NVIDIA V100 FHHL Full Specs

Summary

5,120 Shaders 1.29GHz

16GB HBM2829.4GB/s

Peak·FP32·FP16 13.21 TFLOPS

Form Factor PCIe Card

TDP 250W

Power Connectors 1x 8-Pin

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP16-16 Tensor FP16-32 FP64 Memory Bandwidth

V100 FHHL105.7 TFLOPSFP16-16 Tensor

x1

Top Score3.35 PFLOPS FP4 Tensor SparseDesktop1xGeForce RTX 5090

x31.72

Theoretical Performance

Clock Speed1290MHz UC·Base·Boost·OC

Peak OPS 105.7 TFLOPSFP16-16 Tensor

Tensor FP16-16 105.7 TFLOPS Tensor FP16-32 105.7 TFLOPS

FP32 13.21 TFLOPS

FP64 6.61 TFLOPS

Pixel Rate 165.1 GPixel/s

Texture Rate 412.8 GTexel/s

Core Config

Shaders 5,120 Shaders

TMUs 320 TMUs

ROPs 128 ROPs

Tensor Cores 640 T-Cores

SMs 80 SMs

Clocks

Base Clock 937MHz

Boost Clock 1.29GHz

Cache

L1 128KB/SM

L2 Cache 6MB shared

Memory

16GB HBM2

Memory Bus 4096-bit

Memory Speed 1.6GT/s

Memory Bandwidth 829.4GB/s

ECC No

Power & Thermals

TDP 250W

Video Output

Max Resolution 7680x4320

Refresh Rate Calculator 7680x4320 Resolution8K UHD Refresh Rate 30Hz

Adaptive Sync G-Sync FreeSync

DSC Not Supported

API Support

Shader Model 6.7

DirectX DirectX 12 Direct3D 12_1

OpenGL 4.6 OpenCL 3

CUDA 7 PureVideo HD VP9 VDPAU Feature Set I

Encoder

Encoder 3x NVENC 5

Codec AVC (H.264) HEVC (H.265)

Decoder

Decoder NVDEC 3

Codec MPEG-1 MPEG-2 MPEG-4 VC-1 VP9 AVC (H.264) HEVC (H.265)

Card

Form Factor PCIe Card

PCIe PCIe 3.0 x16 1-Slots

Height 111mm (4.37") Width 168mm (6.61") Depth 20mm (0.79")

Cooling Passive

Power Connectors 1x 8-Pin

Chip

Manufacturer NVIDIA

Chip Designer NVIDIA

Architecture Volta

Family Server

Branding

Codename NV140

Chip Variant GV100-400-A1

Market Segment Server

Release Date Mar 27, 2018

Fabrication

Foundry TSMC

Fabrication Node 12FFN

Die Size 815mm²

Transistor Count 21.1B

Transistor Density 25.89 MTr/mm²

Images