Fix CUDA API Interportability (#639)

* Fixed a size_t to unsigned int warning in wrapper_cblas.hpp

* Update CHANGELOG

Co-authored-by: Cedric Nugteren <web@cedricnugteren.nl>

* Removed include of "clblast.h" which was breaking the library's compatibility with the CUDA API.

* Updated clblast_cuda API implementation to also include clblast_cuda.h

* Applied more clang format.

* Formatted remaining files.

* Formatted database files again.

* Fixed compilation errors.

* Removed CLBLAST_BUILDING_CLBLAST macro.

---------

Co-authored-by: Cedric Nugteren <web@cedricnugteren.nl>

Author: EJainDev

src/api_common.cpp

@@ -12,7 +12,6 @@
 #include <vector>
 
 #include "cache.hpp"
-#include "clblast.h"
 #include "database/database_structure.hpp"
 #include "routines/routines.hpp"
 #include "utilities/backend.hpp"

src/cache.hpp

@@ -17,7 +17,6 @@
 #include <string>
 #include <tuple>
 
-#include "clblast.h"
 #include "utilities/backend.hpp"
 
 namespace clblast {

src/clblast_c.cpp

@@ -12,7 +12,6 @@
 #include <cstddef>
 #include <string>
 
-#include "clblast.h"
 #include "utilities/clblast_exceptions.hpp"
 #include "utilities/utilities.hpp"
 

src/clblast_cuda.cpp

@@ -15,7 +15,6 @@
 #include <cstddef>
 #include <string>
 
-#include "clblast.h"
 #include "database/database.hpp"
 #include "routines/routines.hpp"
 #include "utilities/backend.hpp"

src/clblast_netlib_c.cpp

@@ -14,7 +14,6 @@
 #include <cstdlib>
 #include <stdexcept>
 
-#include "clblast.h"
 #include "utilities/backend.hpp"
 #include "utilities/utilities.hpp"
 

src/database/database.cpp

@@ -15,7 +15,6 @@
 #include <string>
 #include <vector>
 
-#include "clblast.h"
 #include "database/apple_cpu_fallback.hpp"
 #include "database/database_structure.hpp"
 #include "database/kernels/copy/copy.hpp"

src/database/database.hpp

@@ -19,7 +19,6 @@
 #include <unordered_map>
 #include <vector>
 
-#include "clblast.h"
 #include "database/database_structure.hpp"
 #include "utilities/backend.hpp"
 #include "utilities/clblast_exceptions.hpp"

src/database/database_structure.hpp

@@ -20,6 +20,7 @@
 #ifdef OPENCL_API
 #define CL_TARGET_OPENCL_VERSION 110
 #include "clblast.h"
+
 #elif CUDA_API
 #include "clblast_cuda.h"
 #endif

src/routine.cpp

@@ -17,7 +17,6 @@
 #include <vector>
 
 #include "cache.hpp"
-#include "clblast.h"
 #include "database/database_structure.hpp"
 #include "utilities/backend.hpp"
 #include "utilities/clblast_exceptions.hpp"

src/routine.hpp

@@ -19,7 +19,6 @@
 #include <vector>
 
 #include "cache.hpp"
-#include "clblast.h"
 #include "database/database.hpp"
 #include "database/database_structure.hpp"
 #include "utilities/backend.hpp"