diff --git a/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h b/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h
index 2520eff..c0fef45 100644
--- a/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017 ARM Limited.
+ * Copyright (c) 2017-2018 ARM Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -47,7 +47,7 @@
  * \end{array} \right)
  * @f]
  *
- * After this operation, the output matrix will have the following shape: [ height * 4, ceil(width / 4.0f) ]
+ * After this operation, the output matrix will have the following shape: [ height * W, ceil(width / W) ] where W = 4 * mult_interleave4x4_height
  */
 class CLGEMMInterleave4x4Kernel : public ICLKernel
 {
@@ -64,18 +64,20 @@
     CLGEMMInterleave4x4Kernel &operator=(CLGEMMInterleave4x4Kernel &&) = default;
     /** Initialise the kernel's input and output.
      *
-     * @param[in]  input  Input tensor. Data types supported: U8/S8/QS8/QASYMM8/U16/S16/QS16/F16/U32/S32/F32
-     * @param[out] output Output tensor. Data type supported: same as @p input
+     * @param[in]  input                     Input tensor. Data types supported: U8/S8/QS8/QASYMM8/U16/S16/QS16/F16/U32/S32/F32
+     * @param[out] output                    Output tensor. Data type supported: same as @p input
+     * @param[in]  mult_interleave4x4_height (Optional) Multiplication factor for the height of the 4x4 interleave block
      */
-    void configure(const ICLTensor *input, ICLTensor *output);
+    void configure(const ICLTensor *input, ICLTensor *output, int mult_interleave4x4_height = 1);
     /** Static function to check if given info will lead to a valid configuration of @ref CLGEMMInterleave4x4Kernel
      *
-     * @param[in] input  Input tensor info. Data types supported: U8/S8/QS8/QASYMM8/U16/S16/QS16/F16/U32/S32/F32
-     * @param[in] output Output tensor info which stores the interleaved matrix. Data type supported: same as @p input.
+     * @param[in] input                     Input tensor info. Data types supported: U8/S8/QS8/QASYMM8/U16/S16/QS16/F16/U32/S32/F32
+     * @param[in] output                    Output tensor info which stores the interleaved matrix. Data type supported: same as @p input.
+     * @param[in] mult_interleave4x4_height Multiplication factor for the height of the 4x4 interleave block
      *
      * @return a status
      */
-    static Status validate(const ITensorInfo *input, const ITensorInfo *output);
+    static Status validate(const ITensorInfo *input, const ITensorInfo *output, int mult_interleave4x4_height);
 
     // Inherited methods overridden
     void run(const Window &window, cl::CommandQueue &queue) override;
diff --git a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h
index 4e73d7e..7260c4a 100644
--- a/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMMatrixMultiplyKernel.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017 ARM Limited.
+ * Copyright (c) 2017-2018 ARM Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -58,8 +58,10 @@
      * @param[out] output                    Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0
      * @param[in]  alpha                     Weight of the matrix product
      * @param[in]  is_interleaved_transposed (Optional) True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMTranspose1xWKernel
+     * @param[in]  reshape_info              (Optional) GEMM reshape info. If is_interleaved_transposed = true, this object must contain the information to understand how the matrix A and matrix B have been reshaped
+     *
      */
-    void configure(const ICLTensor *input0, const ICLTensor *input1, ICLTensor *output, float alpha, bool is_interleaved_transposed = true);
+    void configure(const ICLTensor *input0, const ICLTensor *input1, ICLTensor *output, float alpha, bool is_interleaved_transposed = true, const GEMMReshapeInfo &reshape_info = GEMMReshapeInfo());
     /** Static function to check if given info will lead to a valid configuration of @ref CLGEMMMatrixMultiplyKernel
      *
      * @param[in] input0                    Input tensor containing the Matrix A. Data types supported: QS8/QS16/F16/F32
@@ -67,11 +69,13 @@
      * @param[in] output                    Output tensor to store the result of matrix multiplication. Data type supported: same as @p input0
      * @param[in] alpha                     Weight of the matrix product
      * @param[in] is_interleaved_transposed True if input0 and input1 have been reshaped respectively using @ref CLGEMMInterleave4x4Kernel and @ref CLGEMMTranspose1xWKernel
+     * @param[in] reshape_info              GEMM reshape info. If is_interleaved_transposed = true, this object must contain the information to understand how the matrix A and matrix B have been reshaped
      * @param[in] gpu_target                GPU Target
      *
      * @return a status
      */
-    static Status validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *output, float alpha, bool is_interleaved_transposed, GPUTarget gpu_target);
+    static Status validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *output, float alpha, bool is_interleaved_transposed, const GEMMReshapeInfo &reshape_info,
+                           GPUTarget gpu_target);
 
     // Inherited methods overridden:
     void run(const Window &window, cl::CommandQueue &queue) override;
diff --git a/arm_compute/core/CL/kernels/CLGEMMTranspose1xWKernel.h b/arm_compute/core/CL/kernels/CLGEMMTranspose1xWKernel.h
index 8721643..9a3069e 100644
--- a/arm_compute/core/CL/kernels/CLGEMMTranspose1xWKernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMTranspose1xWKernel.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017 ARM Limited.
+ * Copyright (c) 2017-2018 ARM Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -62,7 +62,7 @@
  * \end{array} \right)
  * @f]
  *
- * @note The output matrix will have the following shape: [ height * W, ceil(width / W) ], where W = (16 / element size of the tensor)
+ * @note The output matrix will have the following shape: [ height * W, ceil(width / W) ], where W = (16 / element size of the tensor) * mult_transpose1xW_width
  *
  */
 class CLGEMMTranspose1xWKernel : public ICLSimple2DKernel
@@ -70,18 +70,20 @@
 public:
     /** Initialise the kernel's input and output.
      *
-     * @param[in]  input  Input tensor. Data types supported: U8/S8/QS8/QASYMM8/U16/S16/QS16/F16/U32/S32/F32
-     * @param[out] output Output tensor. Data type supported: same as @p input
+     * @param[in]  input                   Input tensor. Data types supported: U8/S8/QS8/QASYMM8/U16/S16/QS16/F16/U32/S32/F32
+     * @param[out] output                  Output tensor. Data type supported: same as @p input
+     * @param[in]  mult_transpose1xW_width (Optional) Multiplication factor for the width of the 1xW transposed block
      */
-    void configure(const ICLTensor *input, ICLTensor *output);
+    void configure(const ICLTensor *input, ICLTensor *output, int mult_transpose1xW_width = 1);
     /** Static function to check if given info will lead to a valid configuration of @ref CLGEMMTranspose1xWKernel
      *
-     * @param[in] input  Input tensor. Data types supported: U8/S8/QS8/QASYMM8/U16/S16/QS16/F16/U32/S32/F32
-     * @param[in] output Output tensor. Data type supported: same as @p input.
+     * @param[in] input                   Input tensor. Data types supported: U8/S8/QS8/QASYMM8/U16/S16/QS16/F16/U32/S32/F32
+     * @param[in] output                  Output tensor. Data type supported: same as @p input.
+     * @param[in] mult_transpose1xW_width Multiplication factor for the width of the 1xW transposed block
      *
      * @return a status
      */
-    static Status validate(const ITensorInfo *input, const ITensorInfo *output);
+    static Status validate(const ITensorInfo *input, const ITensorInfo *output, int mult_transpose1xW_width);
 
     // Inherited methods overridden:
     void run(const Window &window, cl::CommandQueue &queue) override;