Distributed Reshape Implementation (microsoft#18068)

This DistributedReshape aims at supporting all sharding patterns
encountered in llama 2. All patterns found are tested in
`TestDistributedReshape` in `onnxruntime_test_distributed.py`. This PR
implements algorithms to compute the categories below.
- All inputs and outputs are replica, so it's computed like a normal
Reshape.
- Two-axis fusion (if any of the inputs and outputs are sharded). This
category convers, e.g., `[batch, seq, hidden] -> [batch x seq, hidden]`.
- Two-axis decomposition (if any of the inputs and outputs are sharded).
This category convers, e.g., `[batch x seq, hidden] -> [batch, seq,
hidden]`.

Review guideline:
- Ignore the changes in sharding_spec.h and sharding_spec.cc since they
come from another PR microsoft#18025.
- First, read onnxruntime_test_distributed.py to get familiar with the
input/output of DistributedReshape.
- Second, check the new APIs in reshape.h/reshape.cc to expose CUDA
Reshape kernel to DistributedReshape.
- For DistributedReshape, check its `ComputeInternal` for the 3
categories mentioned above.

cmake/onnxruntime_providers_cuda.cmake

@@ -38,6 +38,7 @@
         "${ONNXRUNTIME_ROOT}/contrib_ops/cuda/collective/sharding.cc"
         "${ONNXRUNTIME_ROOT}/contrib_ops/cuda/collective/distributed_matmul.cc"
         "${ONNXRUNTIME_ROOT}/contrib_ops/cuda/collective/distributed_slice.cc"
+        "${ONNXRUNTIME_ROOT}/contrib_ops/cuda/collective/distributed_reshape.cc"
       )
     endif()
     # add using ONNXRUNTIME_ROOT so they show up under the 'contrib_ops' folder in Visual Studio
@@ -246,4 +247,4 @@
   install(TARGETS onnxruntime_providers_cuda
           ARCHIVE  DESTINATION ${CMAKE_INSTALL_LIBDIR}
           LIBRARY  DESTINATION ${CMAKE_INSTALL_LIBDIR}
-          RUNTIME  DESTINATION ${CMAKE_INSTALL_BINDIR})
+          RUNTIME  DESTINATION ${CMAKE_INSTALL_BINDIR})

cmake/onnxruntime_rocm_hipify.cmake

@@ -103,6 +103,8 @@ if (NOT onnxruntime_USE_NCCL)
   list(APPEND contrib_ops_excluded_files "collective/sharding.cc")
   list(APPEND contrib_ops_excluded_files "collective/sharding_spec.cc")
   list(APPEND contrib_ops_excluded_files "collective/distributed_matmul.cc")
+  list(APPEND contrib_ops_excluded_files "collective/distributed_slice.cc")
+  list(APPEND contrib_ops_excluded_files "collective/distributed_reshape.cc")
 endif()
 
 set(provider_excluded_files