Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN) is an open-source performance library for deep learning applications. The library includes basic building blocks for neural networks optimized for Intel Architecture Processors and Intel Processor Graphics. Intel MKL-DNN is intended for deep learning applications and framework developers intersted in improving application performance on Intel CPUs and GPUs.
Compute intensive operations:
Memory bandwidth limited operations:
Data manipulation:
Topic | Engine | C++ API | C API |
---|---|---|---|
Tutorials | CPU | Getting started | |
Memory format propagation | |||
Performance Profiling Example | |||
GPU | Getting started on GPU | Getting started on GPU | |
GPU | Getting started on GPU with OpenCL extensions API | ||
f32 inference | CPU | CNN f32 inference example | CNN f32 inference example |
CPU | RNN f32 inference example | ||
int8 inference | CPU | CNN int8 inference example | |
CPU | RNN int8 inference example | ||
f32 training | CPU | CNN f32 training example | CNN f32 training example |
CPU | RNN f32 training example | ||
bf16 training | CPU | CNN bf16 training example |