PNY NVIDIA® Tesla™ K20 Workstation Card

WHY CHOOSE A TESLA GPU?
DESIGNED FOR HPC PERFORMANCE AND RELIABILITY
The
NVIDIA® CUDA® parallel computing platform
is enabled on
GeForce®
,
Quadro®
, and
Tesla®
products. Whereas GeForce and Quadro are designed for consumer graphics and professional visualization, respectively, the Tesla product family is designed ground-up for parallel computing and programming and offers exclusive High performance computing features.
HIGHEST PERFORMANCE FOR HPC APPLICATIONS
Tesla GPUs are designed with exclusive features to maximize performance forsupercomputing professionals:
Full double precision floating point performance
1.17 TFlops on the Tesla K20 GPU
Higher double precision than consumer products
Faster PCIe communication
The only NVIDIA product with two DMA engines for bi-directional PCIe communication
Higher performance on technical applications with large data sets
Larger on-board memory (5 GB on the Tesla K20 GPU)
Faster communication with InfiniBand using NVIDIA
GPUDirect™
Special Linux patch, InfiniBand driver, and CUDA driver
Higher performance CUDA driver for Windows OS
TCC driver reduces CUDA kernel overhead and enables Windows Remote Desktop and Windows Services
Learn more about
exclusive software for Tesla products
.
LINPACK (HPL) PERFORMANCE
Double Precision, n = 72995
BUILT FOR DATA RELIABILITY
Computational professionals depend on mission critical applications to run reliably without data error. All Tesla GPUs undergo zero error tolerance testing in the most strenuous conditions for hundreds of times longer than any other NVIDIA products. Tesla GPU exclusive features include:
ECC protection for uncompromised data reliability
For memories inside the GPU and the external GDDR5 memory
Zero error tolerance stress testing
Stress tested in manufacturing for several days
Manufactured by NVIDIA and guaranteed to be of highest quality
Higher margin in memory and core clocks for added reliability
Enterprise level support
Three year warranty, higher priority bug resolutions and feature requests, and product lifecycle of 18-24 months
ISV Certification
HPC software vendors only certify software on Tesla products
 
BUILT FOR HPC SOLUTIONS
HPC customers have unique requirements. Only Tesla business unit provides products and solutions to meet these special needs:
Integrated OEM Systems
Innovative OEM servers, blades, and workstations designed specifically for Tesla products
Long-term supply and availability of Tesla products
18-24 month life-cycle availability
Data center warranty
3 year warranty from NVIDIA and OEM partners on Tesla products
Cluster management and GPU monitoring software
GPU temperature monitoring, fan speed, and power Exclusive access to GPUs in a cluster
HPC expertise in pre-sales and post-sales support
Total HPC solution expertise provided by CUDA tuning engineers, solution architects, and dedicated sales team.