- SDS011 the Air Quality SensorPosted 1 month ago
- NIXIE STYLE LED DISPLAYPosted 4 months ago
- TOTEM: learning by experimentingPosted 4 months ago
- Google Assistant Voice Controlled Switch – NodeMCU IOT ProjePosted 5 months ago
- Water Softener Salt Level MonitorPosted 5 months ago
- Sparkly Air SensorPosted 5 months ago
- Ultra sonic distance finder with live statusPosted 5 months ago
- Windows interface to have total control over lampsPosted 5 months ago
- Smart AquariumPosted 5 months ago
- Wearable ProjectionPosted 5 months ago
MIOpen and ROCm: AMD’s free, open-source deep learning softwares
To support the new family of Radeon Instinct accelerators, AMD plans to roll out an open source library called MIOpen. It provides GPU-tuned implementations for standard routines such as convolution, pooling, activation functions, normalization and tensor format.
AMD will also launch the ROCm software platform, which the company said is optimized for accelerating deep learning frameworks such as Caffe, Torch 7 and Tensorflow.
Among the sectors AMD is targeting with Instinct, MIOpen and ROCm, are self-driving cars, smart homes, autopilot drones, personal robots, financial services and security.
“Radeon Instinct is set to dramatically advance the pace of machine intelligence through an approach built on high-performance GPU accelerators, and free, open-source software in MIOpen and ROCm,” said Raja Koduri, head of AMD’s Radeon Technologies Group.
AMD said its new Instinct accelerators are aimed at enabling customers to better use and understand the vastly expanding volumes of data being generated by a wide range of applications and devices. The new technologies are designed to provide a blueprint for an open software ecosystem for machine intelligence, helping to speed inference insights and algorithm training.
The Radeon Instinct lineup includes three different accelerators: two for inference applications and one designed for deep learning training:
– MI6 inference-focused accelerator, based on the Polaris GPU architecture, will offer a peak FP16 performance of 5.7 teraflops and is passively cooled.
– MI8 inference accelerator is based on the Fiji architecture and promises a peak FP16 performance of 8.2 teraflops
– Radeon Instinct MI25, is optimized for deep learning training and is built on AMD’s Vega GPU architecture. It is passively cooled.