FM / native

/usr/local/lib64/python3.6/site-packages/torch/include/ATen/native/

/usr/local/lib64/python3.6/site-packages/torch/include/ATen/native

Name	Size	Mode	Actions
cpu/	-	0755	rm
cuda/	-	0755	rm
quantized/	-	0755	rm
Activation.h	3069	0644	edit dl rm
AdaptivePooling.h	1165	0644	edit dl rm
BatchLinearAlgebra.h	8246	0644	edit dl rm
batch_norm.h	1285	0644	edit dl rm
BinaryOps.h	4916	0644	edit dl rm
BucketizationUtils.h	4248	0644	edit dl rm
ComplexHelper.h	3797	0644	edit dl rm
CompositeRandomAccessor.h	888	0644	edit dl rm
CompositeRandomAccessorCommon.h	6713	0644	edit dl rm
ConvUtils.h	5350	0644	edit dl rm
Copy.h	356	0644	edit dl rm
CPUBlas.h	4199	0644	edit dl rm
CPUFallback.h	2404	0644	edit dl rm
Cross.h	262	0644	edit dl rm
DilatedConvolutionUtils.h	6416	0644	edit dl rm
DispatchStub.h	7672	0644	edit dl rm
Distance.h	732	0644	edit dl rm
Distributions.h	21654	0644	edit dl rm
DistributionTemplates.h	18623	0644	edit dl rm
EmbeddingBag.h	1320	0644	edit dl rm
Fill.h	384	0644	edit dl rm
ForeachUtils.h	5962	0644	edit dl rm
FunctionOfAMatrixUtils.h	436	0644	edit dl rm
GridSampler.h	10525	0644	edit dl rm
group_norm.h	896	0644	edit dl rm
Histogram.h	492	0644	edit dl rm
im2col.h	2838	0644	edit dl rm
im2col_shape_check.h	6181	0644	edit dl rm
IndexingUtils.h	5373	0644	edit dl rm
layer_norm.h	2892	0644	edit dl rm
Lerp.h	553	0644	edit dl rm
LinearAlgebra.h	603	0644	edit dl rm
LinearAlgebraUtils.h	25236	0644	edit dl rm
LossMulti.h	2197	0644	edit dl rm
Math.h	91356	0644	edit dl rm
MathBitFallThroughLists.h	4086	0644	edit dl rm
MathBitsFallback.h	7326	0644	edit dl rm
MaxPooling.h	1234	0644	edit dl rm
Normalization.h	302	0644	edit dl rm
PointwiseOps.h	749	0644	edit dl rm
Pool.h	10922	0644	edit dl rm
Pow.h	1694	0644	edit dl rm
ReduceAllOps.h	378	0644	edit dl rm
ReduceOps.h	1745	0644	edit dl rm
ReduceOpsUtils.h	12245	0644	edit dl rm
Repeat.h	1286	0644	edit dl rm
Resize.h	6501	0644	edit dl rm
ResizeCommon.h	1321	0644	edit dl rm
RNN.h	2467	0644	edit dl rm
ScatterGatherChecks.h	3641	0644	edit dl rm
SegmentReduce.h	685	0644	edit dl rm
SharedReduceOps.h	15785	0644	edit dl rm
SobolEngineOpsUtils.h	1723	0644	edit dl rm
Sorting.h	536	0644	edit dl rm
SortingUtils.h	5722	0644	edit dl rm
SpectralOpsUtils.h	3146	0644	edit dl rm
StridedRandomAccessor.h	6847	0644	edit dl rm
TensorAdvancedIndexing.h	3072	0644	edit dl rm
TensorCompare.h	1333	0644	edit dl rm
TensorDimApply.h	1832	0644	edit dl rm
TensorFactories.h	3382	0644	edit dl rm
TensorIterator.h	46	0644	edit dl rm
TensorIteratorDynamicCasting.h	2025	0644	edit dl rm
TensorShape.h	1049	0644	edit dl rm
TensorTransformations.h	938	0644	edit dl rm
TriangularOpsUtils.h	2000	0644	edit dl rm
TypeProperties.h	496	0644	edit dl rm
UnaryOps.h	4464	0644	edit dl rm
Unfold2d.h	551	0644	edit dl rm
Unfold3d.h	852	0644	edit dl rm
UnfoldBackward.h	5398	0644	edit dl rm
UpSample.h	13599	0644	edit dl rm
vol2col.h	3642	0644	edit dl rm

Edit: /usr/local/lib64/python3.6/site-packages/torch/include/ATen/native/ForeachUtils.h (5962B)

#pragma once

#include <ATen/ATen.h>
#include <c10/util/irange.h>

namespace at {
namespace native {
namespace {
// Check if tensor list has either a boolean tensor or a integer tensor
bool has_integral_tensor(TensorList tensors, const bool includeBool) {
  return std::any_of(tensors.begin(), tensors.end(),
    [&includeBool](const auto & t) { return at::isIntegralType(t.scalar_type(), includeBool); });
}
// check if tensor list has bool tensors
bool has_bool_tensor(TensorList tensors) {
  return std::any_of(tensors.begin(), tensors.end(),
    [](const auto & t) -> bool { return t.scalar_type() == ScalarType::Bool; });
}

// Check foreach API restrictions
// - Tensor lists must be non-empty.
// - All TensorLists and ScalarLists must have the same number of elements.
// - Corresponding tensors must have the same size.
void check_foreach_api_restrictions(TensorList tensors) {
  TORCH_CHECK(tensors.size() > 0, "Tensor list must have at least one tensor.");
}

void check_foreach_api_restrictions(TensorList tensors, ArrayRef<Scalar> scalars) {
  check_foreach_api_restrictions(tensors);
  TORCH_CHECK(tensors.size() == scalars.size(), "Tensor list must have same number of elements as scalar list.");
}

void check_foreach_api_restrictions(TensorList tensors1, TensorList tensors2) {
  TORCH_CHECK(tensors1.size() > 0, "Tensor list must have at least one tensor.");
  TORCH_CHECK(tensors2.size() > 0, "Tensor list must have at least one tensor.");
  TORCH_CHECK(tensors1.size() == tensors2.size(), "Tensor lists must have the same number of tensors, got ", tensors1.size(), " and ", tensors2.size());
}

void check_foreach_api_restrictions(TensorList tensors1, TensorList tensors2, TensorList tensors3) {
  TORCH_CHECK(tensors1.size() > 0, "Tensor list must have at least one tensor.");
  TORCH_CHECK(tensors2.size() > 0, "Tensor list must have at least one tensor.");
  TORCH_CHECK(tensors3.size() > 0, "Tensor list must have at least one tensor.");
  TORCH_CHECK(tensors1.size() == tensors2.size(), "Tensor lists must have the same number of tensors, got ", tensors1.size(), " and ", tensors2.size());
  TORCH_CHECK(tensors1.size() == tensors3.size(), "Tensor lists must have the same number of tensors, got ", tensors1.size(), " and ", tensors3.size());
}

void check_foreach_api_restrictions(TensorList tensors1, TensorList tensors2, TensorList tensors3, ArrayRef<Scalar> scalars) {
  check_foreach_api_restrictions(tensors1, tensors2, tensors3);
  TORCH_CHECK(tensors1.size() == scalars.size(), "Tensor list must have same number of elements as scalar list, got ", tensors1.size(), " and ", scalars.size());
}

// To go via 'fast' path, several conditions must be satisfied
// - All tensors in all lists must have the same dtype.
// - All tensors must be on the same device
// - All tensors must have strided layout
// - All tensors must be non-overlapping and dense
// - Resulting tensor must have the same dtype as the input one

// Please, make sure to call check_foreach_api_restrictions before calling this method.
// There is a set of preconditions that have to be satisfied.
bool check_fast_path_restrictions(
  ArrayRef<TensorList> tensorLists,
  ArrayRef<Scalar> scalarList = {},
  bool does_op_promote_integer_inputs_to_float = false) {
    const auto expected_dtype = tensorLists[0][0].dtype();
    const auto expected_device = tensorLists[0][0].device();

auto is_tensor_okay = [&](const Tensor& tensor) {
      return tensor.dtype() == expected_dtype &&
             tensor.device() == expected_device &&
             tensor.layout() == at::kStrided &&
             tensor.is_non_overlapping_and_dense();
    };

for (const auto& tensorList : tensorLists) {
      for (const auto& tensor : tensorList) {
        if (!is_tensor_okay(tensor)) {
          return false;
        }
      }
    }

// Check if corresponding tensors in tensor lists have the same sizes and strides.
    for (const auto& tensor_list : tensorLists) {
      for (const auto j : c10::irange(tensorLists[0].size())) {
        if (tensorLists[0][j].sizes() != tensor_list[j].sizes()) {
          return false;
        }
        if (tensorLists[0][j].strides() != tensor_list[j].strides()) {
          return false;
        }
      }
    }

// This function has already checked that `tensorList[j][i]` for all j, i has the same dtype
    // using `is_tensor_okay` function above.
    // This means we only need to check if {tensorList[0][0], tensorList[0][1], tensorList[0][2], ...}
    // do type promotion with scalarLIst.
    for (const auto i : c10::irange(tensorLists[0].size())) {
      // For division, integer inputs will result in float.
      if (does_op_promote_integer_inputs_to_float) {
        if (at::isIntegralType(tensorLists[0][i].scalar_type(), /*includeBool*/ true)) {
          return false;
        }
      }
      if (scalarList.size() > 0) {
        const auto& scalar = scalarList.size() == 1 ? scalarList[0] : scalarList[i];
        const auto& tensor = tensorLists[0][i];
        // note(mkozuki): This check might be responsible for `_foreach_add(bool_tensors, bool_tensors)`
        // being pushed to slow path.
        if (tensor.scalar_type() != at::native::result_type(scalar, tensor)) {
          return false;
        }
      }
    }

return true;
}

bool can_use_fast_route(ArrayRef<TensorList> tensorLists,
                        ArrayRef<Scalar> scalarList = {},
                        bool does_op_promote_integer_inputs_to_float = false) {
#ifdef __HIP_PLATFORM_HCC__
  return false;
#else
  return check_fast_path_restrictions(tensorLists, scalarList, does_op_promote_integer_inputs_to_float);
#endif
}

bool can_use_fast_route(TensorList tensors1, TensorList tensors2, bool does_op_promote_integer_inputs_to_float = false) {
#ifdef __HIP_PLATFORM_HCC__
  return false;
#else
  return can_use_fast_route({tensors1, tensors2}, {}, does_op_promote_integer_inputs_to_float);
#endif
}

}
}} // at::native

cmd: