COMPMID-421: Fixed FP16 support in Neon GEMM.

Fixed GEMM FP16 problem with matrices that are not multiple of 32.
Added a new test suite NEON/GEMM/Float16/SmallGEMM.
Implemented FP16 function to multiply vector by a matrix.

Change-Id: Ie6c692885a48d0206bd6fe748332fa83bc286d67
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/79118
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Moritz Pflanzer <moritz.pflanzer@arm.com>
diff --git a/scripts/check_clang-tidy.py b/scripts/check_clang-tidy.py
index a376d0b..6ab1747 100755
--- a/scripts/check_clang-tidy.py
+++ b/scripts/check_clang-tidy.py
@@ -39,6 +39,7 @@
                    ("Validation.cpp" in line and "parameter 'expected_labels' is unused" in line) or
                    ("Reference.cpp" in line and "parameter 'rois' is unused" in line) or
                    ("ReferenceCPP.cpp" in line and "parameter 'rois' is unused" in line) or
+                   ("NEGEMMMatrixMultiplyKernel.cpp" in line and "do not use C-style cast to convert between unrelated types" in line) or
                    "3rdparty" in line):
                     continue