Wednesday, September 26, 2018
Search
  
Submit your own News for
inclusion in our Site.
Click here...
Breaking News
PS4 Gets Fortnite Cross-play Support
ARM Unveils the Cortex-A76AE Chip Design for Autonomous Cars
Google to Allow Chrome users to Disable Automatic Login Feature
Multimedia-focused Nero 2019 Released
Mouse and Keyboard Support for Xbox One Coming Soon
Apple Said to Shaves Cost from Displays in iPhones
GLOBALFOUNDRIES Delivering 8SW RF SOI Client Chips on 300mm Platform, Enhanced 14/12nm FinFET offerings
Qualcomm Says Apple Gave Modem Secrets to Intel
Active Discussions
Which of these DVD media are the best, most durable?
How to back up a PS2 DL game
Copy a protected DVD?
roxio issues with xp pro
Help make DVDInfoPro better with dvdinfomantis!!!
menu making
Optiarc AD-7260S review
cdrw trouble
 Home > News > General Computing > Faceboo...
Last 7 Days News : SU MO TU WE TH FR SA All News

Friday, September 14, 2018
Facebook Confirms Internal Silicon Team


Facebook has confirmed reports the social networking giant is hiring chip engineers and designing at least one ASIC.

Facebook "is absolutely bringing up a silicon team focused on working with silicon providers, and we have a chip we're building, but it's not our primary focus," said Jason Taylor, vice president of infrastructure at Facebook. The chip is "not the equivalent of [Google's] TPU" deep learning accelerator, he added, declining to provide further details on its focus or time frame.

The news came at the @Scale event in San Franscisco, where Facebook announced five chip companies will support Glow, an open-source, deep-learning compiler it backs.

Working with the estimated 50 companies designing AI accelerators is one focus for the new Facebook chip group. "There will be a lot of [accelerator] chips in the market. The big question is whether the workloads they are designed for are the important ones at the time" given it takes two years to field a new chip, Taylor said.

Glow as a generic compiler to let developers target any of the emerging deep-learning accelerators for inference in the cloud or at the edge of the network. It does not target client systems such as smartphones.

"We expect there will be hardware fragmentation [in inference accelerators]. Our work with Glow is to help machine-learning experts design neural nets and not have to do the work required to tune them to each unique chip, Taylor said.

"We know the fragmentation is coming because no one knows what combination of [hardware] resources [such as on-chip memory blocks and multiply-accumulate arrays] will win, so we'll let developers focus on the high-level graphs without hand coding for the specifics of hardware," he added.

Glow takes an AI graph produced by a framework such as TensorFlow or Caffe2 and renders it into byte code for hardware accelerators, Taylor explained. The compiler includes several tools including an instruction scheduler, a linear algebra optimizer, a memory allocator to generate efficient code for a chip's specific memory configuration and a CPU-based reference implementation for testing the accuracy of the hardware.

Cadence, Esperanto Technologies, Intel, Marvell and Qualcomm said they will support Glow on future chips.

Glow is a framework for deploying a neural network in production systems. Its input would be a graph created in a framework such as TensorFlow or Caffe2.

Nvidia's Tensor RT also takes in a graph from a framework and outputs Cuda code for its GPUs.

Facebook, Microsoft and others are backing ONNX, a standard way to express a graph with its weights. In December, the Khronos Group released NNEF, a hardware abstraction layer for deep-learning accelerators.



Previous
Next
Samsung Galaxy S10 Smartphone Said to Come in Three Versions, With Up to Five Cameras On Board        All News        SpaceX Signs Up First Private Passenger for Round-the-Moon Trip
IBC: Next Generation Maestro Real-time Graphics and Video Hardware Rendering Platform     General Computing News      SpaceX Signs Up First Private Passenger for Round-the-Moon Trip

Get RSS feed Easy Print E-Mail this Message

Related News
Microsoft Focuses on Security and Brings AI to the Masses at Ignite 2018
Airbnb to Comply with European Commission Demands, Facebook and Twitter Need to Do More
Samsung AI Forum Underlines the Importance of Unsupervised Learning
Facebook Launches Bug Bounty Program For Security Holes in Apps
Facebook Algorithms to Check Authenticity of Photos and Videos
Facebook, Google Face EU Fine if Extremist Content Stay Online For Over an Hour
Cisco Unveils Server for Artificial Intelligence and Machine Learning
Samsung Opens a New AI Center in New York City
Facebook to Invest $1 billion in Data center in Singapore
U.S Lawmakers Push Facebook and Twitter to Make Rules Clearer
Facebook Sues BlackBerry Over Voice-Messaging Tech
Facebook Expands Its Headquarters in Menlo Park

Most Popular News
 
Home | News | All News | Reviews | Articles | Guides | Download | Expert Area | Forum | Site Info
Site best viewed at 1024x768+ - CDRINFO.COM 1998-2018 - All rights reserved -
Privacy policy - Contact Us .