MIOpen - AshokBhat/notes GitHub Wiki

About

• From AMD
• Foundation for Deep Learning acceleration
• Support for Convolutional Neural Network acceleration
• Built to run on top of the ROCm software stack!

Contents of 1.0

• Deep Convolution Solvers optimized for both forward and backward propagation
• Optimized Convolutions including Winograd and FFT transformations
• Optimized GEMM’s for Deep Learning
• Pooling, Softmax, Activations, Gradient Algorithms Batch Normalization, and LR Normalization
• MIOpen describes data as 4-D tensors ‒ Tensors 4D NCHW format
• Support for OpenCL and HIP enabled frameworks
• MIOpen Driver enables to testing forward/backward network of any particular layer in MIOpen.

Availablity

• Binary Package support for Ubuntu 16.04 and Fedora 24
• Source code at ROCm Software Platform Github site

Further information

• Paper MIOpen: An Open Source Library For Deep Learning Primitives