[STF] Move core stf headers outside of places/ (#7939)

* Remove unused exec_affinity.cuh include from place_partition.cuh

place_partition.cuh does not use exec_affinity; the include was a leftover.

Made-with: Cursor

* Add missing changes

* Revert "Add missing changes" (not intended for this branch)

This reverts commit 7fd0545.

* Move loop_dispatch.cuh to a more STF specific header

* Move places/inner_shape.cuh in internal/inner_shape.cuh

* clang-format

* add a missing header

Author: caugonnet

cudax/include/cuda/experimental/__stf/internal/context.cuh

@@ -23,12 +23,12 @@
 #include <cuda/experimental/__stf/allocators/pooled_allocator.cuh>
 #include <cuda/experimental/__stf/allocators/uncached_allocator.cuh>
 #include <cuda/experimental/__stf/graph/graph_ctx.cuh>
+#include <cuda/experimental/__stf/internal/inner_shape.cuh>
 #include <cuda/experimental/__stf/internal/reducer.cuh>
 #include <cuda/experimental/__stf/internal/scalar_interface.cuh>
 #include <cuda/experimental/__stf/internal/task_dep.cuh>
 #include <cuda/experimental/__stf/internal/void_interface.cuh>
 #include <cuda/experimental/__stf/places/exec/cuda_stream.cuh>
-#include <cuda/experimental/__stf/places/inner_shape.cuh>
 #include <cuda/experimental/__stf/stream/stream_ctx.cuh>
 
 #include <map>

…xperimental/__stf/places/inner_shape.cuh …erimental/__stf/internal/inner_shape.cuhcudax/include/cuda/experimental/__stf/places/inner_shape.cuh renamed to cudax/include/cuda/experimental/__stf/internal/inner_shape.cuh cudax/include/cuda/experimental/__stf/places/inner_shape.cuh renamed to cudax/include/cuda/experimental/__stf/internal/inner_shape.cuh

@@ -26,7 +26,6 @@
 #endif // no system header
 
 #include <cuda/experimental/__stf/internal/async_resources_handle.cuh>
-#include <cuda/experimental/__stf/internal/exec_affinity.cuh>
 #include <cuda/experimental/__stf/places/exec/cuda_stream.cuh>
 #include <cuda/experimental/__stf/places/exec/green_context.cuh>
 #include <cuda/experimental/__stf/places/places.cuh>

…erimental/__stf/places/loop_dispatch.cuh …imental/__stf/internal/loop_dispatch.cuhcudax/include/cuda/experimental/__stf/places/loop_dispatch.cuh renamed to cudax/include/cuda/experimental/__stf/internal/loop_dispatch.cuh cudax/include/cuda/experimental/__stf/places/loop_dispatch.cuh renamed to cudax/include/cuda/experimental/__stf/internal/loop_dispatch.cuh

@@ -23,12 +23,12 @@
 #include <cuda/experimental/__stf/graph/graph_ctx.cuh>
 // #include <cuda/experimental/__stf/internal/algorithm.cuh>
 #include <cuda/experimental/__stf/internal/context.cuh>
+#include <cuda/experimental/__stf/internal/inner_shape.cuh>
 #include <cuda/experimental/__stf/internal/reducer.cuh>
 #include <cuda/experimental/__stf/internal/scalar_interface.cuh>
 #include <cuda/experimental/__stf/internal/task_dep.cuh>
 #include <cuda/experimental/__stf/internal/void_interface.cuh>
 #include <cuda/experimental/__stf/places/exec/cuda_stream.cuh>
 #include <cuda/experimental/__stf/places/exec/green_context.cuh>
-#include <cuda/experimental/__stf/places/inner_shape.cuh>
 #include <cuda/experimental/__stf/stream/stream_ctx.cuh>
 #include <cuda/experimental/__stf/utility/run_once.cuh>

cudax/include/cuda/experimental/__stf/places/place_partition.cuh

@@ -193,7 +193,7 @@ set(
   cuda/experimental/__stf/internal/slice.cuh
   cuda/experimental/__stf/internal/thread_hierarchy.cuh
   cuda/experimental/__stf/places/cyclic_shape.cuh
-  cuda/experimental/__stf/places/inner_shape.cuh
+  cuda/experimental/__stf/internal/inner_shape.cuh
   cuda/experimental/__stf/places/places.cuh
   cuda/experimental/__stf/places/tiled_partition.cuh
   cuda/experimental/__stf/stream/stream_ctx.cuh

cudax/include/cuda/experimental/stf.cuh

@@ -8,7 +8,7 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include <cuda/experimental/__stf/places/loop_dispatch.cuh>
+#include <cuda/experimental/__stf/internal/loop_dispatch.cuh>
 #include <cuda/experimental/stf.cuh>
 
 using namespace cuda::experimental::stf;

cudax/test/stf/CMakeLists.txt

@@ -10,7 +10,7 @@
 
 #include <cuda/std/cmath>
 
-#include <cuda/experimental/__stf/places/loop_dispatch.cuh>
+#include <cuda/experimental/__stf/internal/loop_dispatch.cuh>
 #include <cuda/experimental/stf.cuh>
 
 using namespace cuda::experimental::stf;