[FRONTEND] Added interpreter mode (#1573)

Simple mechanism to run Triton kernels on PyTorch for debugging purpose
(upstream from Kernl).

Todo:
- random grid iteration
- support of atomic ops
- more unit tests
- cover new APIs?

python/setup.py

@@ -249,6 +249,7 @@ setup(
         "triton/_C",
         "triton/common",
         "triton/compiler",
+        "triton/debugger",
         "triton/language",
         "triton/language/extra",
         "triton/ops",