[CK] Integrate GPU reference into ckProfiler for convolutions (#3379)

Refactor and integrate CK GPU references into ckProfiler.
- All convolution layouts and groupings supported for all three directions
- Unit tests verifying GPU and CPU reference is the same
- Support added to profiler (do_verification = 2 enables GPU reference)
- One profiler-based test per direction changed to GPU reference to demonstrate usag

Closes AICK-427

example/09_convnd_fwd/run_convnd_fwd_example.inc

@@ -12,7 +12,7 @@ bool run_convnd_fwd_example(int argc, char* argv[])
 {
     print_helper_msg();
 
-    int do_verification = 1; // 0=no, 1=CPU, 2=GPU
+    int do_verification = 2; // 0=no, 1=CPU, 2=GPU
     int init_method     = 1;
     bool time_kernel    = false;
 
@@ -71,6 +71,9 @@ bool run_convnd_fwd_example(int argc, char* argv[])
             WeiElementOp,
             OutElementOp,
             DeviceGroupedConvNDFwdInstance<ndim_spatial_value, InLayout, WeiLayout, OutLayout>,
+            InLayout,
+            WeiLayout,
+            OutLayout,
             ComputeDataType>(do_verification,
                              init_method,
                              time_kernel,