[codemod] c10:optional -> std::optional (pytorch#126135)

Generated by running the following from PyTorch root:
```
find . -regex ".*\.\(cpp\|h\|cu\|hpp\|cc\|cxx\)$" | grep -v "build/" | xargs -n 50 -P 4 perl -pi -e 's/c10::optional/std::optional/'
```

`c10::optional` is just an alias for `std::optional`. This removes usages of that alias in preparation for eliminating it entirely.

Pull Request resolved: pytorch#126135
Approved by: https://github.com/Skylion007, https://github.com/malfet, https://github.com/albanD, https://github.com/aaronenyeshi

aten/src/ATen/CPUGeneratorImpl.cpp

@@ -81,8 +81,8 @@ inline uint64_t make64BitsFrom32Bits(uint32_t hi, uint32_t lo) {
 CPUGeneratorImpl::CPUGeneratorImpl(uint64_t seed_in)
   : c10::GeneratorImpl{Device(DeviceType::CPU), DispatchKeySet(c10::DispatchKey::CPU)},
     engine_{seed_in},
-    next_float_normal_sample_{c10::optional<float>()},
-    next_double_normal_sample_{c10::optional<double>()} { }
+    next_float_normal_sample_{std::optional<float>()},
+    next_double_normal_sample_{std::optional<double>()} { }
 
 /**
  * Manually seeds the engine with the seed input
@@ -151,16 +151,16 @@ void CPUGeneratorImpl::set_state(const c10::TensorImpl& new_state) {
   detail::check_rng_state(new_state);
 
   at::mt19937 engine;
-  auto float_normal_sample = c10::optional<float>();
-  auto double_normal_sample = c10::optional<double>();
+  auto float_normal_sample = std::optional<float>();
+  auto double_normal_sample = std::optional<double>();
 
   // Construct the state of at::CPUGeneratorImpl based on input byte tensor size.
   CPUGeneratorImplStateLegacy* legacy_pod{nullptr};
   auto new_state_size = new_state.numel();
   if (new_state_size == size_legacy) {
     legacy_pod = (CPUGeneratorImplStateLegacy*)new_state.data();
     // Note that in CPUGeneratorImplStateLegacy, we didn't have float version
-    // of normal sample and hence we leave the c10::optional<float> as is
+    // of normal sample and hence we leave the std::optional<float> as is
 
     // Update next_double_normal_sample.
     // Note that CPUGeneratorImplStateLegacy stores two uniform values (normal_x, normal_y)
@@ -171,22 +171,22 @@ void CPUGeneratorImpl::set_state(const c10::TensorImpl& new_state) {
       auto r = legacy_pod->normal_rho;
       auto theta = 2.0 * c10::pi<double> * legacy_pod->normal_x;
       // we return the sin version of the normal sample when in caching mode
-      double_normal_sample = c10::optional<double>(r * ::sin(theta));
+      double_normal_sample = std::optional<double>(r * ::sin(theta));
     }
   } else if (new_state_size == size_current) {
     auto rng_state = (CPUGeneratorImplState*)new_state.data();
     legacy_pod = &rng_state->legacy_pod;
     // update next_float_normal_sample
     if (rng_state->is_next_float_normal_sample_valid) {
-      float_normal_sample = c10::optional<float>(rng_state->next_float_normal_sample);
+      float_normal_sample = std::optional<float>(rng_state->next_float_normal_sample);
     }
 
     // Update next_double_normal_sample.
     // Note that in getRNGState, we now return the actual normal sample in normal_y
     // and if it's valid in normal_is_valid. The redundant normal_x and normal_rho
     // are squashed to 0.0.
     if (legacy_pod->normal_is_valid) {
-      double_normal_sample = c10::optional<double>(legacy_pod->normal_y);
+      double_normal_sample = std::optional<double>(legacy_pod->normal_y);
     }
   } else {
     AT_ERROR("Expected either a CPUGeneratorImplStateLegacy of size ", size_legacy,
@@ -283,14 +283,14 @@ uint64_t CPUGeneratorImpl::random64() {
 /**
  * Get the cached normal random in float
  */
-c10::optional<float> CPUGeneratorImpl::next_float_normal_sample() {
+std::optional<float> CPUGeneratorImpl::next_float_normal_sample() {
   return next_float_normal_sample_;
 }
 
 /**
  * Get the cached normal random in double
  */
-c10::optional<double> CPUGeneratorImpl::next_double_normal_sample() {
+std::optional<double> CPUGeneratorImpl::next_double_normal_sample() {
   return next_double_normal_sample_;
 }
 
@@ -299,7 +299,7 @@ c10::optional<double> CPUGeneratorImpl::next_double_normal_sample() {
  *
  * See Note [Acquire lock when using random generators]
  */
-void CPUGeneratorImpl::set_next_float_normal_sample(c10::optional<float> randn) {
+void CPUGeneratorImpl::set_next_float_normal_sample(std::optional<float> randn) {
   next_float_normal_sample_ = randn;
 }
 
@@ -308,7 +308,7 @@ void CPUGeneratorImpl::set_next_float_normal_sample(c10::optional<float> randn)
  *
  * See Note [Acquire lock when using random generators]
  */
-void CPUGeneratorImpl::set_next_double_normal_sample(c10::optional<double> randn) {
+void CPUGeneratorImpl::set_next_double_normal_sample(std::optional<double> randn) {
   next_double_normal_sample_ = randn;
 }
 

aten/src/ATen/CPUGeneratorImpl.h

@@ -24,18 +24,18 @@ struct TORCH_API CPUGeneratorImpl : public c10::GeneratorImpl {
   static c10::DeviceType device_type();
   uint32_t random();
   uint64_t random64();
-  c10::optional<float> next_float_normal_sample();
-  c10::optional<double> next_double_normal_sample();
-  void set_next_float_normal_sample(c10::optional<float> randn);
-  void set_next_double_normal_sample(c10::optional<double> randn);
+  std::optional<float> next_float_normal_sample();
+  std::optional<double> next_double_normal_sample();
+  void set_next_float_normal_sample(std::optional<float> randn);
+  void set_next_double_normal_sample(std::optional<double> randn);
   at::mt19937 engine();
   void set_engine(at::mt19937 engine);
 
  private:
   CPUGeneratorImpl* clone_impl() const override;
   at::mt19937 engine_;
-  c10::optional<float> next_float_normal_sample_;
-  c10::optional<double> next_double_normal_sample_;
+  std::optional<float> next_float_normal_sample_;
+  std::optional<double> next_double_normal_sample_;
 };
 
 namespace detail {

aten/src/ATen/Context.h

@@ -59,7 +59,7 @@ class TORCH_API Context {
     }
   }
   const AcceleratorHooksInterface& getAcceleratorHooksInterface(
-      c10::optional<c10::DeviceType> opt_device_type = c10::nullopt) {
+      std::optional<c10::DeviceType> opt_device_type = c10::nullopt) {
     c10::DeviceType device_type = opt_device_type.has_value()
         ? opt_device_type.value()
         : at::getAccelerator(true).value();
@@ -395,7 +395,7 @@ class TORCH_API Context {
   bool release_original_weights = false;
 #endif
   bool display_vmap_fallback_warnings_ = false;
-  c10::optional<at::QEngine> quantized_engine = c10::nullopt;
+  std::optional<at::QEngine> quantized_engine = c10::nullopt;
   bool enable_sparse_tensor_invariant_checks = false;
   bool allow_fp16_reduction_cpu = false;
 

aten/src/ATen/DeviceGuard.h

@@ -15,22 +15,22 @@ namespace at {
 //    OptionalDeviceGuard guard(device_of(tensor));
 
 /// Return the Device of a Tensor, if the Tensor is defined.
-inline c10::optional<Device> device_of(const Tensor& t) {
+inline std::optional<Device> device_of(const Tensor& t) {
   if (t.defined()) {
     return c10::make_optional(t.device());
   } else {
     return c10::nullopt;
   }
 }
 
-inline c10::optional<Device> device_of(const c10::optional<Tensor>& t) {
+inline std::optional<Device> device_of(const c10::optional<Tensor>& t) {
   return t.has_value() ? device_of(t.value()) : c10::nullopt;
 }
 
 /// Return the Device of a TensorList, if the list is non-empty and
 /// the first Tensor is defined.  (This function implicitly assumes
 /// that all tensors in the list have the same device.)
-inline c10::optional<Device> device_of(ITensorListRef t) {
+inline std::optional<Device> device_of(ITensorListRef t) {
   if (!t.empty()) {
     return device_of(t.front());
   } else {

aten/src/ATen/EmptyTensor.cpp

@@ -163,7 +163,7 @@ TensorBase _empty_generic(
     c10::Allocator* allocator,
     c10::DispatchKeySet ks,
     ScalarType scalar_type,
-    c10::optional<c10::MemoryFormat> memory_format_opt) {
+    std::optional<c10::MemoryFormat> memory_format_opt) {
   at::detail::check_size_nonnegative(size);
   at::detail::raise_warning_for_complex_half(scalar_type);
   caffe2::TypeMeta dtype = scalarTypeToTypeMeta(scalar_type);
@@ -197,7 +197,7 @@ TensorBase empty_generic(
     c10::Allocator* allocator,
     c10::DispatchKeySet ks,
     ScalarType scalar_type,
-    c10::optional<c10::MemoryFormat> memory_format_opt) {
+    std::optional<c10::MemoryFormat> memory_format_opt) {
   return _empty_generic(size, allocator, ks, scalar_type, memory_format_opt);
 }
 
@@ -206,7 +206,7 @@ TensorBase empty_generic_symint(
     c10::Allocator* allocator,
     c10::DispatchKeySet ks,
     ScalarType scalar_type,
-    c10::optional<c10::MemoryFormat> memory_format_opt) {
+    std::optional<c10::MemoryFormat> memory_format_opt) {
   return _empty_generic(size, allocator, ks, scalar_type, memory_format_opt);
 }
 
@@ -252,19 +252,19 @@ TensorBase empty_strided_symint_generic(
 }
 
 TensorBase empty_cpu(IntArrayRef size, ScalarType dtype, bool pin_memory,
-                     c10::optional<c10::MemoryFormat> memory_format_opt) {
+                     std::optional<c10::MemoryFormat> memory_format_opt) {
   auto allocator = GetCPUAllocatorMaybePinned(pin_memory);
   constexpr c10::DispatchKeySet cpu_ks(c10::DispatchKey::CPU);
   return empty_generic(size, allocator, cpu_ks, dtype, memory_format_opt);
 }
 
 TensorBase empty_cpu(
     IntArrayRef size,
-    c10::optional<ScalarType> dtype_opt,
-    c10::optional<Layout> layout_opt,
-    c10::optional<Device> device_opt,
-    c10::optional<bool> pin_memory_opt,
-    c10::optional<c10::MemoryFormat> memory_format_opt) {
+    std::optional<ScalarType> dtype_opt,
+    std::optional<Layout> layout_opt,
+    std::optional<Device> device_opt,
+    std::optional<bool> pin_memory_opt,
+    std::optional<c10::MemoryFormat> memory_format_opt) {
   TORCH_INTERNAL_ASSERT_DEBUG_ONLY(device_or_default(device_opt).type() == DeviceType::CPU);
   TORCH_INTERNAL_ASSERT_DEBUG_ONLY(layout_or_default(layout_opt) == Layout::Strided);
 
@@ -295,10 +295,10 @@ TensorBase empty_strided_cpu(IntArrayRef size, IntArrayRef stride,
 TensorBase empty_strided_cpu(
     IntArrayRef size,
     IntArrayRef stride,
-    c10::optional<ScalarType> dtype_opt,
-    c10::optional<Layout> layout_opt,
-    c10::optional<Device> device_opt,
-    c10::optional<bool> pin_memory_opt) {
+    std::optional<ScalarType> dtype_opt,
+    std::optional<Layout> layout_opt,
+    std::optional<Device> device_opt,
+    std::optional<bool> pin_memory_opt) {
   TORCH_INTERNAL_ASSERT_DEBUG_ONLY(device_or_default(device_opt).type() == DeviceType::CPU);
   TORCH_INTERNAL_ASSERT_DEBUG_ONLY(layout_or_default(layout_opt) == Layout::Strided);
 
@@ -342,7 +342,7 @@ static MetaAllocator g_meta_alloc;
 REGISTER_ALLOCATOR(kMeta, &g_meta_alloc);
 
 TensorBase empty_meta(IntArrayRef size, ScalarType dtype,
-                     c10::optional<c10::MemoryFormat> memory_format_opt) {
+                     std::optional<c10::MemoryFormat> memory_format_opt) {
   auto *allocator = GetAllocator(kMeta);
   constexpr c10::DispatchKeySet meta_dks(c10::DispatchKey::Meta);
   return at::detail::empty_generic(
@@ -351,11 +351,11 @@ TensorBase empty_meta(IntArrayRef size, ScalarType dtype,
 
 TensorBase empty_meta(
   IntArrayRef size,
-  c10::optional<ScalarType> dtype_opt,
-  c10::optional<Layout> layout_opt,
-  c10::optional<Device> device_opt,
-  c10::optional<bool> pin_memory_opt,
-  c10::optional<c10::MemoryFormat> memory_format_opt
+  std::optional<ScalarType> dtype_opt,
+  std::optional<Layout> layout_opt,
+  std::optional<Device> device_opt,
+  std::optional<bool> pin_memory_opt,
+  std::optional<c10::MemoryFormat> memory_format_opt
 ) {
   TORCH_INTERNAL_ASSERT_DEBUG_ONLY(device_or_default(device_opt).type() == DeviceType::Meta);
   // NB: because there is no SparseMeta (yet), non-strided layout is
@@ -371,11 +371,11 @@ TensorBase empty_meta(
 
 TensorBase empty_symint_meta(
   SymIntArrayRef size,
-  c10::optional<ScalarType> dtype_opt,
-  c10::optional<Layout> layout_opt,
-  c10::optional<Device> device_opt,
-  c10::optional<bool> pin_memory_opt,
-  c10::optional<c10::MemoryFormat> memory_format_opt
+  std::optional<ScalarType> dtype_opt,
+  std::optional<Layout> layout_opt,
+  std::optional<Device> device_opt,
+  std::optional<bool> pin_memory_opt,
+  std::optional<c10::MemoryFormat> memory_format_opt
 ) {
   auto *allocator = GetAllocator(kMeta);
   constexpr c10::DispatchKeySet ks(c10::DispatchKey::Meta);
@@ -405,10 +405,10 @@ TensorBase empty_strided_meta(IntArrayRef size, IntArrayRef stride,
 TensorBase empty_strided_meta(
     IntArrayRef size,
     IntArrayRef stride,
-    c10::optional<ScalarType> dtype_opt,
-    c10::optional<Layout> layout_opt,
-    c10::optional<Device> device_opt,
-    c10::optional<bool> pin_memory_opt) {
+    std::optional<ScalarType> dtype_opt,
+    std::optional<Layout> layout_opt,
+    std::optional<Device> device_opt,
+    std::optional<bool> pin_memory_opt) {
   TORCH_INTERNAL_ASSERT_DEBUG_ONLY(device_or_default(device_opt).type() == DeviceType::Meta);
   TORCH_INTERNAL_ASSERT_DEBUG_ONLY(layout_or_default(layout_opt) == Layout::Strided);
 
@@ -440,10 +440,10 @@ TensorBase empty_strided_symint_meta(SymIntArrayRef size, SymIntArrayRef stride,
 TensorBase empty_strided_symint_meta(
     SymIntArrayRef size,
     SymIntArrayRef stride,
-    c10::optional<ScalarType> dtype_opt,
-    c10::optional<Layout> layout_opt,
-    c10::optional<Device> device_opt,
-    c10::optional<bool> pin_memory_opt) {
+    std::optional<ScalarType> dtype_opt,
+    std::optional<Layout> layout_opt,
+    std::optional<Device> device_opt,
+    std::optional<bool> pin_memory_opt) {
   TORCH_INTERNAL_ASSERT_DEBUG_ONLY(device_or_default(device_opt).type() == DeviceType::Meta);
   TORCH_INTERNAL_ASSERT_DEBUG_ONLY(layout_or_default(layout_opt) == Layout::Strided);