mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-24 23:54:56 +08:00
4cb534f92e
Summary:
This is an automatic change generated by the following script:
```
#!/usr/bin/env python3
from subprocess import check_output, check_call
import os
def get_compiled_files_list():
import json
with open("build/compile_commands.json") as f:
data = json.load(f)
files = [os.path.relpath(node['file']) for node in data]
for idx, fname in enumerate(files):
if fname.startswith('build/') and fname.endswith('.DEFAULT.cpp'):
files[idx] = fname[len('build/'):-len('.DEFAULT.cpp')]
return files
def run_clang_tidy(fname):
check_call(["python3", "tools/clang_tidy.py", "-c", "build", "-x", fname,"-s"])
changes = check_output(["git", "ls-files", "-m"])
if len(changes) == 0:
return
check_call(["git", "commit","--all", "-m", f"NOLINT stubs for {fname}"])
def main():
git_files = check_output(["git", "ls-files"]).decode("ascii").split("\n")
compiled_files = get_compiled_files_list()
for idx, fname in enumerate(git_files):
if fname not in compiled_files:
continue
if fname.startswith("caffe2/contrib/aten/"):
continue
print(f"[{idx}/{len(git_files)}] Processing {fname}")
run_clang_tidy(fname)
if __name__ == "__main__":
main()
```
Pull Request resolved: https://github.com/pytorch/pytorch/pull/56892
Reviewed By: H-Huang
Differential Revision: D27991944
Pulled By: malfet
fbshipit-source-id: 5415e1eb2c1b34319a4f03024bfaa087007d7179
75 lines
2.5 KiB
C++
75 lines
2.5 KiB
C++
#include <gtest/gtest.h>
|
|
|
|
#include "test/cpp/jit/test_utils.h"
|
|
#include "torch/csrc/jit/runtime/graph_executor.h"
|
|
#include "torch/jit.h"
|
|
#include "torch/script.h"
|
|
#include "torch/torch.h"
|
|
|
|
namespace torch {
|
|
namespace jit {
|
|
|
|
// NOLINTNEXTLINE(cppcoreguidelines-avoid-non-const-global-variables)
|
|
TEST(GraphExecutorTest, Basic_CUDA) {
|
|
constexpr int batch_size = 4;
|
|
constexpr int input_size = 256;
|
|
|
|
int hidden_size = 2 * input_size;
|
|
|
|
auto input = at::randn({batch_size, input_size}, at::kCUDA);
|
|
auto hx = at::randn({batch_size, hidden_size}, at::kCUDA);
|
|
auto cx = at::randn({batch_size, hidden_size}, at::kCUDA);
|
|
auto w_ih = t_def(at::randn({4 * hidden_size, input_size}, at::kCUDA));
|
|
auto w_hh = t_def(at::randn({4 * hidden_size, hidden_size}, at::kCUDA));
|
|
|
|
auto g = build_lstm();
|
|
GraphExecutor executor(g, "");
|
|
auto stack = createStack({input, hx, cx, w_ih, w_hh});
|
|
executor.run(stack);
|
|
ASSERT_EQ(stack.size(), 2);
|
|
at::Tensor r0, r1;
|
|
std::tie(r0, r1) = lstm(input, hx, cx, w_ih, w_hh);
|
|
ASSERT_TRUE(almostEqual(stack[0].toTensor(), r0));
|
|
ASSERT_TRUE(almostEqual(stack[1].toTensor(), r1));
|
|
}
|
|
|
|
// NOLINTNEXTLINE(cppcoreguidelines-avoid-non-const-global-variables)
|
|
TEST(GraphExecutorTest, runAsync_executor) {
|
|
/*
|
|
TODO: there are some problem with C++ parsing script program involving
|
|
fork. Use the test module below for now.
|
|
issue about this: github.com/pytorch/pytorch/issues/46368
|
|
The test module file is generated by following:
|
|
class DemoModule(torch.nn.Module):
|
|
def forward(self):
|
|
r1 = torch.jit.fork(torch.mm, torch.rand(100,100),torch.rand(100,100))
|
|
r2 = torch.jit.fork(torch.mm, torch.rand(100,100),torch.rand(100,100))
|
|
return r1.wait() + r2.wait()
|
|
demo = DemoModule()
|
|
torch.jit.save(torch.jit.script(demo), 'test_interpreter_async.pt')
|
|
*/
|
|
std::string filePath(__FILE__);
|
|
auto testModelFile = filePath.substr(0, filePath.find_last_of("/\\") + 1);
|
|
testModelFile.append("test_interpreter_async.pt");
|
|
auto module = load(testModelFile);
|
|
auto graph = module.get_method("forward").graph();
|
|
GraphExecutor graphExecutor(graph, "");
|
|
auto asyncCounter = 0;
|
|
std::mutex mtx;
|
|
// a dummy executor which actually use at::launch, but add up a counter
|
|
auto launcher = [&](std::function<void()> f) {
|
|
mtx.lock();
|
|
++asyncCounter;
|
|
mtx.unlock();
|
|
at::launch(move(f));
|
|
};
|
|
std::vector<IValue> stack;
|
|
// NOLINTNEXTLINE(modernize-use-emplace)
|
|
stack.push_back(module._ivalue());
|
|
graphExecutor.runAsync(stack, launcher)->wait();
|
|
ASSERT_TRUE(asyncCounter > 0);
|
|
}
|
|
|
|
} // namespace jit
|
|
} // namespace torch
|