merge develop

include/ck/utility/common_header.hpp

@@ -32,7 +32,7 @@
 #include "debug.hpp"
 
 #include "amd_buffer_addressing.hpp"
-#include "generic_memory_space_atomic_add.hpp"
+#include "generic_memory_space_atomic.hpp"
 #include "get_id.hpp"
 #include "synchronization.hpp"
 #include "amd_address_space.hpp"

include/ck/utility/statically_indexed_array_multi_index.hpp

@@ -93,6 +93,13 @@ __host__ __device__ constexpr auto operator*(index_t a, const Tuple<Xs...>& x)
     return r;
 }
 
+// MultiIndex = MultiIndex * index_t
+template <typename... Xs>
+__host__ __device__ constexpr auto operator*(const Tuple<Xs...>& x, index_t a)
+{
+    return a * x;
+}
+
 template <typename... Xs>
 __host__ __device__ void print_multi_index(const Tuple<Xs...>& x)
 {