Hi, our team is focusing on torch/pytorch performance optimization on Intel Platform, Xeon and Xeon Phi.
We provide packages of mklnn and mkltorch, similar to cudnn/cutorch.
Distro repo for install torch with mklnn/mkltorch by default is available at intel-torch
The usage of mklnn is very easy, simply add:
require 'mklnn'
model=mklnn.convert(model, 'mkl')
Overall performance of mklnn is much faster than nn on CPU.
The following features are being developed on torch:
tensor operations optimization with OpenMP
tensor operations optimization using AVX512 instruction set, targeting for latest generation of Xeon (Skylake) and Xeon Phi (Knights Mill)
Hi, our team is focusing on torch/pytorch performance optimization on Intel Platform, Xeon and Xeon Phi. We provide packages of mklnn and mkltorch, similar to cudnn/cutorch. Distro repo for install torch with mklnn/mkltorch by default is available at intel-torch
The usage of mklnn is very easy, simply add: require 'mklnn' model=mklnn.convert(model, 'mkl')
Overall performance of mklnn is much faster than nn on CPU.
The following features are being developed on torch:
Counterpart optimization for PyTorch is also WIP.
Any feedback from your side is highly valuable for us!