Achieve far more results with far fewer processors

A Truly Scalable Solution

Our scalable network allows any number of nodes to be plugged into the switch, and our systems deliver huge performance improvements to the Hard Problems – difficult research the rest of the market is leaving behind. Our systems allow better performance for applications that need better data communications. For equal performance on a specific hard problem, our initial systems require less space and represent a 90% savings in power consumption. A Data Vortex system of equal size has a 32-100x performance improvement over a comparable system with the same number of x86 cores.

 


 

Graph 500 Breadth First Search

null

Source of Graph 500 performance data of other systems


Giga Updates Per Second (GUPS)

Data Vortex White Paper: “HPCC Random Access Benchmark Excels on Data Vortex”


 GFFT System Performance Comparison

3 GFFT System Performance Comparison - Finalized

*See last slide on this page for detailed data                              Source of GFFT performance data of other systems

 


 

GFFT GFLOPs per CORE

DV GFFT GFLOPs per CORE

*See last slide on this page for detailed data                              Source of GFFT performance data of other systems

 


 

GFFT GFLOPs per KW

DV GFFT GFLOPs per KW

*See last slide on this page for detailed data                              Source of GFFT performance data of other systems

 


 

Infiniband vs. Data Vortex Barrier Sync Times

Infiniband vs Data Vortex Barrier Sync Times

 


 

3D FFT Performance Comparison

DV 3D FFT Performance Comparison

Source of Jaguar data

 


 

Single port ping-pong BW each direction (packets/sec per port)

DV single port ping-pong bandwidth

Source of IB performance data

 


 

HPCC Global FFT Detailed Data

DV HPCC Global FFT Detailed Data