mirror of
https://github.com/pytorch/pytorch.git
synced 2026-11-20 09:04:25 +08:00
Make JIT Serialization support arbitrary std::function<> IO (#28039)
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/28039 Right now, torch::save() uses std::ostream, which results in unnecessary data copies in practice. Similar for torch::load(). Adding a std::function<size_t(const void*, size_t)> as an output option, parallel to the existing filename and std::ostream apis, gives users the flexibility to emit directly to a backing store. For a simple case of appending the output to a std::string, we observe significant benchmark savings (on order of -50%), even with the minor std::function<> dispatch overhead. The main reason is that std::ostringstream effectively requires 2 extra copies of the data beyond a simple string.append lambda. We also provide a parallel api for the load(), though this one is slightly more complex due to the need to do arbitrary position reads. Test Plan: buck test mode/dev-nosan caffe2/test/... (Basic serialization test in caffe2/test/cpp/api/serialize.cpp) Benchmark in experimental/jeremyl/c2/SerializationBench.cpp, with D17823443 (1M time goes from 90ms -> 40ms, albeit with crc patch applied) Differential Revision: D17939034 fbshipit-source-id: 344cce46f74b6438cb638a8cfbeccf4e1aa882d7
This commit is contained in:
committed by
Facebook Github Bot
parent
9cc4405dc9
commit
2e0294cb39
@@ -60,6 +60,37 @@ TEST(SerializeTest, BasicToFile) {
|
||||
ASSERT_TRUE(x.allclose(y));
|
||||
}
|
||||
|
||||
TEST(SerializeTest, BasicViaFunc) {
|
||||
torch::manual_seed(0);
|
||||
|
||||
auto x = torch::randn({5, 5});
|
||||
|
||||
std::string serialized;
|
||||
torch::save(x, [&](const void* buf, size_t n) {
|
||||
serialized.append(reinterpret_cast<const char *>(buf), n);
|
||||
return n;
|
||||
});
|
||||
torch::Tensor y;
|
||||
torch::load(y, serialized.data(), serialized.size());
|
||||
|
||||
ASSERT_TRUE(y.defined());
|
||||
ASSERT_EQ(x.sizes().vec(), y.sizes().vec());
|
||||
ASSERT_TRUE(x.allclose(y));
|
||||
|
||||
torch::Tensor z;
|
||||
torch::load(z, [&](uint64_t pos, void* buf, size_t n) -> size_t {
|
||||
if (pos >= serialized.size()) return 0;
|
||||
size_t nbytes = std::min(static_cast<size_t>(pos) + n,
|
||||
serialized.size()) - pos;
|
||||
memcpy(buf, serialized.data() + pos, nbytes);
|
||||
return nbytes;
|
||||
},
|
||||
[&]() -> size_t { return serialized.size(); });
|
||||
ASSERT_TRUE(z.defined());
|
||||
ASSERT_EQ(x.sizes().vec(), z.sizes().vec());
|
||||
ASSERT_TRUE(x.allclose(z));
|
||||
}
|
||||
|
||||
TEST(SerializeTest, Resized) {
|
||||
torch::manual_seed(0);
|
||||
|
||||
|
||||
Reference in New Issue
Block a user