Peak double precision floating point performance
- N/A
Peak single precision floating point performance
- N/A
Number of accelerators per card
- 4
Cores
- 768 (192/GPU)
Memory size per board (GDDR5)
- 16GB (4GB/GPU)
Memory bandwidth for board (ECC off)
- N/A
Accelerator applications
- VDI and high performance graphics
Architecture features
- Features NVIDIA Kepler-based GPUs that allow hardware virtualization of the GPU so that multiple users can share a single GPU, improving user density without compromising performance. NVIDIA's low-latency remote display technology greatly improves the user experience by reducing the lag that users feel when interacting with their virtual machine. Also, the Kepler GPU includes a high-performance H.264 encoding engine capable of encoding simultaneous streams with superior quality.