Comments (8)
We definitely want to use one single API for both Intel MKL and MKL-DNN. This single API will be MKL-DNN one.
Alas, right now I can't estimate when this will happen. Also since Intel MKL has to provide backward compatibility, DNN interface of Intel MKL will also remain supported for time being (at least for several years after deprecation notice).
from onednn.
Hi @Maratyszcza,
For the description of current differences please see this comment.
MKL-DNN interface was re-thought, in particular layout (mkldnn_memory_desc_t
) become transparent, while in Intel MKL it is opaque for user. For the rest Intel MKL (DNN primitives) and MKL-DNN are pretty close.
from onednn.
Thank you. Will Intel MKL adapt interfaces of MKL-DNN in the future, or there will be two parallel sets of interfaces?
from onednn.
@Maratyszcza Do you plan to integrate in NNPACK?
from onednn.
@bhack Integrate what?
from onednn.
I mean using NNPACK internal implementation and MKL-DNN with the same NNPACK API..
from onednn.
No, this wouldn't be efficient. MKL-DNN uses a different layout for layers.
from onednn.
@Maratyszcza So.. We need to interface another engine in tiny 😉
from onednn.
Related Issues (20)
- "could not create a primitive descriptor for an eltwise forward propagation primitive" error HOT 4
- Why choose the direct convolution? HOT 1
- dnnl_use_shift in dnnl_batch_normalization_backward_primitive_desc_create causes illegal argument error HOT 1
- Conservative reshaping HOT 6
- Test Failure with threadpool enabled on Arm. HOT 2
- Problem with creating descriptor for pooling primitive HOT 6
- [nvidia] batch normalization primitive fails correctness check HOT 2
- how to dispatch "avx2_vnni_2" HOT 8
- [nvidia] pooling primitive fails correctness check HOT 2
- [nvidia] resampling primitive fails correctness check
- gemm_api and Reorder in HuggingFace OPT model HOT 6
- [nvidia|amd] Add missing synchronization HOT 2
- oneDNN does not build with Intel oneMKL as BLAS Vendor HOT 5
- Falling to ref code in matmul HOT 2
- Understand jit_brgemm_kernel_t and its internals HOT 2
- Help need: use graph API to construct a subgraph of multi-head attention HOT 8
- CPU usage is not as high as expected when thread number >30 HOT 4
- Meet a erro in building process about dnnl HOT 2
- benchdnn matmul failing tests on aarch64 HOT 1
- Expected Multi-Threaded CPU Performance HOT 4
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 onednn.