GTC ON-DEMAND

 
SEARCH SESSIONS
SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Presentation
Media
Abstract:
We'll introduce the first use of tensor cores on NVIDIA's Volta architecture in lattice quantum chromodynamics (QCD), within the framework of QUDA. Lattice QCD remains the only reliable first-principle approach to study QCD, the theory that describes how different types of matter we see every day interact with each other. We'll provide brief introduction to QCD. The Warp Matrix Multiply and Accumulate API is used to speed up the large sparse matrix operations in Monte Carlo sampling of QCD. As an example of our work, we show how the overwhelming computation power of tensor cores could be used in high performance computing.
We'll introduce the first use of tensor cores on NVIDIA's Volta architecture in lattice quantum chromodynamics (QCD), within the framework of QUDA. Lattice QCD remains the only reliable first-principle approach to study QCD, the theory that describes how different types of matter we see every day interact with each other. We'll provide brief introduction to QCD. The Warp Matrix Multiply and Accumulate API is used to speed up the large sparse matrix operations in Monte Carlo sampling of QCD. As an example of our work, we show how the overwhelming computation power of tensor cores could be used in high performance computing.  Back
 
Topics:
Computational Physics
Type:
Talk
Event:
GTC Silicon Valley
Year:
2019
Session ID:
S9330
Streaming:
Download:
Share:
 
 
Previous
  • Amazon Web Services
  • IBM
  • Cisco
  • Dell EMC
  • Hewlett Packard Enterprise
  • Inspur
  • Lenovo
  • SenseTime
  • Supermicro Computers
  • Synnex
  • Autodesk
  • HP
  • Linear Technology
  • MSI Computer Corp.
  • OPTIS
  • PNY
  • SK Hynix
  • vmware
  • Abaco Systems
  • Acceleware Ltd.
  • ASUSTeK COMPUTER INC
  • Cray Inc.
  • Exxact Corporation
  • Flanders - Belgium
  • Google Cloud
  • HTC VIVE
  • Liqid
  • MapD
  • Penguin Computing
  • SAP
  • Sugon
  • Twitter
Next