NVIDIA Tesla K80 24GB GDDR5 Graphics GPU Server Accelerator 900-22080-0000-000 For Sale
NVIDIA Tesla K80 24GB GDDR5 Graphics GPU Server Accelerator 900-22080-0000-000 :
Accelerate your most demanding data analytics and scientific computing applications with NVIDIA Tesla Referral GPU Accelerators. Based on the NVIDIA Kepler Architecture, Tesla Referral 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 Referral accelerators, up to 10x faster than with CPUs. For computational scientists, Tesla Referral accelerators deliver the horsepower needed to run bigger simulations faster than ever.
Tesla Referral K80 GPU Accelerator
A dual GPU board that combines 24 GB of memory with blazing fast memory bandwidth and up to 2.91 Tflops double precision performance with NVIDIA GPU Boost, the Tesla Referral K80 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:
2.91 Tflops (GPU Boost Clocks)
1.87 Tflops (Base Clocks)
Peak single precision floating point performance:
8.74 Tflops (GPU Boost Clocks)
5.6 Tflops (Base Clocks)
Memory bandwidth (ECC off)**: 480 GB/sec (240 GB/sec per GPU)
**With ECC on, 6.25% of the GPU memory is used for ECC bits. For example, 6 GB total memory yields 5.25 GB of user available memory with ECC on.