Nikolay Shchegolev

Results 12 comments of Nikolay Shchegolev
trafficstars

In general this solution looks complicated for such task. Please look at this [solution](https://github.com/openvinotoolkit/openvino/blob/93c94a7637d848ec1426919129c6da6e247ca3c9/src/plugins/intel_cpu/src/nodes/kernels/kernel_utils.hpp#L467) and [usage](https://github.com/openvinotoolkit/openvino/blob/93c94a7637d848ec1426919129c6da6e247ca3c9/src/plugins/intel_cpu/src/nodes/kernels/grid_sample_kernel.cpp).

> > In general this solution looks complicated for such task. Please look at this [solution](https://github.com/openvinotoolkit/openvino/blob/93c94a7637d848ec1426919129c6da6e247ca3c9/src/plugins/intel_cpu/src/nodes/kernels/kernel_utils.hpp#L467) and [usage](https://github.com/openvinotoolkit/openvino/blob/93c94a7637d848ec1426919129c6da6e247ca3c9/src/plugins/intel_cpu/src/nodes/kernels/grid_sample_kernel.cpp). > > @nshchego, @lohika-denis-kotov actually, this solution is much simpler in use....

> > In general this solution looks complicated for such task. Please look at this [solution](https://github.com/openvinotoolkit/openvino/blob/93c94a7637d848ec1426919129c6da6e247ca3c9/src/plugins/intel_cpu/src/nodes/kernels/kernel_utils.hpp#L467) and [usage](https://github.com/openvinotoolkit/openvino/blob/93c94a7637d848ec1426919129c6da6e247ca3c9/src/plugins/intel_cpu/src/nodes/kernels/grid_sample_kernel.cpp). > > @nshchego I think that we should hide complexity of allocation...

@dmitry-gorokhov, could you please take a look and merge this PR?

> ache twiddles for FFT function and add x86 JIT implementations. Please add the ticket number.

Is there a PR for oneDNN changes?

The code LGTM. We need to run Bench to prove the performance gain. I'll try to do it soon.

> Could you give some test data about how much benefit we can achieve from import model with mmap buffer? such as, how many memory has been saved? And is...

> Implementation LGTM. Please, add tests There are enough number of test cases in the CompileModelCacheTestBase. They cover mmap as well.

Hello, Please check which data types the CPU plugin supports [here](https://docs.openvino.ai/2023.3/openvino_docs_OV_UG_supported_plugins_CPU.html). In particular, i64 is not supported. You can execute extension node in i64, but inputs/outputs will be converted anyway....