Overview

QsNet
- Network cards
- Switches
QsTenG 10 GigE
- TG201 Switch
Software
- Drivers
- RMS

HPC Services
QsEm for UAVs
Overview

Software:

Eagle Release
Hawk release
Kernel Integration
Installation Guide
Software Roadmap
3rd Party software

Software Download


Documentation

QsNet Hardware
QsNet Software
QsTenG 10GigE

Supported Platforms

Platform Compliance

Reporting Problems:

GNATS tool

Other Resources:

FAQ
Training Courses
Case Studies
Performance Results
Benchmarks
Features & Benefits

Documents Library

Presentations
Image Gallery
Overview

Example Configurations

QsNetII Budgetary Request

Partners

TG201 Price List
TG201 Budgetary Request
10GE Partners

Terms and conditions
About Quadrics

Office Locations

Travel Information
Email Addresses

Quadrics Customers


Alliances


Our Green Policy
 
Home   Screensaver   Legal   Login
 
   
   
 

ASCI Q


ASCI Q Clusters at LANL

From the architectural point of view, the Q-machine can be described as a cluster of Shared Memory Multiprocessors (SMP), which is expected to the deliver a peak performance in excess of 30 TeraOps (with approximately 12000 processors). Multiple independent QsNet network rails will interconnect the SMPs through their I/O ports (PCI or PCI-X).
An interesting feature of QsNet is the native support for collective communication.
Experimental results conducted on 64-node AlphaServer cluster with 256 processors indicate that the time to complete the hardware-based barrier synchronization on the whole network is as low as 6 mus, with very good scalability. Good latency and scalability are also achieved with the software-based synchronization, which takes about 15 mus. With the broadcast, similar performance is achieved by the hardware- and software-based implementations, which can deliver messages of up to 256 bytes in 13 mus and can get a sustained asymptotic bandwidth of 288 Mbytes/sec on all the nodes. The hardware-based barrier is almost insensitive to the network congestion, with 93% of the synchronizations taking less than 20 when the network is flooded with a background traffic of unicast messages.


Further information available on ASCI Q

Los Alamos National Laboratory Advanced Simulation and Computing Program (ASC)

HP's supercomputers power TOP500 advanced simulation computing

The ASCI Q System: 30 TeraOPS Capability at Los Alamos National Laboratory

ASC Training information on Q

Advanced ASC Training information on Q

Scalable Collective Communication on the ASCI Q Machine

The Quadrics Network Whitepaper

Primeur: Quadrics Top in Top 500 and IDC Rating

Top500: ASCI Q - AlphaServer SC45, 1.25 GHz
Image courtesy of LANL

> Legal