GPUDatacenterReleased Mar 24, 2017

NVIDIA Tesla P6

16 GB GDDR5 · 256-bit · 2,048 cores

The Tesla P6 is the blade-server member of NVIDIA's Pascal virtualization line, built on an MXM 3.1 Type B module so it can fit the dense chassis that have no room for a PCIe card. A GP104 GPU provides 2,048 CUDA cores and 16 GB of GDDR5 on a 256-bit interface for 192 GB/s, clocked at 1,012 MHz base and 1,506 MHz boost within a 90 W limit that system builders can drop to 70 W. It was aimed at NVIDIA vGPU deployments serving virtual desktops and graphics workloads from blade hardware.

General

Manufacturer: NVIDIA
Model: Tesla P6
Segment: Datacenter
GPU chip: GP104
Architecture: Pascal
Release date: Mar 24, 2017
Price: Search on Amazon

Memory

Memory size: 16 GB
Memory type: GDDR5
Bus width: 256-bit
Bandwidth: 192.2 GB/s
Memory clock: 1,502 MHz

Clocks & silicon

GPU clock: 1,012 MHz
Boost clock: 1,506 MHz
Shader units: 2,048 CUDA Cores
Tensor / AI cores: —
RT cores: —
Transistors: 7.2 billion
Technology (nm): 16 nm
TSMC 16 nm FinFET
TDP / TBP: 90 W

Interface & APIs

Bus interface: MXM 3.1 Type B
SLI / multi-GPU: —
DirectX: 12 (12_1)
OpenGL: 4.6
Vulkan: 1.3
Other APIs: CUDA Compute Capability 6.1, OpenCL 3.0

AI support

Precisions: FP8FP16BF16INT8INT4TF32FP64
AI accelerator: None (no matrix units)
Peak AI TOPS: —
Notes: No matrix or tensor hardware. Pascal GP104 adds DP4A 8-bit integer dot-product instructions for inference, but NVIDIA publishes no INT8 rating for this module.

All NVIDIA GPUs →

Datacenter gpus from NVIDIA announced around the same time as the NVIDIA Tesla P6. Add any of them to your compare list to see the specs side by side.

gpu