diff --git a/src/core/CL/cl_kernels/gemm.cl b/src/core/CL/cl_kernels/gemm.cl
index b1bef30..b6afb85 100644
--- a/src/core/CL/cl_kernels/gemm.cl
+++ b/src/core/CL/cl_kernels/gemm.cl
@@ -2704,7 +2704,7 @@
 #if defined(REINTERPRET_OUTPUT_AS_3D)
 
     // The plane (zin) is calculated dividing M (y * M0) by HEIGHT_GEMM3D
-    CALCULATE_Z_OFFSET(M0, uint, zout, get_global_id(1), HEIGHT_GEMM3D, DEPTH_GEMM3D, dst_cross_plane_pad, dst_stride_y);
+    CALCULATE_Z_OFFSET(M0, uint, zout, get_global_id(1) * (uint)M0, HEIGHT_GEMM3D, DEPTH_GEMM3D, dst_cross_plane_pad, dst_stride_y);
     // Add offset for batched GEMM. The batches will be in the fourth dimension and for this reason we
     // multiply dst_stride_z by DEPTH_GEMM3D
     dst_addr += get_global_id(2) * dst_stride_z * DEPTH_GEMM3D;
@@ -2974,7 +2974,7 @@
 #if defined(REINTERPRET_OUTPUT_AS_3D)
 
     // The plane (zin) is calculated dividing M (y * M0) by HEIGHT_GEMM3D
-    CALCULATE_Z_OFFSET(M0, uint, zout, get_global_id(1), HEIGHT_GEMM3D, DEPTH_GEMM3D, dst_cross_plane_pad, dst_stride_y);
+    CALCULATE_Z_OFFSET(M0, uint, zout, get_global_id(1) * (uint)M0, HEIGHT_GEMM3D, DEPTH_GEMM3D, dst_cross_plane_pad, dst_stride_y);
     // Add offset for batched GEMM. The batches will be in the fourth dimension and for this reason we
     // multiply dst_stride_z by DEPTH_GEMM3D
     dst_addr += get_global_id(2) * dst_stride_z * DEPTH_GEMM3D;
@@ -3469,7 +3469,7 @@
 #if defined(REINTERPRET_OUTPUT_AS_3D)
 
     // The plane (zin) is calculated dividing M (y * M0) by HEIGHT_GEMM3D
-    CALCULATE_Z_OFFSET(M0, uint, zout, y, HEIGHT_GEMM3D, DEPTH_GEMM3D, dst_cross_plane_pad, dst_stride_y);
+    CALCULATE_Z_OFFSET(M0, uint, zout, y * (uint)M0, HEIGHT_GEMM3D, DEPTH_GEMM3D, dst_cross_plane_pad, dst_stride_y);
     // Add offset for batched GEMM. The batches will be in the fourth dimension and for this reason we
     // multiply dst_stride_z by DEPTH_GEMM3D
     dst_addr += z * dst_stride_z * DEPTH_GEMM3D;
@@ -3837,7 +3837,7 @@
 #if defined(REINTERPRET_OUTPUT_AS_3D)
 
     // The plane (zin) is calculated dividing M (y * M0) by HEIGHT_GEMM3D
-    CALCULATE_Z_OFFSET(M0, uint, zout, y, HEIGHT_GEMM3D, DEPTH_GEMM3D, dst_cross_plane_pad, dst_stride_y);
+    CALCULATE_Z_OFFSET(M0, uint, zout, y * (uint)M0, HEIGHT_GEMM3D, DEPTH_GEMM3D, dst_cross_plane_pad, dst_stride_y);
     // Add offset for batched GEMM. The batches will be in the fourth dimension and for this reason we
     // multiply dst_stride_z by DEPTH_GEMM3D
     dst_addr += z * dst_stride_z * DEPTH_GEMM3D;