Appro and NVIDIA® GPU Supercomputing Solutions
 |
|
|
| Appro
Supercomputing Solutions |
|
Based on the massively parallel CUDA GPU computing architecture, the Tesla M2090 GPU Computing Module features many "must have" HPC capabilities including:
 512 computing cores
665 gigaflops of double precision performance
ECC memory for uncompromised accuracy and reliability
An L1/L2 cache for improved bandwidth and data sharing |
Appro Xtreme-X™ Supercomputer
Designed for terascale and petascale configurations, the Xtreme-X combines CPU/GPU processing or accelerator configuration technology options per node. It offers best performance per dollar for many applications and excellent memory capacity per FLOP. The system architecture is based on a Scalable Unit cluster building block that is fully optimized and ready to be managed as a tightly integrated system.
This is the ideal design for applications that are highly parallel, addressing a rapidly growing number of accelerator-optimized applications with many simultaneous users and applications.
|
Appro GreenBlade™ System
A modular, performance-optimized building block solutions that offers a CPU and GPU combination in a 5U form factor that supports 5 dual CPU server blades with 5 GPU expansion blades delivering up to 5,120 GPU cores per system.
|
Appro Rackmount
Hybrid Servers
Integrates 2 CPUs and 4 GPUs based on NVIDIA Tesla M2090 cards in one server delivering outstanding performance, density, and flexibility with a variety of configuration options.
|
|
|
|
|
|
|
|
Videos/Webcasts