Move cuda/runtime/shim/utils to cuda/runtime for better usibility. (#14913)

This PR was created by the merge bot to help merge the original PR into
the main branch.
ghstack PR number: #14900 by
@Gasoonjia
^ Please use this as the source of truth for the PR details, comments,
and reviews
ghstack PR base:
https://github.com/pytorch/executorch/tree/gh/gasoonjia/45/base
ghstack PR head:
https://github.com/pytorch/executorch/tree/gh/gasoonjia/45/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/main
Merge bot PR head:
https://github.com/pytorch/executorch/tree/gh/gasoonjia/45/orig
Differential Revision:
[D84169267](https://our.internmc.facebook.com/intern/diff/D84169267/)
@diff-train-skip-merge

Co-authored-by: gasoonjia <[email protected]>

Author: pytorchbot

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>