diff --git a/src/backends/cl/workloads/ClSoftmaxFloatWorkload.cpp b/src/backends/cl/workloads/ClSoftmaxFloatWorkload.cpp
index bb56802..c78ab03 100644
--- a/src/backends/cl/workloads/ClSoftmaxFloatWorkload.cpp
+++ b/src/backends/cl/workloads/ClSoftmaxFloatWorkload.cpp
@@ -4,11 +4,12 @@
 //
 
 #include "ClSoftmaxFloatWorkload.hpp"
+#include "ClWorkloadUtils.hpp"
+
+#include <aclCommon/ArmComputeUtils.hpp>
 #include <cl/ClTensorHandle.hpp>
 #include <backendsCommon/CpuTensorHandle.hpp>
 
-#include "ClWorkloadUtils.hpp"
-
 namespace armnn
 {
 
@@ -21,7 +22,9 @@
 
     arm_compute::ICLTensor& input  = static_cast<ClTensorHandle*>(m_Data.m_Inputs[0])->GetTensor();
     arm_compute::ICLTensor& output = static_cast<ClTensorHandle*>(m_Data.m_Outputs[0])->GetTensor();
-    m_SoftmaxLayer.configure(&input, &output, m_Data.m_Parameters.m_Beta);
+
+    unsigned int aclAxis = ComputeSoftmaxAclAxis(info.m_InputTensorInfos[0]);
+    m_SoftmaxLayer.configure(&input, &output, m_Data.m_Parameters.m_Beta, aclAxis);
 }
 
 void ClSoftmaxFloatWorkload::Execute() const
diff --git a/src/backends/cl/workloads/ClSoftmaxUint8Workload.cpp b/src/backends/cl/workloads/ClSoftmaxUint8Workload.cpp
index c386e38..086f375 100644
--- a/src/backends/cl/workloads/ClSoftmaxUint8Workload.cpp
+++ b/src/backends/cl/workloads/ClSoftmaxUint8Workload.cpp
@@ -4,11 +4,12 @@
 //
 
 #include "ClSoftmaxUint8Workload.hpp"
+#include "ClWorkloadUtils.hpp"
+
+#include <aclCommon/ArmComputeUtils.hpp>
 #include <cl/ClTensorHandle.hpp>
 #include <backendsCommon/CpuTensorHandle.hpp>
 
-#include "ClWorkloadUtils.hpp"
-
 namespace armnn
 {
 
@@ -30,7 +31,8 @@
             "Invalid quantization for output. Only scale = 1.0f / 256.0f and offset = 0 supported");
     }
 
-    m_SoftmaxLayer.configure(&input, &output, descriptor.m_Parameters.m_Beta);
+    unsigned int aclAxis = ComputeSoftmaxAclAxis(info.m_InputTensorInfos[0]);
+    m_SoftmaxLayer.configure(&input, &output, descriptor.m_Parameters.m_Beta, aclAxis);
 }
 
 void ClSoftmaxUint8Workload::Execute() const