Comments (7)
i found qnnp_run_operator run faster when set the threadpool var to nullptr than set the threadpool to 1~4 thread num.
from qnnpack.
so how many thread is opened by default within the qnnpack_run_operator func.
from qnnpack.
in my experiments, the default performance(set the threadpool to nullptr) is similar to set the threadpool to 4 threads.
from qnnpack.
which thread pool implementation do you use? pthreadpool library is not very efficient, but Caffe2 reimplements pthreadpool interface on top of its own (a lot more efficient) thread pool.
from qnnpack.
yes, i used pthreadpool. i‘ll look into caffe2.
from qnnpack.
In the past few days, I have rewrite the threadpool like caffe2, and the computation speed has been greatly improved, so I would like to know if you have any plans to add a custom threadpool library.
from qnnpack.
I have plans to upstream Caffe2 threadpool modifications to pthreadpool, but this is not the first priority right now.
from qnnpack.
Related Issues (20)
- Per channel quantization for the weights HOT 1
- Implementation detail things... HOT 9
- Deconvolutional Layer is slow for large kernel size HOT 2
- No performance difference between ARMv7 (32-bit) Android and ARM64 (64-bit) Android HOT 1
- Request to add Conv1d related operation HOT 1
- What's the relationship between the ASM and C version micro kernel? HOT 5
- Request to add a Concat layer HOT 1
- Crashed when running conv3x3 test
- Typo in the announcement blog? HOT 1
- 3d convolution support HOT 1
- Is the code multithreaded for arm64? HOT 7
- build error
- is there any example to use fp16 gemm?
- COMPAIR ERROR HOT 2
- How to build dependencies separately
- Is QNNPACK still being developed? HOT 1
- Understanding XZP ukernel HOT 1
- Build failed on rasp pi 4 (Error: selected processor does not support `yield' in ARM mode) HOT 1
- Support for nn.ConvTranspose2d
- Qnnpack accuracy very poor on unet model HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from qnnpack.