@@ -160,7 +160,7 @@ Next, we apply a number of lowering passes to ``stmt``. These passes are impleme
...
@@ -160,7 +160,7 @@ Next, we apply a number of lowering passes to ``stmt``. These passes are impleme
After lowering is done, ``build()`` function generates target machine code from the lowered function. This code can contain SSE or AVX instructions if you target x86, or PTX instructions for CUDA target. In addition to target specific machine code, TVM also generates host side code that is responsible for memory management, kernel launch etc.
After lowering is done, ``build()`` function generates target machine code from the lowered function. This code can contain SSE or AVX instructions if you target x86, or PTX instructions for CUDA target. In addition to target specific machine code, TVM also generates host side code that is responsible for memory management, kernel launch etc.
Code generation is done by ``build_module()`` function, defined in ``python/tvm/codege.py``. On the C++ side, code generation is implemented in ``src/codegen`` subdirectory. ``build_module()`` Python function will reach ``Build()`` function below in ``src/codegen/codegen.cc``:
Code generation is done by ``build_module()`` function, defined in ``python/tvm/codegen.py``. On the C++ side, code generation is implemented in ``src/codegen`` subdirectory. ``build_module()`` Python function will reach ``Build()`` function below in ``src/codegen/codegen.cc``: