GPUDatacenterReleased May 10, 2017

NVIDIA Tesla V100 SXM2 16GB

16 GB HBM2 · 4096-bit · 5,120 cores

The SXM2 module version of NVIDIA's Volta data center accelerator, the product that introduced Tensor Cores and became the workhorse of HPC and AI training clusters in the late 2010s. Mounted directly on the system board rather than in a PCIe slot, it links to neighbouring GPUs over NVLink so that a server can pool eight accelerators, and as a compute-only product it has no display outputs. Announced at GTC in May 2017; a 32 GB version followed the next year.

General

Manufacturer: NVIDIA
Model: Tesla V100 SXM2 16GB
Segment: Datacenter
GPU chip: GV100
Architecture: Volta
Release date: May 10, 2017
Price: Search on Amazon

Memory

Memory size: 16 GB
Memory type: HBM2
Bus width: 4096-bit
Bandwidth: 900 GB/s
Memory clock: 876 MHz

Clocks & silicon

GPU clock: 1,312 MHz
Boost clock: 1,530 MHz
Shader units: 5,120 CUDA Cores
Tensor / AI cores: 640
RT cores: —
Transistors: 21.1 billion
Technology (nm): 12 nm
TSMC 12 nm FFN
TDP / TBP: 300 W

Interface & APIs

Bus interface: SXM2
SLI / multi-GPU: NVLink 2.0 (300 GB/s)
DirectX: N/A (compute-only)
OpenGL: N/A (compute-only)
Vulkan: N/A (compute-only)
Other APIs: CUDA (Compute Capability 7.0), OpenCL 3.0, DirectCompute, OpenACC

AI support

Precisions: FP8FP16BF16INT8INT4TF32FP64
AI accelerator: 1st Gen Tensor Cores (640)
Peak AI TOPS: —
Notes: First-generation Tensor Cores do FP16 multiply with FP32 accumulate for up to 125 TFLOPS of deep learning throughput. FP64 runs at half rate (7.8 TFLOPS) and FP32 at 15.7 TFLOPS. Volta has no BFLOAT16, TF32, FP8 or structured sparsity.

All NVIDIA GPUs →

Datacenter gpus from NVIDIA announced around the same time as the NVIDIA Tesla V100 SXM2 16GB. Add any of them to your compare list to see the specs side by side.

gpu