NVIDIA VGX GPUs
 
NVIDIA Kepler Telsa
NVIDIA Tesla K20
(Active Cooling)
NVIDIA Tesla K20
(Passive Cooling)
NVIDIA Tesla K10
(Standard Airflow)
NVIDIA Tesla K10
(Reverse Airflow)
NVIDIA Tesla M-Series
NVIDIA Tesla M2090
NVIDIA Tesla M2075
NVIDIA Tesla M2070
NVIDIA Tesla M2050
NVIDIA Tesla C-Series
NVIDIA Tesla C2075
NVIDIA Tesla C2070
NVIDIA Tesla C2050
SabrePC GPU Barebones
4U Superworkstation
2U Superserver
CPU/GPU Customized Solutions

NVIDIA® Tesla® K20 GPU Accelerators

Designed for HPC Performance and Reliability

Tesla K20 GPUs - The World’s Fastest Accelerators

Designed to be the performance leader in the broader supercomputing market, the Tesla K20 and K20X GPU Accelerators both feature a single GK110 Kepler GPU that includes the Dynamic Parallelism and Hyper-Q features. With more than one teraflop peak double precision performance, the Tesla K20 accelerators are ideal for the most aggressive high-performance computing workloads including climate and weather modeling, CFD, CAE, computational physics, biochemistry simulations, and computational finance.
Kepler architecture:

SMX: 3x More Performance Per Watt

The new SMX (Next Generation Streaming Multiprocessor) is an architectural innovation designed from the ground-up to deliver high efficiency performance. With SMX at its core, Tesla accelerators deliver the industry’s highest single and double precision performance- 3.95 teraflops and 1.31 teraflops respectively for Tesla K20X- at an unprecedented 93% computational efficiency.
SMX

Hyper-Q: Easy Speed-up for Legacy MPI Codes

Hyper-Q feature that enables multiple CPU cores to simultaneously utilize the CUDA cores on a single Tesla GPU. Plus it enables GPU acceleration of abroader set of popular algorithms, likeadaptive mesh refinement (AMR), fastmultipole method (FMM), and multigridmethods.This dramatically increases GPU utilization, slashes CPU idle times, and advances programmability—ideal for cluster applications that use MPI.

Dynamic Parallelism: Simplifying Parallel Programming

Dynamic Parallelism allows the GPU to operate more autonomously from the CPU by generating new work for itself at runtime, from inside a kernel. The concept is simple, but the impact is powerful: it can make programming easier, particularly for algorithms traditionally considered difficult such as divide-and-conquer problems.
Features and Benefits
• ECC memory error protection • System monitory features
• L1 and L2 caches • Asynchronous transfer withdual DMA engines
• Flexible programmingenvironment with broadsupport of programminglanguages and APIs
NVIDIA Telsa K20 Server/Workstation Solutions:
The NVIDIA Tesla K20/K20X GPU accelerator is a PCI Express, dual-slot full height (4.376 inches by 10.5 inches by 1.52 inches) form factor computing module comprising of a single GK110 GPU. The Tesla GPUs are designed for servers and offers up to 6 GB of GDDR5 on-board memory and supports PCI Express Gen2.
TESLA K20 Active
Key Features Applications  
K20 Active GPU
1.17 teraflops Peak double precision floating pointperformance
- Built for Workstations
- 1 x GK110, 2496 Cores
- 5 GB GDDR5
- 208 GBytes/sec Memory bandwidth
> CFD, CAE
> CAE (structural analysis)
> Molecular dynamics
> Financial Computing
> Computational Chemistry
K20 Active Product Page
 
TESLA K20 Passive
Key Features Applications  
K20 Passive GPU
1.17 teraflops Peak double precision floating pointperformance
- Built for Servers
- 1 x GK110, 2496 Cores
- 5 GB GDDR5
- 208 GBytes/sec Memory bandwidth
> CFD, CAE
> CAE (structural analysis)
> Molecular dynamics
> Financial Computing
> Computational Chemistry
K20 Passive Product Page
 
TESLA K20X Passive
Key Features Applications  
K20X Passive GPU
1.31 teraflops Peak double precision floating pointperformance
- Built for Servers
- 1 x GK110, 2688 Cores
- 6 GB GDDR5
- 250 GBytes/sec Memory bandwidth
> CFD, CAE
> CAE (structural analysis)
> Molecular dynamics
> Financial Computing
> Computational Chemistry
K20X Passive Product Page