NVIDIA Tesla K*0 2 x Kepler GK**0 *****************0 *4GB (*2GB per GPU) ***-bit GDDR5 PCI Express 3.0 x*6 GPU Accelerators for Servers

TESLA K*0
    ***2 CUDA Cores
    *4GB GDDR5
    PCI Express 3.0 x*6

Brand
    NVIDIA

Series
    Tesla K*0

Model
    *****************0

Interface

Interface
    PCI Express 3.0 x*6

Chipset

Chipset Manufacturer
    NVIDIA

GPU
    2 x Kepler GK**0

Core Clock
    **0MHz Core - Boostable to **6MHz

CUDA Cores
    ***2 (***6 per GPU)

Memory

Memory Clock
    *0 GHz

Memory Size
    *4GB (*2GB per GPU)

Memory Interface
    ***-bit

Memory Type
    GDDR5

Details

Cooler
    Passive Heatsink Cooling

Features

Features
    Accelerate your most demanding data analytics and scientific computing applications with NVIDIA Tesla GPU Accelerators. Based on the NVIDIA Kepler Architecture, Tesla accelerators are designed to deliver faster, more efficient compute performance.

    From energy exploration to machine learning, data scientists can crunch through petabytes of data with Tesla accelerators, up to *0x faster than with CPUs. For computational scientists, Tesla accelerators deliver the horsepower needed to run bigger simulations faster than ever.

    Tesla K*0 GPU Accelerator
    A dual GPU board that combines *4 GB of memory with blazing fast memory bandwidth and up to 2.*1 Tflops double precision performance with NVIDIA GPU Boost, the Tesla K*0 GPU is designed for the most demanding computational tasks. It's ideal for single and double precision workloads that not only require leading compute performance but also demands high data throughput.

    Peak double precision floating point performance:
    2.*1 Tflops (GPU Boost Clocks)
    1.*7 Tflops (Base Clocks)

    Peak single precision floating point performance:
    8.*4 Tflops (GPU Boost Clocks)
    5.6 Tflops (Base Clocks)

    Memory bandwidth (ECC off)**: **0 GB/sec (**0 GB/sec per GPU)

    **With ECC on, 6.*5% of the GPU memory is used for ECC bits. For example, 6 GB total memory yields 5.*5 GB of user available memory with ECC on.