.cpp
@@ -104,7 +104,7 @@
     cl::Context context;
     cl::CommandQueue commandQueue;
 
-    if (arm_compute::CLScheduler::get().context()() != NULL)
+    if (arm_compute::CLScheduler::get().is_initialised() && arm_compute::CLScheduler::get().context()() != NULL)
     {
         // Wait for all queued CL requests to finish before reinitialising it.
         arm_compute::CLScheduler::get().sync();
diff --git a/src/backends/cl/workloads/ClDepthwiseConvolutionWorkload.cpp b/src/backends/cl/workloads/ClDepthwiseConvolutionWorkload.cpp
index 126950c..eb837d7 100644
--- a/src/backends/cl/workloads/ClDepthwiseConvolutionWorkload.cpp
+++ b/src/backends/cl/workloads/ClDepthwiseConvolutionWorkload.cpp
@@ -118,8 +118,8 @@
     bool use3x3Optimisation = (weightInfo.GetShape()[2] == 3) && (weightInfo.GetShape()[3] == 3);
     if (use3x3Optimisation)
     {
-        m_DepthwiseConvolutionLayer = std::make_unique<arm_compute::CLDepthwiseConvolutionLayer3x3>();
-        static_cast<arm_compute::CLDepthwiseConvolutionLayer3x3*>(m_DepthwiseConvolutionLayer.get())->configure(
+        m_DepthwiseConvolutionLayer = std::make_unique<arm_compute::CLDepthwiseConvolutionLayer>();
+        static_cast<arm_compute::CLDepthwiseConvolutionLayer*>(m_DepthwiseConvolutionLayer.get())->configure(
             &input,
             m_KernelTensor.get(),
             m_BiasTensor.get(),
diff --git a/src/backends/neon/workloads/NeonArgMinMaxWorkload.cpp b/src/backends/neon/workloads/NeonArgMinMaxWorkload.cpp
index e8d537f..4b43052 100644
--- a/src/backends/neon/workloads/NeonArgMinMaxWorkload.cpp
+++ b/src/backends/neon/workloads/NeonArgMinMaxWorkload.cpp
@@ -59,20 +59,24 @@
     auto unsignedAxis = armnnUtils::GetUnsignedAxis(numDims, m_Data.m_Parameters.m_Axis);
     int aclAxis = boost::numeric_cast<int>(CalcAclAxis(numDims, unsignedAxis));
 
+    auto layer = std::make_unique<arm_compute::NEArgMinMaxLayer>();
+
     if (m_Data.m_Parameters.m_Function == ArgMinMaxFunction::Max)
     {
-        m_ArgMinMaxLayer.configure(&input, aclAxis, &output, arm_compute::ReductionOperation::ARG_IDX_MAX);
+        layer->configure(&input, aclAxis, &output, arm_compute::ReductionOperation::ARG_IDX_MAX);
     }
     else
     {
-        m_ArgMinMaxLayer.configure(&input, aclAxis, &output, arm_compute::ReductionOperation::ARG_IDX_MIN);
+        layer->configure(&input, aclAxis, &output, arm_compute::ReductionOperation::ARG_IDX_MIN);
     }
+
+    m_ArgMinMaxLayer.reset(layer.release());
 }
 
 void NeonArgMinMaxWorkload::Execute() const
 {
     ARMNN_SCOPED_PROFILING_EVENT_NEON("NeonArgMinMaxWorkload_Execute");
-    m_ArgMinMaxLayer.run();
+    m_ArgMinMaxLayer->run();
 }
 
 } //namespace armnn
diff --git a/src/backends/neon/workloads/NeonArgMinMaxWorkload.hpp b/src/backends/neon/workloads/NeonArgMinMaxWorkload.hpp
index 6301b13..6e1cc46 100644
--- a/src/backends/neon/workloads/NeonArgMinMaxWorkload.hpp
+++ b/src/backends/neon/workloads/NeonArgMinMaxWorkload.hpp
@@ -8,7 +8,8 @@
 #include <backendsCommon/Workload.hpp>
 
 #include <arm_compute/core/Error.h>
-#include <arm_compute/runtime/NEON/functions/NEArgMinMaxLayer.h>
+#include <arm_compute/runtime/IFunction.h>
+
 namespace armnn
 {
 
@@ -23,7 +24,7 @@
     virtual void Execute() const override;
 
 private:
-    mutable arm_compute::NEArgMinMaxLayer m_ArgMinMaxLayer;
+    std::unique_ptr<arm_compute::IFunction> m_ArgMinMaxLayer;
 };
 
 } //namespace armnn
diff --git a/src/backends/neon/workloads/NeonDepthwiseConvolutionWorkload.cpp b/src/backends/neon/workloads/NeonDepthwiseConvolutionWorkload.cpp
index 18085ed..2093613 100644
--- a/src/backends/neon/workloads/NeonDepthwiseConvolutionWorkload.cpp
+++ b/src/backends/neon/workloads/NeonDepthwiseConvolutionWorkload.cpp
@@ -120,19 +120,19 @@
 
     // Check for optimisation opportunities
     arm_compute::Status optimizationStatus =
-        arm_compute::NEDepthwiseConvolutionLayerOptimized::validate(inputInfo,
-                                                                    kernelInfo,
-                                                                    biasInfo,
-                                                                    outputInfo,
-                                                                    padStrideInfo,
-                                                                    depthMultiplier,
-                                                                    arm_compute::ActivationLayerInfo(),
-                                                                    aclDilationInfo);
+        arm_compute::NEDepthwiseConvolutionLayer::validate(inputInfo,
+                                                           kernelInfo,
+                                                           biasInfo,
+                                                           outputInfo,
+                                                           padStrideInfo,
+                                                           depthMultiplier,
+                                                           arm_compute::ActivationLayerInfo(),
+                                                           aclDilationInfo);
 
     if (optimizationStatus.error_code() == arm_compute::ErrorCode::OK)
     {
-        m_pDepthwiseConvolutionLayer = std::make_unique<arm_compute::NEDepthwiseConvolutionLayerOptimized>();
-        static_cast<arm_compute::NEDepthwiseConvolutionLayerOptimized*>(
+        m_pDepthwiseConvolutionLayer = std::make_unique<arm_compute::NEDepthwiseConvolutionLayer>();
+        static_cast<arm_compute::NEDepthwiseConvolutionLayer*>(
             m_pDepthwiseConvolutionLayer.get())->configure(&input,
                                                            m_KernelTensor.get(),
                                                            m_BiasTensor.get(),