COMPMID-817: Tuner: Port kernels to new design.

Change-Id: Iaabb1153c2abe0400ec79d51a21347debe92d642
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/134062
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
diff --git a/src/runtime/CL/functions/CLGEMM.cpp b/src/runtime/CL/functions/CLGEMM.cpp
index 7f37520..a0ec66f 100644
--- a/src/runtime/CL/functions/CLGEMM.cpp
+++ b/src/runtime/CL/functions/CLGEMM.cpp
@@ -143,7 +143,9 @@
         _transpose_kernel.configure(b, &_tmp_b, mult_transpose1xW_width);
     }
 
+    // Configure and tune matrix multiply kernel
     _mm_kernel.configure(matrix_a, matrix_b, output, alpha, _is_interleaved_transposed, GEMMReshapeInfo(m, n, k, mult_transpose1xW_width, mult_interleave4x4_height));
+    CLScheduler::get().tune_kernel_static(_mm_kernel);
 
     if(_is_interleaved_transposed)
     {