mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-29 20:14:01 +00:00
Update docs for AzureEP and threading (#16061)
1. Remove zlib and re2 deps for AzureEP. 2. Explain --use_lock_free_queue usage. --------- Co-authored-by: Randy Shuai <rashuai@microsoft.com>
This commit is contained in:
parent
9e6613db1e
commit
627112921e
2 changed files with 9 additions and 8 deletions
|
|
@ -28,14 +28,6 @@ Pre-built Python binaries of ONNX Runtime with Azure EP are published on Pypi: [
|
|||
|
||||
## Requirements
|
||||
|
||||
For Windows, please install [zlib](https://zlib.net/) and [re2](https://github.com/google/re2), and add their binaries into the system path.
|
||||
If built from source, zlib and re2 binaries could be easily located with:
|
||||
|
||||
```dos
|
||||
cd <build_output_path>
|
||||
dir /s zlib1.dll re2.dll
|
||||
```
|
||||
|
||||
For Linux, please make sure openssl is installed.
|
||||
|
||||
## Build
|
||||
|
|
|
|||
|
|
@ -60,3 +60,12 @@ whenever it is ready to run. So over a period of time, threads in the pool are l
|
|||
Due to the same reason, the dynamic cost model may also improve the performance for cases when threads are more likely be preempted.
|
||||
Per our tests, by far the best configuration for dynamic_block_base is 4, which lowers the variance while keeping good performance.
|
||||
|
||||
|
||||
## I am seeing high CPU usage on windows
|
||||
|
||||
It is observed that for machines have more than 64 logical cores, CPU usage could be notably lowered by letting the thread pool use a lock-free task queue,
|
||||
which utilizes spinlock instead of mutex for synchronization. The lock-free task queue could be enabled by building onnxruntime from source with following flag:
|
||||
|
||||
```
|
||||
--use_lock_free_queue
|
||||
```
|
||||
Loading…
Reference in a new issue