Implement CLDirectConv3D f32/f16

Resolve COMPMID-4660

Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Change-Id: Ibd66ec1eb6faa60086981b1e3a9c12561df3445f
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6420
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
diff --git a/src/gpu/cl/ClKernelLibrary.cpp b/src/gpu/cl/ClKernelLibrary.cpp
index c05bb96..4af4226 100644
--- a/src/gpu/cl/ClKernelLibrary.cpp
+++ b/src/gpu/cl/ClKernelLibrary.cpp
@@ -433,6 +433,7 @@
     { "dwc_native_fp_nhwc", "nhwc/dwc_native_fp_nhwc.cl" },
     { "dwc_native_quantized_nhwc", "nhwc/dwc_native_quantized_nhwc.cl" },
     { "direct_convolution_nhwc", "nhwc/direct_convolution.cl" },
+    { "direct_convolution3d_ndhwc", "nhwc/direct_convolution3d.cl" },
     { "im2col3x3_nhwc", "nhwc/im2col.cl" },
     { "im2col9x9_nhwc", "nhwc/im2col.cl" },
     { "im2col_generic_nhwc", "nhwc/im2col.cl" },
@@ -858,6 +859,10 @@
 #include "./cl_kernels/nhwc/direct_convolution.clembed"
     },
     {
+        "nhwc/direct_convolution3d.cl",
+#include "./cl_kernels/nhwc/direct_convolution3d.clembed"
+    },
+    {
         "nhwc/dwc_native_fp_nhwc.cl",
 #include "./cl_kernels/nhwc/dwc_native_fp_nhwc.clembed"
     },