[SYCL][bfloat16] Simplify bfloat16 class (#17258)

This change makes a few changes aiming to make the code more readable.

* Move declaration of the bfloat16 class right on top of the header file
  and move all declarations with the implementation helpers after the
  class declaration.

* Converted ConvertToBfloat16 class to namespace. The class doesn't
  represent any object, it's a collection of static methods.

* Declare public API of the class first.

* Move Bfloat16StorageT declaration from the detail namespace directly
  into bfloat16 class definition.

* Co-locate declaration of functions with similar functionality (e.g.
  conversion functions).

* Simplified uniry operator- implementation by removing additional
  branch for the SPIR target. Generic code for SPIR target produces
  exactly the same code.

* Added compile time checks for the array size inside conversion helper
  functions. Device side implementation of these functions work
  correctly only for certain array sizes.

* Include C++ header instead of C (i.e. cstdint instead of stdint.h).

* Applied "no-else-after-return" and "no-braces-for-single-statement-if"
  coding style changes.

Author: bader

sycl/include/sycl/detail/generic_type_traits.hpp

@@ -172,7 +172,7 @@ template <typename T> auto convertToOpenCLType(T &&x) {
   } else if constexpr (std::is_same_v<no_ref, ext::oneapi::bfloat16>) {
     // On host, don't interpret BF16 as uint16.
 #ifdef __SYCL_DEVICE_ONLY__
-    using OpenCLType = sycl::ext::oneapi::detail::Bfloat16StorageT;
+    using OpenCLType = sycl::ext::oneapi::bfloat16::Bfloat16StorageT;
     return sycl::bit_cast<OpenCLType>(x);
 #else
     return std::forward<T>(x);