clang -cc1 -cc1 -triple x86_64-unknown-linux-gnu -analyze -disable-free -disable-llvm-verifier -discard-value-names -main-file-name tensor_apply.cpp -analyzer-store=region -analyzer-opt-analyze-nested-blocks -analyzer-checker=core -analyzer-checker=apiModeling -analyzer-checker=unix -analyzer-checker=deadcode -analyzer-checker=cplusplus -analyzer-checker=security.insecureAPI.UncheckedReturn -analyzer-checker=security.insecureAPI.getpw -analyzer-checker=security.insecureAPI.gets -analyzer-checker=security.insecureAPI.mktemp -analyzer-checker=security.insecureAPI.mkstemp -analyzer-checker=security.insecureAPI.vfork -analyzer-checker=nullability.NullPassedToNonnull -analyzer-checker=nullability.NullReturnedFromNonnull -analyzer-output plist -w -analyzer-output=html -analyzer-checker=python -analyzer-disable-checker=deadcode -analyzer-config prune-paths=true,suppress-c++-stdlib=true,suppress-inlined-defensive-checks=false,suppress-null-return-paths=false,crosscheck-with-z3=true,model-path=/opt/pyrefcon/lib/pyrefcon/models/models -analyzer-config experimental-enable-naive-ctu-analysis=true,ctu-dir=/tmp/pyrefcon/pytorch/csa-scan,ctu-index-name=/tmp/pyrefcon/pytorch/csa-scan/externalDefMap.txt,ctu-invocation-list=/tmp/pyrefcon/pytorch/csa-scan/invocations.yaml,display-ctu-progress=false -setup-static-analyzer -analyzer-config-compatibility-mode=true -mrelocation-model pic -pic-level 2 -fhalf-no-semantic-interposition -mframe-pointer=none -relaxed-aliasing -fno-rounding-math -ffp-exception-behavior=ignore -mconstructor-aliases -munwind-tables -target-cpu x86-64 -tune-cpu generic -debugger-tuning=gdb -fcoverage-compilation-dir=/tmp/pyrefcon/pytorch/build -resource-dir /opt/pyrefcon/lib/clang/13.0.0 -isystem third_party/gloo -isystem ../cmake/../third_party/gloo -isystem ../cmake/../third_party/googletest/googlemock/include -isystem ../cmake/../third_party/googletest/googletest/include -isystem ../third_party/protobuf/src -isystem ../third_party/gemmlowp -isystem ../third_party/neon2sse -isystem ../third_party/XNNPACK/include -isystem ../third_party -isystem ../cmake/../third_party/eigen -isystem /opt/pyrefcon/lib/pyrefcon/models/python3.8 -isystem /usr/lib/python3/dist-packages/numpy/core/include -isystem ../cmake/../third_party/pybind11/include -isystem /usr/lib/x86_64-linux-gnu/openmpi/include/openmpi -isystem /usr/lib/x86_64-linux-gnu/openmpi/include -isystem ../third_party/ideep/mkl-dnn/include -isystem ../third_party/ideep/include -D BUILDING_TESTS -D FMT_HEADER_ONLY=1 -D HAVE_MALLOC_USABLE_SIZE=1 -D HAVE_MMAP=1 -D HAVE_SHM_OPEN=1 -D HAVE_SHM_UNLINK=1 -D MINIZ_DISABLE_ZIP_READER_CRC32_CHECKS -D ONNXIFI_ENABLE_EXT=1 -D ONNX_ML=1 -D ONNX_NAMESPACE=onnx_torch -D THP_BUILD_MAIN_LIB -D USE_C10D -D USE_C10D_GLOO -D USE_C10D_MPI -D USE_DISTRIBUTED -D USE_EXTERNAL_MZCRC -D USE_NUMPY -D USE_RPC -D USE_TENSORPIPE -D USE_VALGRIND -D _FILE_OFFSET_BITS=64 -D torch_python_EXPORTS -I aten/src -I ../aten/src -I . -I ../ -I ../cmake/../third_party/benchmark/include -I caffe2/contrib/aten -I ../third_party/onnx -I third_party/onnx -I ../third_party/foxi -I third_party/foxi -I ../torch/.. -I ../torch/../aten/src -I ../torch/../aten/src/TH -I caffe2/aten/src -I third_party -I ../torch/../third_party/valgrind-headers -I ../torch/../third_party/gloo -I ../torch/../third_party/onnx -I ../torch/csrc -I ../torch/csrc/api/include -I ../torch/lib -I ../torch/lib/libshm -I ../torch/csrc/distributed -I ../torch/csrc/api -I ../c10/.. -I third_party/ideep/mkl-dnn/include -I ../third_party/ideep/mkl-dnn/src/../include -I ../torch/lib/libshm/../../../torch/lib -I ../third_party/fmt/include -D USE_PTHREADPOOL -D NDEBUG -D USE_KINETO -D LIBKINETO_NOCUPTI -D USE_FBGEMM -D USE_QNNPACK -D USE_PYTORCH_QNNPACK -D USE_XNNPACK -D SYMBOLICATE_MOBILE_DEBUG_HANDLE -D HAVE_AVX_CPU_DEFINITION -D HAVE_AVX2_CPU_DEFINITION -D NDEBUG -D NDEBUG -D CAFFE2_USE_GLOO -D HAVE_GCC_GET_CPUID -D USE_AVX -D USE_AVX2 -D TH_HAVE_THREAD -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/10/../../../../include/c++/10 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/10/../../../../include/x86_64-linux-gnu/c++/10 -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/10/../../../../include/c++/10/backward -internal-isystem /opt/pyrefcon/lib/clang/13.0.0/include -internal-isystem /usr/local/include -internal-isystem /usr/lib/gcc/x86_64-linux-gnu/10/../../../../x86_64-linux-gnu/include -internal-externc-isystem /usr/include/x86_64-linux-gnu -internal-externc-isystem /include -internal-externc-isystem /usr/include -O3 -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -Wno-unused-but-set-variable -Wno-maybe-uninitialized -Werror=format -Werror=cast-function-type -Wno-stringop-overflow -Wno-write-strings -Wno-strict-aliasing -w -std=gnu++14 -fdeprecated-macro -fdebug-compilation-dir=/tmp/pyrefcon/pytorch/build -ferror-limit 19 -fvisibility-inlines-hidden -fopenmp -fopenmp-cuda-parallel-target-regions -pthread -fgnuc-version=4.2.1 -fcxx-exceptions -fexceptions -faligned-allocation -fcolor-diagnostics -vectorize-loops -vectorize-slp -faddrsig -D__GCC_HAVE_DWARF2_CFI_ASM=1 -o /tmp/pyrefcon/pytorch/csa-scan/reports -x c++ ../torch/csrc/utils/tensor_apply.cpp
| 1 | #include <torch/csrc/utils/tensor_apply.h> |
| 2 | |
| 3 | #include <ATen/TensorUtils.h> |
| 4 | #include <ATen/ExpandUtils.h> |
| 5 | #include <c10/util/irange.h> |
| 6 | |
| 7 | #include <torch/csrc/Exceptions.h> |
| 8 | #include <torch/csrc/utils/python_numbers.h> |
| 9 | #include <torch/csrc/utils/python_scalars.h> |
| 10 | |
| 11 | using namespace at; |
| 12 | |
| 13 | namespace torch { namespace utils { |
| 14 | |
| 15 | struct StridedData { |
| 16 | StridedData(const Tensor & tensor) |
| 17 | : data(tensor.data_ptr()) |
| 18 | , strides(tensor.strides()) |
| 19 | , elementSize(tensor.element_size()) {} |
| 20 | |
| 21 | void* data; |
| 22 | IntArrayRef strides; |
| 23 | int64_t elementSize; |
| 24 | |
| 25 | void step(int dim) { |
| 26 | data = (char*)data + (strides[dim] * elementSize); |
| 27 | } |
| 28 | }; |
| 29 | |
| 30 | template<size_t N> |
| 31 | static void recursive_apply(IntArrayRef sizes, ScalarType scalarType, int64_t dim, |
| 32 | PyObject* fn, std::array<StridedData, N> strided_data) { |
| 33 | int64_t ndim = sizes.size(); |
| 34 | if (dim == ndim) { |
| 1 | Assuming 'dim' is equal to 'ndim' | |
|
| |
| 35 | auto args = THPObjectPtr(PyTuple_New(N)); |
| |
| 5 | | Returning from 'PyTuple_New' | |
|
| 10 | | PyObject ownership leak with reference count of 1 |
|
| 36 | if (!args) throw python_error(); |
| 6 | | Assuming the condition is false | |
|
| |
| 37 | for(const auto i : c10::irange(N)) { |
| 38 | PyObject* arg = load_scalar(strided_data[i].data, scalarType); |
| 39 | if (!arg) throw python_error(); |
| |
| |
| 40 | PyTuple_SET_ITEM(args.get(), i, arg); |
| 41 | } |
| 42 | auto ret = THPObjectPtr(PyObject_CallObject(fn, args.get())); |
| 43 | if (!ret) throw python_error(); |
| 44 | store_scalar(strided_data[0].data, scalarType, ret.get()); |
| 45 | return; |
| 46 | } |
| 47 | |
| 48 | auto n = sizes[dim]; |
| 49 | for(const auto i : c10::irange(n)) { |
| 50 | (void)i; |
| 51 | recursive_apply(sizes, scalarType, dim + 1, fn, strided_data); |
| 52 | for (auto& td : strided_data) { |
| 53 | td.step(dim); |
| 54 | } |
| 55 | } |
| 56 | } |
| 57 | |
| 58 | const Tensor & apply_(const Tensor & self, PyObject* fn) { |
| 59 | if (self.is_meta()) { |
| 60 | return self; |
| 61 | } |
| 62 | if (!self.device().is_cpu()) { |
| 63 | throw TypeError("apply_ is only implemented on CPU tensors"); |
| 64 | } |
| 65 | auto scalarType = self.scalar_type(); |
| 66 | recursive_apply<1>(self.sizes(), scalarType, 0, fn, {{ self }}); |
| 67 | return self; |
| 68 | } |
| 69 | |
| 70 | const Tensor & map_(const Tensor & self, const Tensor & other_, PyObject* fn) { |
| 71 | if (!other_.options().type_equal(self.options())) { |
| 72 | throw TypeError("map_: expected %s for 'other' (got %s)", |
| 73 | self.toString().c_str(), other_.toString().c_str()); |
| 74 | } |
| 75 | if (self.is_meta()) { |
| 76 | return self; |
| 77 | } |
| 78 | if (!self.device().is_cpu()) { |
| 79 | throw TypeError("map_ is only implemented on CPU tensors"); |
| 80 | } |
| 81 | c10::MaybeOwned<Tensor> other = expand_inplace(self, other_, "map_"); |
| 82 | auto scalarType = self.scalar_type(); |
| 83 | recursive_apply<2>(self.sizes(), scalarType, 0, fn, {{ self, *other }}); |
| 84 | return self; |
| 85 | } |
| 86 | |
| 87 | const Tensor & map2_(const Tensor & self, const Tensor & x_, const Tensor & y_, PyObject* fn) { |
| 88 | if (!x_.options().type_equal(self.options())) { |
| 89 | throw TypeError("map2_: expected %s for argument 'x' (got %s)", |
| 90 | self.toString().c_str(), x_.toString().c_str()); |
| 91 | } |
| 92 | if (!y_.options().type_equal(self.options())) { |
| 93 | throw TypeError("map2_: expected %s for argument 'y' (got %s)", |
| 94 | self.toString().c_str(), y_.toString().c_str()); |
| 95 | } |
| 96 | if (self.is_meta()) { |
| 97 | return self; |
| 98 | } |
| 99 | if (!self.device().is_cpu() || !x_.device().is_cpu() || !y_.device().is_cpu()) { |
| 100 | throw TypeError("map2_ is only implemented on CPU tensors"); |
| 101 | } |
| 102 | auto others = expand_inplace(self, x_, y_, "map2_"); |
| 103 | auto scalarType = self.scalar_type(); |
| 104 | recursive_apply<3>(self.sizes(), scalarType, 0, fn, {{ self, *std::get<0>(others), *std::get<1>(others) }}); |
| 105 | return self; |
| 106 | } |
| 107 | |
| 108 | }} |