Renamed all C++ source files to .cpp to match the .hpp extension better

CHANGELOG

@@ -4,6 +4,7 @@ Development version (next release)
 - Made it possible to compile the performance tests (clients) separately from the correctness tests
 - Made a reference BLAS and head-to-head performance comparison optional in the clients
 - Increased the verbosity of the "-verbose" option in the correctness tests
+- Refactored the host code for better compilation times and fewer lines of code
 - Improved the API documentation
 - Various minor fixes and enhancements
 - Added tuned parameters for various devices (see README)

CMakeLists.txt

@@ -141,25 +141,25 @@ set(PRECISIONS 32 64 3232 6464)
 
 # Gathers all source-files
 set(SOURCES
-  src/database/database.cc
-  src/routines/common.cc
-  src/cache.cc
-  src/clblast.cc
-  src/clblast_c.cc
-  src/routine.cc
-  src/utilities.cc
+  src/database/database.cpp
+  src/routines/common.cpp
+  src/cache.cpp
+  src/clblast.cpp
+  src/clblast_c.cpp
+  src/routine.cpp
+  src/utilities.cpp
 )
 foreach(ROUTINE ${LEVEL1_ROUTINES})
-  set(SOURCES ${SOURCES} src/routines/level1/${ROUTINE}.cc)
+  set(SOURCES ${SOURCES} src/routines/level1/${ROUTINE}.cpp)
 endforeach()
 foreach(ROUTINE ${LEVEL2_ROUTINES})
-  set(SOURCES ${SOURCES} src/routines/level2/${ROUTINE}.cc)
+  set(SOURCES ${SOURCES} src/routines/level2/${ROUTINE}.cpp)
 endforeach()
 foreach(ROUTINE ${LEVEL3_ROUTINES})
-  set(SOURCES ${SOURCES} src/routines/level3/${ROUTINE}.cc)
+  set(SOURCES ${SOURCES} src/routines/level3/${ROUTINE}.cpp)
 endforeach()
 foreach(ROUTINE ${LEVELX_ROUTINES})
-  set(SOURCES ${SOURCES} src/routines/levelx/${ROUTINE}.cc)
+  set(SOURCES ${SOURCES} src/routines/levelx/${ROUTINE}.cpp)
 endforeach()
 
 # Creates and links the library
@@ -193,7 +193,7 @@ if(SAMPLES)
 
   # Adds sample programs (C++)
   foreach(SAMPLE ${SAMPLE_PROGRAMS_CPP})
-    add_executable(clblast_sample_${SAMPLE} samples/${SAMPLE}.cc)
+    add_executable(clblast_sample_${SAMPLE} samples/${SAMPLE}.cpp)
     target_link_libraries(clblast_sample_${SAMPLE} clblast ${OPENCL_LIBRARIES})
     install(TARGETS clblast_sample_${SAMPLE} DESTINATION bin)
   endforeach()
@@ -218,7 +218,7 @@ if(TUNERS)
 
   # Adds tuning executables
   foreach(KERNEL ${KERNELS})
-    add_executable(clblast_tuner_${KERNEL} src/tuning/kernels/${KERNEL}.cc)
+    add_executable(clblast_tuner_${KERNEL} src/tuning/kernels/${KERNEL}.cpp)
     target_link_libraries(clblast_tuner_${KERNEL} clblast ${CLTUNE_LIBRARIES} ${OPENCL_LIBRARIES})
     install(TARGETS clblast_tuner_${KERNEL} DESTINATION bin)
   endforeach()
@@ -275,24 +275,24 @@ endif()
 if(CLIENTS)
 
   # Creates the common performance-tests objects (requires CMake 2.8.8)
-  add_library(test_performance_common OBJECT test/performance/client.cc)
+  add_library(test_performance_common OBJECT test/performance/client.cpp)
 
   # Compiles the performance-tests
   foreach(ROUTINE ${LEVEL1_ROUTINES})
     add_executable(clblast_client_${ROUTINE} $<TARGET_OBJECTS:test_performance_common>
-                   test/performance/routines/level1/${ROUTINE}.cc)
+                   test/performance/routines/level1/${ROUTINE}.cpp)
   endforeach()
   foreach(ROUTINE ${LEVEL2_ROUTINES})
     add_executable(clblast_client_${ROUTINE} $<TARGET_OBJECTS:test_performance_common>
-                   test/performance/routines/level2/${ROUTINE}.cc)
+                   test/performance/routines/level2/${ROUTINE}.cpp)
   endforeach()
   foreach(ROUTINE ${LEVEL3_ROUTINES})
     add_executable(clblast_client_${ROUTINE} $<TARGET_OBJECTS:test_performance_common>
-                   test/performance/routines/level3/${ROUTINE}.cc)
+                   test/performance/routines/level3/${ROUTINE}.cpp)
   endforeach()
   foreach(ROUTINE ${LEVELX_ROUTINES})
     add_executable(clblast_client_${ROUTINE} $<TARGET_OBJECTS:test_performance_common>
-                   test/performance/routines/levelx/${ROUTINE}.cc)
+                   test/performance/routines/levelx/${ROUTINE}.cpp)
   endforeach()
   foreach(ROUTINE ${ROUTINES})
     target_link_libraries(clblast_client_${ROUTINE} clblast ${REF_LIBRARIES} ${OPENCL_LIBRARIES})
@@ -310,24 +310,24 @@ if(TESTS)
 
   # Creates the common correctness-tests objects (requires CMake 2.8.8)
   add_library(test_correctness_common OBJECT
-              test/correctness/tester.cc test/correctness/testblas.cc)
+              test/correctness/tester.cpp test/correctness/testblas.cpp)
 
   # Compiles the correctness-tests
   foreach(ROUTINE ${LEVEL1_ROUTINES})
     add_executable(clblast_test_${ROUTINE} $<TARGET_OBJECTS:test_correctness_common>
-                   test/correctness/routines/level1/${ROUTINE}.cc)
+                   test/correctness/routines/level1/${ROUTINE}.cpp)
   endforeach()
   foreach(ROUTINE ${LEVEL2_ROUTINES})
     add_executable(clblast_test_${ROUTINE} $<TARGET_OBJECTS:test_correctness_common>
-                   test/correctness/routines/level2/${ROUTINE}.cc)
+                   test/correctness/routines/level2/${ROUTINE}.cpp)
   endforeach()
   foreach(ROUTINE ${LEVEL3_ROUTINES})
     add_executable(clblast_test_${ROUTINE} $<TARGET_OBJECTS:test_correctness_common>
-                   test/correctness/routines/level3/${ROUTINE}.cc)
+                   test/correctness/routines/level3/${ROUTINE}.cpp)
   endforeach()
   foreach(ROUTINE ${LEVELX_ROUTINES})
     add_executable(clblast_test_${ROUTINE} $<TARGET_OBJECTS:test_correctness_common>
-                   test/correctness/routines/levelx/${ROUTINE}.cc)
+                   test/correctness/routines/levelx/${ROUTINE}.cpp)
   endforeach()
   foreach(ROUTINE ${ROUTINES})
     target_link_libraries(clblast_test_${ROUTINE} clblast ${REF_LIBRARIES} ${OPENCL_LIBRARIES})

README.md

@@ -136,7 +136,7 @@ Note that CLBlast's tuners are based on the CLTune auto-tuning library, which ha
 
 Compiling with `-DTUNERS=ON` will generate a number of tuners, each named `clblast_tuner_xxxxx`, in which `xxxxx` corresponds to a `.opencl` kernel file as found in `src/kernels`. These kernels corresponds to routines (e.g. `xgemm`) or to common pre-processing or post-processing kernels (`copy` and `transpose`). Running such a tuner will test a number of parameter-value combinations on your device and report which one gave the best performance. Running `make alltuners` runs all tuners for all precisions in one go. You can set the default device and platform for `alltuners` by setting the `DEFAULT_DEVICE` and `DEFAULT_PLATFORM` environmental variables before running CMake.
 
-The tuners output a JSON-file with the results. The best results need to be added to `include/internal/database/xxxxx.h` in the appropriate section. However, this can be done automatically based on the JSON-data using a Python script in `scripts/database/database.py`. If you want the found parameters to be included in future releases of CLBlast, please attach the JSON files to the corresponding issue on GitHub or [email the main author](http://www.cedricnugteren.nl).
+The tuners output a JSON-file with the results. The best results need to be added to `include/internal/database/xxxxx.hpp` in the appropriate section. However, this can be done automatically based on the JSON-data using a Python script in `scripts/database/database.py`. If you want the found parameters to be included in future releases of CLBlast, please attach the JSON files to the corresponding issue on GitHub or [email the main author](http://www.cedricnugteren.nl).
 
 In summary, tuning the entire library for your device can be done as follows (starting from the root of the CLBlast folder):
 

scripts/generator/generator.py

@@ -10,14 +10,14 @@
 # This script automatically generates the bodies of the following files, creating the full CLBlast
 # API interface and implementation (C, C++, and reference BLAS wrappers):
 #    clblast.h
-#    clblast.cc
+#    clblast.cpp
 #    clblast_c.h
-#    clblast_c.cc
+#    clblast_c.cpp
 #    wrapper_clblas.h
 #    wrapper_cblas.h
 # It also generates the main functions for the correctness and performance tests as found in
-#    test/correctness/routines/levelX/xYYYY.cc
-#    test/performance/routines/levelX/xYYYY.cc
+#    test/correctness/routines/levelX/xYYYY.cpp
+#    test/performance/routines/levelX/xYYYY.cpp
 # It also produces the API documentation found in doc/clblast.md
 #
 # ==================================================================================================
@@ -200,7 +200,7 @@ def clblast_h(routines):
 		result += routine.RoutineHeaderCPP(12, " = nullptr")+";\n"
 	return result
 
-# The C++ API implementation (.cc)
+# The C++ API implementation (.cpp)
 def clblast_cc(routines):
 	result = ""
 	for routine in routines:
@@ -237,7 +237,7 @@ def clblast_c_h(routines):
 			result += routine.RoutineHeaderC(flavour, 31, " PUBLIC_API")+";\n"
 	return result
 
-# The C API implementation (.cc)
+# The C API implementation (.cpp)
 def clblast_c_cc(routines):
 	result = ""
 	for routine in routines:
@@ -379,9 +379,9 @@ if len(sys.argv) != 2:
 path_clblast = sys.argv[1]
 files = [
   path_clblast+"/include/clblast.h",
-  path_clblast+"/src/clblast.cc",
+  path_clblast+"/src/clblast.cpp",
   path_clblast+"/include/clblast_c.h",
-  path_clblast+"/src/clblast_c.cc",
+  path_clblast+"/src/clblast_c.cpp",
   path_clblast+"/test/wrapper_clblas.hpp",
   path_clblast+"/test/wrapper_cblas.hpp",
 ]
@@ -433,7 +433,7 @@ for i in xrange(0,len(files)):
 for level in [1,2,3,4]:
 	for routine in routines[level-1]:
 		if routine.has_tests:
-			filename = path_clblast+"/test/correctness/routines/level"+levelnames[level-1]+"/x"+routine.name+".cc"
+			filename = path_clblast+"/test/correctness/routines/level"+levelnames[level-1]+"/x"+routine.name+".cpp"
 			with open(filename, "w") as f:
 				body = ""
 				body += "#include \"test/correctness/testblas.hpp\"\n"
@@ -459,7 +459,7 @@ for level in [1,2,3,4]:
 for level in [1,2,3,4]:
 	for routine in routines[level-1]:
 		if routine.has_tests:
-			filename = path_clblast+"/test/performance/routines/level"+levelnames[level-1]+"/x"+routine.name+".cc"
+			filename = path_clblast+"/test/performance/routines/level"+levelnames[level-1]+"/x"+routine.name+".cpp"
 			with open(filename, "w") as f:
 				body = ""
 				body += "#include \"test/performance/client.hpp\"\n"