[PYTHON][TESTS][DOC] Various improvement of the API and code quality:

* Simplified `triton.kernel` API to achieve lower latency:
  > .data_ptr() must now be passed as kernel argument. No more implicit
conversion from torch.tensor
  > compilation options are now constant attributes, i.e., opt.d('VAR')
becomes opt.VAR
  > torch.device must now be passed explicitly to triton.kernel (no
longer inferred from torch.tensor arguments)
* C++ tests moved to `python/tests/`
* C++ tutorial created in `tutorials/`
* Python tutorial created in python/tutorials/
* Version changed to 1.0alpha
* No longer copying C++ headers into the Python package
* added python/triton/ops/ package for pre-written Triton ops

CMakeLists.txt

@@ -4,7 +4,7 @@ include(CTest)
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake")
 
 # Options
-option(BUILD_TESTS "Build C++ Triton tests" ON)
+option(BUILD_TUTORIALS "Build C++ Triton tutorials" ON)
 option(BUILD_PYTHON_MODULE "Build Python Triton bindings" OFF)
 
 # LLVM
@@ -25,16 +25,17 @@ set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -D__STDC_FORMAT_MACROS -fvisibility=defa
 
 # Tests
 if(BUILD_TESTS)
-  message(STATUS "Adding C++ tests")
-  add_subdirectory(tests)
+  message(STATUS "Adding C++ tutorials")
+  add_subdirectory(tutorials)
 endif() 
 
 # Python module
 if(BUILD_PYTHON_MODULE)
     message(STATUS "Adding Python module")
     # PyBind11 wrapper source file
-    set(PYTHON_SRC bindings.cc launch.cc)
-    set_source_files_properties(launch.cc PROPERTIES COMPILE_FLAGS "-std=c++14 -D_GLIBCXX_USE_CXX11_ABI=${TORCH_CXX11_ABI}")
+    set(TORCH_SRC torch/launch.cc torch/superblock.cc)
+    set(PYTHON_SRC bindings.cc ${TORCH_SRC})
+    set_source_files_properties(${TORCH_SRC} PROPERTIES COMPILE_FLAGS "-std=c++14 -D_GLIBCXX_USE_CXX11_ABI=${TORCH_CXX11_ABI}")
     include_directories("." ${PYTHON_INCLUDE_DIRS})
     link_directories(${PYTHON_LINK_DIRS})
 endif()