Nvidia Tesla K20 GK110 5GB 320-bit GDDR5 PCI Express 2.0 Graphic Card
The nVIDIA Tesla Kepler K20 GK110 GPU Accelerator for Server from nVIDIA is based on the nVIDIA Kepler compute architecture and powered by CUDA. It includes innovative technologies like Dynamic Parallelism and Hyper-Q that boost performance as well as power efficiency and deliver record application speeds for seismic processing, biochemistry simulations, weather and climate modeling, image, video and signal processing and more.
- SMX (Streaming Multiprocessor)
- Telsa K20 features SMX technology which delivers up to three times more performance per watt compared to the SM in Fermi. It also delivers one petaflop of computing in just ten server racks.
- Dynamic Parallelism
- Dynamic Parallelism capability enables GPU threads to automatically spawn new threads. By adapting to the data without going back to the CPU, it greatly simplifies parallel programming. Additionally, it enables GPU acceleration of a broader set of popular algorithms like adaptive mesh refinement (AMR), fast multi-pole method (FMM) and multi-grid methods.
- Hyper-Q Technology
- The Hyper-Q feature enables multiple CPU cores to simultaneously utilize the CUDA cores on a single Kepler GPU. This dramatically increases GPU utilization, slashes CPU idle times and advances programmability-ideal for cluster applications that use MPI.
- ECC Memory Error Protection
- ECC memory meets the critical requirement for computing accuracy and reliability in data centers and super-computing centers. Both external and internal memories are ECC protected in Tesla K20.
- System Monitoring Feature
- Integrates the GPU subsystem with the host system's monitoring and management capabilities such as IPMI or OEM-proprietary tools. IT staff can now manage the GPU processors in the computing system using widely used cluster/grid management solutions.
- L1 and L2 Caches
- Accelerates algorithms such as physics solvers, ray-tracing and sparse matrix multiplication where data addresses are not known in advance.
- Asynchronous Transfer with Dual DMA Engines
- Turbo-charges system performance by transferring data over the PCIe bus while the computing cores are executing other data.
- Flexible Programming Environment with Broad Support for Programming Languages and APIs
- Choose OpenACC, CUDA toolkits for C, C++ or FORTRAN to express application parallelism and take advantage of the innovative Kepler architecture.
- GPU Computing Applications
- With more than one teraflop peak double precision performance, the GPU accelerator is ideal for the most aggressive high-performance computing workloads including climate and weather modeling, CFD, CAE, computational physics, biochemistry simulations, and computational finance.
NVIDIA Tesla K20 GK110 Specifications
|Interface||PCIe Gen2 ×16|
|Double Precision Floating Point||1.17 Teraflops|
|Single Precision Floating Point||3.52 Teraflops|
|Memory Size||5 GB|
|Memory Bandwidth||208 Gb/s (ECC off)|
|Memory Clock||2.6 GHz|
|Memory Configurations||20 pieces of 64M ×16|
|Power Connectors||(1) 8-pin PCIe and (1) 6-pin PCIe|
|Board Power||225 W|
|Idle Power||25 W|
|Applications||CFD, CAE, financial computing, computational chemistry and physics, data analytics, satellite imaging, weather modeling|
|System||Server and Workstations|
|OS Supported||Windows Server 2012, 2008 R2 and 2008 64-bit (all editions)|
Linux 64-bitRHEL 5.4 Server
Ubuntu 9.10 Server
RHEL 4.8 Server
|Package Weight||2.35 lb|
|Box Dimensions (LxWxH)||11.9 x 7.0 x 3.0"|
Part numbers: 90Y2346, 900-22081-0412-000, 699-22081-0208-212, 666545547.