Published in PC Hardware

Intel announces new VPU

by on29 August 2017


Chipzilla’s end-to-end AI

Intel has released its new Movidius Myriad X vision processing unit (VPU) which is Intel's end-to-end portfolio for an artificial intelligence (AI) solution.

Intel is hoping the VPU will deliver more autonomous capabilities across a wide range of product categories including drones, robotics, smart cameras and virtual reality (VR).

Intel claimed that the Myriad X is the world's first system-on-chip (SOC) shipping with a dedicated Neural Compute Engine for accelerating deep learning inferences at the edge.

It said that the neural compute engine is an on-chip hardware block specifically designed to run deep neural networks at high speed and low power without compromising accuracy, enabling devices to see, understand and respond to their environments in real time.

The Myriad X’s architecture has a neural compute engine which can manage a trillion operations per second (TOPS) of compute performance on deep neural network inferences.

Capable of delivering more than 4TOPS of total performance, Intel claims its tiny form factor and on-board processing are ideal for autonomous devices. In addition to its neural compute engine, the Myriad X combines imaging, visual processing and deep learning inference in real time.

It has programmable 128-bit VLIW vector processors run multiple imaging and vision application pipelines simultaneously with 16 vector processors optimised for computer vision workloads.

Also under the bonnet are more configurable MIPI lanes connect up to 8 HD resolution RGB cameras directly to the Myriad X with its 16 MIPI lanes included in its rich set of interfaces, to support up to 700 million pixels per second of image signal processing throughput.

Enhanced vision accelerators use over 20 hardware accelerators to perform tasks such as optical flow and stereo depth without introducing additional compute overhead. The centralised 2.5MB of homogenous on-chip memory allows for up to 450GB per second of internal bandwidth, minimizing latency and reducing power consumption by minimizing off-chip data transfer.

The Myriad 2 will not be replaced by the Myriad X. Last January, the Myriad 2 was described as costing under $10; based on the higher cost FinFET process and additional hardware features. The Myriad X will likely command a higher price for the higher performance.

 

Last modified on 29 August 2017
Rate this item
(0 votes)

Read more about: