[1/N] Remove unused header inclusion (#165763)

This PR removes unused header inclusion in C++ files.

Pull Request resolved: https://github.com/pytorch/pytorch/pull/165763
Approved by: https://github.com/Skylion007

c10/core/AllocatorConfig.cpp

@@ -1,5 +1,4 @@
 #include <c10/core/AllocatorConfig.h>
-#include <c10/core/DeviceType.h>
 #include <c10/util/env.h>
 
 namespace c10::CachingAllocator {

c10/core/SymInt.cpp

@@ -4,7 +4,6 @@
 #include <c10/core/SymNodeImpl.h>
 #include <c10/util/intrusive_ptr.h>
 #include <c10/util/safe_numerics.h>
-#include <functional>
 
 namespace c10 {
 

c10/core/TensorImpl.cpp

@@ -9,7 +9,6 @@
 #include <c10/core/impl/TorchDispatchModeTLS.h>
 #include <c10/util/Logging.h>
 #include <c10/util/accumulate.h>
-#include <c10/util/irange.h>
 #include <optional>
 
 #include <utility>

c10/core/TensorOptions.cpp

@@ -1,9 +1,5 @@
 #include <c10/core/TensorOptions.h>
 
-#include <c10/core/Device.h>
-#include <c10/core/Layout.h>
-#include <c10/util/Optional.h>
-
 #include <iostream>
 
 namespace c10 {

c10/core/impl/COW.cpp

@@ -2,7 +2,6 @@
 
 #include <c10/core/Allocator.h>
 #include <c10/core/StorageImpl.h>
-#include <c10/core/alignment.h>
 #include <c10/core/impl/COWDeleter.h>
 #include <c10/util/Exception.h>
 #include <c10/util/ParallelGuard.h>

c10/core/impl/TorchDispatchModeTLS.cpp

@@ -1,5 +1,4 @@
 #include <c10/core/DispatchKey.h>
-#include <c10/core/SafePyObject.h>
 #include <c10/core/impl/LocalDispatchKeySet.h>
 #include <c10/core/impl/TorchDispatchModeTLS.h>
 #include <c10/util/irange.h>

c10/cuda/CUDADeviceAssertionHost.cpp

@@ -1,8 +1,6 @@
 #include <c10/cuda/CUDADeviceAssertionHost.h>
 #include <c10/cuda/CUDAException.h>
 #include <c10/cuda/CUDAFunctions.h>
-#include <c10/util/Backtrace.h>
-#include <c10/util/Exception.h>
 #include <c10/util/env.h>
 #include <c10/util/irange.h>
 #include <cuda_runtime.h>

c10/cuda/CUDAMallocAsyncAllocator.cpp

@@ -4,7 +4,6 @@
 #include <c10/cuda/CUDAGuard.h>
 #include <c10/util/UniqueVoidPtr.h>
 #include <c10/util/flat_hash_map.h>
-#include <c10/util/irange.h>
 
 #include <unordered_set>
 #include <vector>

c10/cuda/CUDAMiscFunctions.cpp

@@ -1,7 +1,6 @@
 #include <c10/cuda/CUDAMiscFunctions.h>
 #include <c10/util/env.h>
 #include <cuda_runtime.h>
-#include <cstring>
 #include <string>
 
 namespace c10::cuda {

c10/cuda/driver_api.cpp

@@ -1,7 +1,6 @@
 #if !defined(USE_ROCM) && defined(PYTORCH_C10_DRIVER_API_SUPPORTED)
 #include <c10/cuda/CUDAException.h>
 #include <c10/cuda/driver_api.h>
-#include <c10/util/CallOnce.h>
 #include <c10/util/Exception.h>
 #include <c10/util/Logging.h>
 #include <cuda_runtime.h>

c10/util/ApproximateClock.cpp

@@ -1,7 +1,6 @@
 #include <c10/util/ApproximateClock.h>
-#include <c10/util/ArrayRef.h>
+#include <c10/util/Exception.h>
 #include <c10/util/irange.h>
-#include <fmt/format.h>
 
 namespace c10 {
 

c10/util/complex_math.cpp

@@ -1,7 +1,5 @@
 #include <c10/util/complex.h>
 
-#include <cmath>
-
 // Note [ Complex Square root in libc++]
 // ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 // In libc++ complex square root is computed using polar form

c10/util/signal_handler.cpp

@@ -11,7 +11,6 @@
 #include <unistd.h>
 
 #include <atomic>
-#include <chrono>
 #include <condition_variable>
 #include <cstdint>
 #include <cstdio>

torch/csrc/distributed/c10d/control_plane/WorkerServer.cpp

@@ -5,7 +5,6 @@
 #include <c10/util/Exception.h>
 #include <c10/util/FileSystem.h>
 #include <c10/util/thread_name.h>
-#include <caffe2/utils/threadpool/WorkersPool.h>
 #include <torch/csrc/distributed/c10d/control_plane/WorkerServer.hpp>
 #include <torch/csrc/distributed/c10d/logging.h>
 

torch/csrc/profiler/util.cpp

@@ -1,6 +1,5 @@
 #include <torch/csrc/autograd/function.h>
 #include <torch/csrc/profiler/collection.h>
-#include <torch/csrc/profiler/kineto_shim.h>
 #include <torch/csrc/profiler/util.h>
 
 #include <c10/util/ArrayRef.h>