Comments (2)
Hi @Devjiu, as for the first question, oneDNN provides API execution tracing with primitive information via the environment variable ONEDNN_VERBOSE
. Please refer to the verbose mode documentation for more detail.
As for the second question, indeed you can use set_data_handle() for example in examples/primitives/convolution.cpp you can replace the the following lines:
write_to_dnnl_memory(src_data.data(), user_src_mem);
write_to_dnnl_memory(weights_data.data(), user_weights_mem);
write_to_dnnl_memory(bias_data.data(), user_bias_mem);
with
user_src_mem.set_data_handle(src_data.data());
user_weights_mem.set_data_handle(weights_data.data());
user_bias_mem.set_data_handle(bias_data.data());
Another option is to pass data during memory creation:
auto user_src_mem = memory({src_dims, dt::f32, tag::nchw}, engine, src_data.data());
Hope this helps, let us know if you run to any other issues!
from onednn.
@yehudaorel
Thanks, for quick response)
I was sure, that already set this variable - but there left dnnl_set_verbose(0);
in my code. Thanks for the hint.
Setting data pointer in c-tor also helped, much better.
Sorry for noob questions, my questions are resolved.
from onednn.
Related Issues (20)
- build failure in aarch64 with ACL HOT 3
- test_benchdnn_matmul_ci_cpu fails on aarch64 with and without the Compute Library backend HOT 12
- GEMM API for efficient LLM inference with W8A16 HOT 3
- How scales work in oneDNN HOT 9
- Static builds with ONEDNN_VERBOSE=OFF produce undefined symbol: dnnl::impl::rt_mds2str HOT 1
- Builds with ONEDNN_ENABLE_MAX_CPU_ISA=OFF crash HOT 2
- accuracy issue in a graph conv test HOT 2
- create memory with tag::any,it crash HOT 3
- bibtex ref about oneDNN HOT 4
- Understand oneDNN graph compiler HOT 7
- Difference between BRGEMM in oneDNN and GEMM in openBLAS HOT 7
- Issue building oneDNN 3.4.4 with CLANG for ARM64 on Windows HOT 1
- cblass_gemm incorrect output HOT 2
- test_shuffle fails on aarch64 when BF16 data type is enabled. HOT 2
- [ACL] Potentially redundant check in `acl_init_conf` HOT 1
- Enable building oneDNN with MKL when integrated with PyTorch and IPEX via ideep HOT 4
- oneDNN 'Build from Source' doesn't work HOT 9
- Why are the convolutional inference results of OneDNN very different from the convolutional structure of pytorch? HOT 8
- How to disable USM feature for GPU plugin HOT 9
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.