Collection of changes to fix clang build. (#1200)

* Remove unused variables

* Qualify calls to make_fragment_? from templated base class.

Fixes clang build error.

* Add missing `#include <cstdio>`

* Various changes to fix clang compile errors.

* More changes to fix clang build.

Remaining issues:

- `params` initializer of `CollectiveEpilogue`.
- `ops` initializer of `Sm90VisitorImplBase`.
- `__usAtomicCAS` needs to be added to clang upstream.

* Fix remaining clang build issues.

* Qualify `cute::rank()` calls.

* Qualify some more calls that are otherwise ambiguous between `cute` and `std` namespace.

* Double-escape special registers in inline asm.

* small change

---------

Co-authored-by: Haicheng Wu <haichengw@nvidia.com>

examples/53_hopper_gemm_permute/53_hopper_gemm_permute.cu

@@ -197,14 +197,14 @@ template<class ... Shapes>
 auto
 select_mode_shape(Shapes const & ... shapes) {
   auto permuted_shapes = filter_tuple(cute::make_tuple(shapes...), [](auto shape) {
-    if constexpr (rank(shape) > 1) {
+    if constexpr (cute::rank(shape) > 1) {
       return cute::make_tuple(shape);
     }
     else {
       return cute::make_tuple();
     }
   });
-  if constexpr (rank(permuted_shapes) == 0) {
+  if constexpr (cute::rank(permuted_shapes) == 0) {
     return get<0>(cute::make_tuple(shapes...));
   }
   else {
@@ -251,7 +251,7 @@ auto
 select_tile_shape(TileSize size, Shape const& shape)
 {
   static_assert(is_static<TileSize>::value, "Tile size must be static");
-  if constexpr (rank(Shape{}) == 0) {
+  if constexpr (cute::rank(Shape{}) == 0) {
     return cute::make_tuple(size);
   }
   else {