Comments (2)
Hi,
Thanks for your support !
By default the library will use the default cl::Context and default cl::CommandQueue
We haven't actually tried that, but I imagine it should be as simple as setting the cl::CommandQueue and cl::Context manually at the beginning of your test:
CLScheduler::get().default_init();
cl::Context context( CL_DEVICE_TYPE_CPU ); /* or CL_DEVICE_TYPE_GPU */
cl::CommandQueue queue( context);
CLScheduler::get().init(context, queue);
Let me know if this does what you want.
Using both at the same time will be more tricky as currently the Runtime scheduler will use only a single queue. However this would be definitely possible if you were using the library at the Core level (i.e only the CLKernels not the CLFunctions) but that would be more work.
Hope this helps,
from computelibrary.
Please reopen if it doesn't solve your problem
from computelibrary.
Related Issues (20)
- Differences between run() and run_op() HOT 2
- Can Khadas Edge2 board be supported? HOT 5
- Performance is slow compared to other inference frameworks. HOT 5
- why CLCannyEdge and NECannyEdge is removed from the new ACL version ? HOT 1
- How to add a new backend? HOT 1
- ACL implementation for fp32 to bf16 conversion and weights pre-packing (reordering) is missing HOT 9
- Problem with deconvolution layer validation HOT 1
- Benchmark for cpu one core and one thread HOT 10
- Help Wanted: Accelerating Scikit-Learn Algorithms with Arm Compute Library (ACL) and OpenBLAS HOT 8
- example neno_sgemm loading *.npy Error which generated by python code HOT 5
- ACL performance gap between baremetal and linux. HOT 1
- Error When compile neon_cnn.cpp using aarch64-linux-gnu-g++ tools HOT 2
- Documentation isn't work for 23.08 release HOT 2
- Pure image processing operations HOT 2
- Add support for self-attention layer for GPU HOT 1
- How to use fixed format kernel? HOT 2
- How to add a new operator to ACL HOT 2
- ACL implementation for Filtering functions like FIR/IIR HOT 2
- Question about thread-safety
- Latency for Conv2d and Depthwise HOT 2
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 computelibrary.