[CK_BUILDER] Put global CK functions in an the CK namespace (#3232)

* Wrap ck host utitlies in CK namespace.

The CK and CK-Tile source code bases are incompatible because CK is not properly using namespaces everywhere. In particular, we need to put hip_check_error in the ck namespace.

Move all functions in include/ck_/host_utility that were in global namespace into the ck namespace.

There may be additional namespace problems like this, and it's possible we'll have namespace clashes. But it is good design to properly guard our to code bases (CK and CKTile) so that they can both coexist. Moreover, estabilishing this compatiblity is essential if we are going to allow the builder to instantiate  kernels from either template library.

* Add using declarations to test code.

After moving some of the untils into the ck namespace, most examples and a few tests had to be updated to recognize the new namespace declarations. We add using declarations to individual compute units for functions that were previously in the global namespace.

* Add using declarations to client examples.

include/ck/host_utility/hip_check_error.hpp

@@ -6,6 +6,8 @@
 #include <sstream>
 #include <hip/hip_runtime.h>
 
+namespace ck {
+
 // To be removed, which really does not tell the location of failed HIP functional call
 inline void hip_check_error(hipError_t x)
 {
@@ -30,3 +32,5 @@ inline void hip_check_error(hipError_t x)
             throw std::runtime_error(ostr.str());                                  \
         }                                                                          \
     } while(0)
+
+} // namespace ck

include/ck/host_utility/io.hpp

@@ -10,6 +10,8 @@
 
 #include "ck/tensor_description/tensor_descriptor.hpp"
 
+namespace ck {
+
 template <typename T>
 std::ostream& operator<<(std::ostream& os, const std::vector<T>& v)
 {
@@ -25,17 +27,19 @@ std::ostream& operator<<(std::ostream& os, const std::array<T, N>& v)
 }
 
 template <typename... Ts>
-std::ostream& operator<<(std::ostream& os, const ck::TensorDescriptor<Ts...>& desc)
+std::ostream& operator<<(std::ostream& os, const TensorDescriptor<Ts...>& desc)
 {
-    constexpr ck::index_t nDim = ck::remove_cvref_t<decltype(desc)>::GetNumOfDimension();
+    constexpr index_t nDim = remove_cvref_t<decltype(desc)>::GetNumOfDimension();
 
     os << "{";
 
-    ck::static_for<0, nDim - 1, 1>{}([&](auto i) { os << desc.GetLength(i) << ", "; });
+    static_for<0, nDim - 1, 1>{}([&](auto i) { os << desc.GetLength(i) << ", "; });
 
-    os << desc.GetLength(ck::Number<nDim - 1>{});
+    os << desc.GetLength(Number<nDim - 1>{});
 
     os << "}";
 
     return os;
 }
+
+} // namespace ck

include/ck/host_utility/kernel_launch.hpp

@@ -10,6 +10,8 @@
 #include "ck/stream_config.hpp"
 #include "ck/host_utility/hip_check_error.hpp"
 
+namespace ck {
+
 template <typename... Args, typename F>
 float launch_and_time_kernel(const StreamConfig& stream_config,
                              F kernel,
@@ -167,4 +169,7 @@ float launch_and_time_kernel_with_preprocess(const StreamConfig& stream_config,
     return 0;
 #endif
 }
+
+} // namespace ck
+
 #endif

include/ck/host_utility/stream_utility.hpp

@@ -8,6 +8,8 @@
 #include "ck/stream_config.hpp"
 #include "ck/host_utility/hip_check_error.hpp"
 
+namespace ck {
+
 static inline int getAvailableComputeUnitCount(const StreamConfig& stream_config)
 {
     constexpr int MAX_MASK_DWORDS = 64;
@@ -41,3 +43,5 @@ static inline int getAvailableComputeUnitCount(const StreamConfig& stream_config
 
     return (ret);
 };
+
+} // namespace ck