OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-06 12:20:52 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity

make g2p ~30% faster on mobile by suppressing a log (#85907)

Browse Source 
Summary: using the tool from D39559248 i was able to make g2p faster on mobile by taking a look at profiles on stella frames. It turned out that the pytorch interpreter code does some logging that ends up being a pretty big bottleneck.

Differential Revision: D39901455

Pull Request resolved: https://github.com/pytorch/pytorch/pull/85907
Approved by: https://github.com/dzdang
This commit is contained in:
Cody Ohlsen 2022-10-08 01:25:03 +00:00 committed by PyTorch MergeBot
parent bac26155e7
commit b645c237bc
2 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
aten/src/ATen/native/quantized/cpu/qlinear_dynamic.cpp
View File

@ -236,7 +236,7 @@ at::Tensor PackedLinearWeightsQnnp::apply_dynamic_impl(
at::Tensor input,
bool reduce_range) {
if (reduce_range) {
TORCH_WARN("Currently, qnnpack incorrectly ignores reduce_range when it is set to true; this may change in a future release.");
TORCH_WARN_ONCE("Currently, qnnpack incorrectly ignores reduce_range when it is set to true; this may change in a future release.");
}
using at::Tensor;

4
torch/csrc/jit/mobile/interpreter.cpp
View File

@ -110,6 +110,10 @@ bool InterpreterState::run(Stack& stack) {
// Check with iliacher if has been done.
// Plus this is not safe as if you throw exception record function will be
// left enabled. That is a TODO
// NOTE: this recordFunction logic takes up ~2-3% of cpu cycles in some
// workflows. do we need it and/or can we opt-out of
// isRecordFunctionEnabled with a macro? if we delete it, things appear to
// work just fine.
bool prev_value = isRecordFunctionEnabled();
if (!prev_value) {
// enable only for the RecordFunction