Move cuda/runtime/shim to cuda/runtime for better usibility.

This diff moves the `cuda/runtime/shim` directory to `cuda/runtime` to make the utility functions sharable among all runtime infrastructure.

Differential Revision: [D84122729](https://our.internmc.facebook.com/intern/diff/D84122729/)

[ghstack-poisoned]

Author: Gasoonjia

backends/cuda/runtime/TARGETS

@@ -11,7 +11,7 @@ runtime.cxx_library(
     headers = [
         "shims/memory.h",
         "shims/tensor_attribute.h",
-        "shims/utils.h",
+        "utils.h",
     ],
     # @lint-ignore BUCKLINT: Avoid `link_whole=True` (https://fburl.com/avoid-link-whole)
     link_whole = True,

backends/cuda/runtime/shims/memory.cpp

@@ -10,7 +10,7 @@
 #include <executorch/backends/aoti/utils.h>
 #include <executorch/backends/cuda/runtime/shims/memory.h>
 #include <executorch/backends/cuda/runtime/shims/tensor_attribute.h>
-#include <executorch/backends/cuda/runtime/shims/utils.h>
+#include <executorch/backends/cuda/runtime/utils.h>
 #include <executorch/runtime/platform/log.h>
 #include <cstdint>
 #include <cstdlib> // For posix_memalign

backends/cuda/runtime/shims/tests/test_aoti_torch__reinterpret_tensor.cpp

@@ -10,7 +10,7 @@
 #include <executorch/backends/aoti/common_shims.h>
 #include <executorch/backends/cuda/runtime/shims/memory.h>
 #include <executorch/backends/cuda/runtime/shims/tensor_attribute.h>
-#include <executorch/backends/cuda/runtime/shims/utils.h>
+#include <executorch/backends/cuda/runtime/utils.h>
 #include <executorch/runtime/core/error.h>
 #include <executorch/runtime/platform/platform.h>
 #include <gtest/gtest.h>

backends/cuda/runtime/shims/tests/test_aoti_torch_copy_.cpp

@@ -10,7 +10,7 @@
 #include <executorch/backends/aoti/common_shims.h>
 #include <executorch/backends/cuda/runtime/shims/memory.h>
 #include <executorch/backends/cuda/runtime/shims/tensor_attribute.h>
-#include <executorch/backends/cuda/runtime/shims/utils.h>
+#include <executorch/backends/cuda/runtime/utils.h>
 #include <executorch/runtime/core/error.h>
 #include <executorch/runtime/platform/platform.h>
 #include <gtest/gtest.h>

backends/cuda/runtime/shims/tests/test_aoti_torch_create_tensor_from_blob_v2.cpp

@@ -10,7 +10,7 @@
 #include <executorch/backends/aoti/common_shims.h>
 #include <executorch/backends/cuda/runtime/shims/memory.h>
 #include <executorch/backends/cuda/runtime/shims/tensor_attribute.h>
-#include <executorch/backends/cuda/runtime/shims/utils.h>
+#include <executorch/backends/cuda/runtime/utils.h>
 #include <executorch/runtime/core/error.h>
 #include <executorch/runtime/platform/platform.h>
 #include <gtest/gtest.h>

backends/cuda/runtime/shims/tests/test_aoti_torch_delete_tensor_object.cpp

@@ -10,7 +10,7 @@
 #include <executorch/backends/aoti/common_shims.h>
 #include <executorch/backends/cuda/runtime/shims/memory.h>
 #include <executorch/backends/cuda/runtime/shims/tensor_attribute.h>
-#include <executorch/backends/cuda/runtime/shims/utils.h>
+#include <executorch/backends/cuda/runtime/utils.h>
 #include <executorch/runtime/core/error.h>
 #include <executorch/runtime/platform/platform.h>
 #include <gtest/gtest.h>

backends/cuda/runtime/shims/tests/test_aoti_torch_empty_strided.cpp

@@ -10,7 +10,7 @@
 #include <executorch/backends/aoti/common_shims.h>
 #include <executorch/backends/cuda/runtime/shims/memory.h>
 #include <executorch/backends/cuda/runtime/shims/tensor_attribute.h>
-#include <executorch/backends/cuda/runtime/shims/utils.h>
+#include <executorch/backends/cuda/runtime/utils.h>
 #include <executorch/runtime/core/error.h>
 #include <executorch/runtime/platform/platform.h>
 #include <gtest/gtest.h>