diff --git a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
index 04ce1cf..8dfb6c8 100644
--- a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
+++ b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
@@ -78,7 +78,8 @@
      * @param[in]  input            Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
      *                              while every optional dimension from 4 and above represent a batch of inputs.
      *                              Data types supported: QASYMM8/F16/F32.
-     * @param[in]  weights          Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported: Same as @p input.
+     * @param[in]  weights          Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
+     *                              Data type supported: Same as @p input or QASYMM8/QSYMM8_PER_CHANNEL when @p input is QASYMM8.
      * @param[in]  biases           Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
      *                              Data type supported: Should match @p input data type, except for input of QASYMM8 type where biases should be of S32 type.
      * @param[out] output           Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
@@ -98,7 +99,8 @@
      * @param[in] input            Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
      *                             while every optional dimension from 4 and above represent a batch of inputs.
      *                             Data types supported: QASYMM8/F16/F32.
-     * @param[in] weights          Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported:Same as @p input.
+     * @param[in] weights          Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
+     *                             Data type supported: Same as @p input or QASYMM8/QSYMM8_PER_CHANNEL when @p input is QASYMM8.
      * @param[in] biases           Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. Data type supported:Same as @p input.
      * @param[in] output           Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
      *                             Data types supported: Same as @p input.
@@ -120,7 +122,8 @@
      * @param[in] input            Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
      *                             while every optional dimension from 4 and above represent a batch of inputs.
      *                             Data types supported: QASYMM8/F16/F32.
-     * @param[in] weights          Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported:Same as @p input.
+     * @param[in] weights          Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
+     *                             Data type supported: Same as @p input or QASYMM8/QSYMM8_PER_CHANNEL when @p input is QASYMM8.
      * @param[in] output           Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
      *                             Data types supported: Same as @p input.
      * @param[in] conv_info        Contains padding and stride information described in @ref PadStrideInfo.
diff --git a/arm_compute/runtime/CL/functions/CLGEMMConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLGEMMConvolutionLayer.h
index 017bf78..3392f11 100644
--- a/arm_compute/runtime/CL/functions/CLGEMMConvolutionLayer.h
+++ b/arm_compute/runtime/CL/functions/CLGEMMConvolutionLayer.h
@@ -60,7 +60,7 @@
     /** Set the input and output tensors.
      *
      * @param[in]  weights    Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
-     *                        Data type supported: QASYMM8/F16/F32.
+     *                        Data type supported: QASYMM8/QSYMM8_PER_CHANNEL/F16/F32.
      * @param[in]  biases     Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p weights.
      * @param[out] output     Destination tensor. Data types supported: Same as @p weights.
      * @param[in]  num_groups (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is only supported for NCHW data layout
@@ -69,7 +69,7 @@
     /** Static function to check if given info will lead to a valid configuration of @ref CLConvolutionLayerReshapeWeights
      *
      * @param[in] weights    Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
-     *                       Data type supported: QASYMM8/F16/F32.
+     *                       Data type supported: QASYMM8/QSYMM8_PER_CHANNEL/F16/F32.
      * @param[in] biases     Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p weights.
      * @param[in] output     Destination tensor. Data types supported: Same as @p weights.
      * @param[in] num_groups (Optional) Number of groups when performing a grouped convolution. num_groups != 1 is only supported for NCHW data layout
@@ -168,7 +168,8 @@
      * @param[in]  input        Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
      *                          while every optional dimension from 4 and above represent a batch of inputs.
      *                          Data types supported: QASYMM8/F16/F32.
-     * @param[in]  weights      Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported: Same as @p input.
+     * @param[in]  weights      Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
+     *                          Data type supported: Same as @p input or QASYMM8/QSYMM8_PER_CHANNEL when @p input is QASYMM8.
      * @param[in]  biases       Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
      *                          Data type supported: Should match @p input data type, except for input of QASYMM8 type where biases should be of S32 type.
      * @param[out] output       Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
@@ -187,7 +188,8 @@
      * @param[in]  input        Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
      *                          while every optional dimension from 4 and above represent a batch of inputs.
      *                          Data types supported: QASYMM8/F16/F32.
-     * @param[in]  weights      Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported: Same as @p input.
+     * @param[in]  weights      Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM].
+     *                          Data type supported: Same as @p input or QASYMM8/QSYMM8_PER_CHANNEL when @p input is QASYMM8.
      * @param[in]  biases       Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
      *                          Data type supported: Should match @p input data type, except for input of QASYMM8 type where biases should be of S32 type.
      * @param[out] output       Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
@@ -212,7 +214,7 @@
     /** Configures the appropriate matrix multiply routine
      *
      * @param[in]      input                 Input tensor. Data types supported: QASYMM8/F16/F32.
-     * @param[in]      weights               Weights tensor. Data type supported: Same as @p input.
+     * @param[in]      weights               Weights tensor. Data type supported: Same as @p input or QASYMM8/QSYMM8_PER_CHANNEL when @p input is QASYMM8.
      * @param[in]      biases                Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
      *                                       Data type supported: Should match @p input data type, except for input of QASYMM8 type where biases should be of S32 type.
      * @param[in, out] output                Output tensor. Data types supported: Same as @p input,
@@ -225,12 +227,12 @@
                       const ActivationLayerInfo &act_info);
     /** Static function to check if given info will lead to a valid configuration of @ref CLGEMMConvolutionLayer matrix multiply routines
      *
-     * @param[in] input                 Input tensor. Data types supported: QASYMM8/F16/F32.
-     * @param[in] weights               Weights tensor. Data type supported: Same as @p input.
-     * @param[in] output                Output tensor. Data types supported: Same as @p input,
-     *                                  except for input of QASYMM8 type where output should be of S32 type.
-     * @param[in] biases                Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
+     * @param[in] input                 Input tensor info. Data types supported: QASYMM8/F16/F32.
+     * @param[in] weights               Weights tensor info. Data type supported: Same as @p input or QASYMM8/QSYMM8_PER_CHANNEL when @p input is QASYMM8.
+     * @param[in] biases                Biases tensor info. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
      *                                  Data type supported: Should match @p input data type, except for input of QASYMM8 type where biases should be of S32 type.
+     * @param[in] output                Output tensor info. Data types supported: Same as @p input,
+     *                                  except for input of QASYMM8 type where output should be of S32 type.
      * @param[in] gemmlowp_output_stage GEMMLowp output stage info
      * @param[in] gemm_3d_depth         Depth of GEMM 3D
      * @param[in] skip_im2col           Flag which specifies if im2col has to be skipped. i.e. 1x1 convolution with NHWC data layout.
diff --git a/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h b/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h
index 6aacbf6..b364653 100644
--- a/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h
+++ b/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h
@@ -24,6 +24,7 @@
 #ifndef __ARM_COMPUTE_CLGEMMLOWPMATRIXMULTIPLYCORE_H__
 #define __ARM_COMPUTE_CLGEMMLOWPMATRIXMULTIPLYCORE_H__
 
+#include "arm_compute/core/CL/kernels/CLDepthConvertLayerKernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyKernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.h"
 #include "arm_compute/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.h"
@@ -49,6 +50,7 @@
  *  -# @ref CLGEMMLowpMatrixBReductionKernel (if the offset of matrix A is not 0)
  *  -# @ref CLGEMMLowpOffsetContributionKernel (if gemm_info.gemmlowp_output_stage == NONE)
  *  -# @ref CLGEMMLowpOffsetContributionOutputStageKernel (if gemm_info.gemmlowp_output_stage != NONE)
+ *  -# @ref CLDepthConvertLayerKernel
  *
 */
 class CLGEMMLowpMatrixMultiplyCore : public IFunction
@@ -84,10 +86,10 @@
     void configure(const ICLTensor *a, const ICLTensor *b, const ICLTensor *c, ICLTensor *output, const GEMMInfo &gemm_info = GEMMInfo());
     /** Static function to check if given info will lead to a valid configuration of @ref CLGEMMLowpMatrixMultiplyCore
      *
-     * @param[in] a         First input tensor  (Matrix A). Data type supported: QASYMM8.
-     * @param[in] b         Second input tensor (Matrix B). Data type supported: same as @p a
-     * @param[in] c         Third input tensor  (Matrix C). It can be a nullptr. Data type supported: S32
-     * @param[in] output    Output tensor. Data type supported: S32 or QASYMM8 if gemm_info.gemmlowp_output_stage != NONE
+     * @param[in] a         First input tensor info (Matrix A). Data type supported: QASYMM8.
+     * @param[in] b         Second input tensor info (Matrix B). Data type supported: same as @p a
+     * @param[in] c         Third input tensor info (Matrix C). It can be a nullptr. Data type supported: S32
+     * @param[in] output    Output tensor info. Data type supported: S32 or QASYMM8 if gemm_info.gemmlowp_output_stage != NONE
      * @param[in] gemm_info (Optional) Specifies if the matrix A and/or matrix B have been reshaped and
      *                      if the reshape of matrix B should be executed only for the first run
      *
@@ -100,7 +102,10 @@
     void prepare() override;
 
 private:
-    MemoryGroup                                   _memory_group;
+    MemoryGroup _memory_group;
+
+    // Kernels used
+    CLDepthConvertLayerKernel                     _weights_to_qasymm8;
     CLGEMMLowpMatrixMultiplyKernel                _mm_midgard_kernel;
     CLGEMMLowpMatrixMultiplyNativeKernel          _mm_native_kernel;
     CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel _mm_reshaped_only_rhs_kernel;
@@ -109,18 +114,29 @@
     CLGEMMLowpMatrixBReductionKernel              _mtx_b_reduction_kernel;
     CLGEMMLowpOffsetContributionKernel            _offset_contribution_kernel;
     CLGEMMLowpOffsetContributionOutputStageKernel _offset_contribution_output_stage_kernel;
-    CLTensor                                      _vector_sum_col;
-    CLTensor                                      _vector_sum_row;
-    CLTensor                                      _tmp_b;
-    CLTensor                                      _mm_result_s32;
-    const ICLTensor                              *_original_b;
-    int32_t                                       _a_offset;
-    int32_t                                       _b_offset;
-    bool                                          _is_gemm_reshaped;
-    bool                                          _is_midgard;
-    bool                                          _reshape_b_only_on_first_run;
-    bool                                          _is_prepared;
-    bool                                          _fuse_output_stage;
+
+    // Temporary tensors
+    CLTensor _qasymm8_weights;
+    CLTensor _vector_sum_col;
+    CLTensor _vector_sum_row;
+    CLTensor _tmp_b;
+    CLTensor _mm_result_s32;
+    CLTensor _gemm_output_stage_multipliers;
+    CLTensor _gemm_output_stage_shifts;
+
+    // Tensor pointers
+    const ICLTensor *_matrix_a;
+    const ICLTensor *_original_b;
+    const ICLTensor *_output;
+
+    int32_t _a_offset;
+    int32_t _b_offset;
+    bool    _is_gemm_reshaped;
+    bool    _is_midgard;
+    bool    _reshape_b_only_on_first_run;
+    bool    _is_prepared;
+    bool    _fuse_output_stage;
+    bool    _convert_to_qasymm8;
 };
-}
+} // namespace arm_compute
 #endif /*__ARM_COMPUTE_CLGEMMLOWPMATRIXMULTIPLYCORE_H__ */
\ No newline at end of file