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>

include/cutlass/numeric_conversion.h

@@ -192,7 +192,7 @@ struct NumericConverter<int8_t, float, FloatRoundStyle::round_to_nearest> {
     return static_cast<result_type>(intermediate);
   }
 
-  CUTLASS_DEVICE
+  CUTLASS_HOST_DEVICE
   result_type operator()(source_type const &s) const {
     return convert(s);
   }