Doc update - describe debug techniques

Also tweak sample to remove unneeded HIP_KERNEL_NAME.
Comment update


[ROCm/hip commit: 1f5d16afe7]

projects/hip/samples/0_Intro/square/square.hipref.cpp

@@ -81,7 +81,7 @@ int main(int argc, char *argv[])
     const unsigned threadsPerBlock = 256;
 
     printf ("info: launch 'vector_square' kernel\n");
-    hipLaunchKernel(HIP_KERNEL_NAME(vector_square), dim3(blocks), dim3(threadsPerBlock), 0, 0, C_d, A_d, N);
+    hipLaunchKernel(vector_square, dim3(blocks), dim3(threadsPerBlock), 0, 0, C_d, A_d, N);
 
     printf ("info: copy Device2Host\n");
     CHECK ( hipMemcpy(C_h, C_d, Nbytes, hipMemcpyDeviceToHost));