mirror of
https://github.com/zebrajr/pytorch.git
synced 2025-12-07 12:21:27 +01:00
517c7c9861
Summary:
Anywhere we used #include "foo.h", we now say #include <foo.h>
Paths are adjusted to be rooted out of aten/src, torch/lib, or
the root level directory.
I modified CMakeLists.txt by hand to remove TH and THC from
the include paths.
I used the following script to do the canonicalization:
```
import subprocess
import re
import os.path
files = subprocess.check_output(['git', 'ls-files']).decode('utf-8').rstrip().split('\n')
for fn in files:
if not any(fn.endswith(suff) for suff in ['.cu', '.cpp', '.in', '.h', '.hpp', '.cu', '.cuh', '.cc']):
continue
if not any(fn.startswith(pref) for pref in ["aten/", "torch/"]):
continue
with open(fn, 'r') as f:
c = f.read()
def fmt(p):
return "#include <{}>".format(p)
def repl(m):
p = m.group(1)
if p in ["dlfcn.h", "unistd.h", "nvrtc.h", "cuda.h", "cuda_runtime.h", "cstdint", "cudnn.h", "Python.h", "cusparse.h", "cuda_runtime_api.h", "cuda_fp16.h", "cublas_v2.h", "stdint.h", "curand_kernel.h"]:
return fmt(p)
if any(p.startswith(pref) for pref in ["torch/csrc", "c10/", "ATen/", "caffe2/", "TH/", "THC/", "Eigen/", "gtest/", "zdl/", "gloo/", "onnx/", "miopen/"]):
return fmt(p)
for root in ["aten/src", "torch/lib", ""]:
for bad_root in [os.path.dirname(fn), "aten/src/TH", "aten/src/THC", "torch/csrc"]:
new_p = os.path.relpath(os.path.join(bad_root, p), root)
if not new_p.startswith("../") and (os.path.exists(os.path.join(root, new_p)) or os.path.exists(os.path.join(root, new_p + ".in"))):
return fmt(new_p)
print("ERROR: ", fn, p)
return m.group(0)
new_c = re.sub(r'#include "([^"]+)"', repl, c)
if new_c != c:
print(fn)
with open(fn, 'w') as f:
f.write(new_c)
```
Signed-off-by: Edward Z. Yang <ezyang@fb.com>
Pull Request resolved: https://github.com/pytorch/pytorch/pull/14849
Reviewed By: dzhulgakov
Differential Revision: D13363445
Pulled By: ezyang
fbshipit-source-id: 52361f878a672785f9306c9e9ab2513128092b68
95 lines
2.9 KiB
C++
95 lines
2.9 KiB
C++
#include <torch/csrc/autograd/function.h>
|
|
|
|
#include <torch/csrc/autograd/engine.h>
|
|
#include <torch/csrc/autograd/variable.h>
|
|
#include <torch/csrc/jit/ir.h>
|
|
|
|
#include <ATen/ATen.h>
|
|
|
|
#include <algorithm>
|
|
#include <cstdint>
|
|
#include <memory>
|
|
#include <stdexcept>
|
|
#include <string>
|
|
#include <utility>
|
|
#include <vector>
|
|
#include <deque>
|
|
|
|
namespace torch { namespace autograd {
|
|
|
|
/// Monotonically incrementing (thread local!) counter to supply sequence
|
|
/// numbers.
|
|
thread_local uint64_t Function_next_sequence_nr_ = 0;
|
|
|
|
uint64_t Function::peek_at_next_sequence_nr() {
|
|
return Function_next_sequence_nr_;
|
|
}
|
|
|
|
uint64_t& Function::get_next_sequence_nr() {
|
|
return Function_next_sequence_nr_;
|
|
}
|
|
|
|
auto Function::name() const -> std::string {
|
|
return c10::demangle(typeid(*this).name());
|
|
}
|
|
|
|
AnomalyMetadata* Function::metadata() noexcept {
|
|
if (!anomaly_metadata_) {
|
|
anomaly_metadata_ = Engine::get_default_engine().make_anomaly_metadata();
|
|
}
|
|
return anomaly_metadata_.get();
|
|
}
|
|
|
|
static void gatherFunctions(
|
|
Function* func,
|
|
std::vector<std::shared_ptr<Function>>& stack) {
|
|
func->release_variables();
|
|
|
|
for (auto& edge : func->next_edges()) {
|
|
if (edge.function.use_count() == 1) {
|
|
stack.emplace_back(std::move(edge.function));
|
|
} else {
|
|
edge.function.reset();
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Fix for #5534: prevent stack overflow on deletion of deep computation graph
|
|
*
|
|
* Sometimes one can end up with a very big computation graph of Functions
|
|
* and Edges. Each std::shared_ptr<Function> contains a list of Edge, and
|
|
* each Edge contains a std::shared_ptr<Function>. Deleting a
|
|
* std::shared_ptr<Function> can trigger the recursive deletion of other
|
|
* std::shared_ptr<Function>'s: this can stack overflow if the graph
|
|
* is deep enough. Here is an example of such a graph:
|
|
*
|
|
* shared_ptr<Function> -> Edge -> shared_ptr<Function> -> Edge -> ... -> shared_ptr<Function>
|
|
*
|
|
* The solution here is to detect when we are decrementing away the last
|
|
* reference to a Function, and when doing so to buffer up the Function's
|
|
* that will be recursively decremented. We can then decrement (and free)
|
|
* the original Function without causing a recursive cascade, before
|
|
* draining the buffer applying the same behavior. This is, in effect,
|
|
* converting recursion to a loop, using a heap buffer in place of the
|
|
* recursive call stack.
|
|
*/
|
|
void deleteFunction(Function* function) {
|
|
// To avoid stack overflow on large computational graphs,
|
|
// we need to track reference decrementing and freeing
|
|
// on the heap.
|
|
function->release_variables();
|
|
std::vector<std::shared_ptr<Function>> stack;
|
|
gatherFunctions(function, stack);
|
|
delete function;
|
|
|
|
while (!stack.empty()) {
|
|
auto func = std::move(stack.back());
|
|
stack.pop_back();
|
|
gatherFunctions(func.get(), stack);
|
|
// Reference count is decremented on the loop backedge.
|
|
}
|
|
}
|
|
|
|
}} // namespace torch::autograd
|