Report an Error

NVIDIA GV100

Default
GV100
GV100-400-A1
GV100-400-A1
Die Shot
Die Shot
Block Diagram
Block Diagram
SM Diagram
SM Diagram
NVIDIA's GV100 GPU uses the Volta architecture and is made using a 12 nm production process at TSMC. With a die size of 815 mm² and a transistor count of 21,100 million it is a very big chip. GV100 supports DirectX 12.0 (Feature Level 12_1). It features 5120 shading units, 320 texture mapping units and 128 ROPs. Also included are 640 tensor cores which help improve the speed of machine learning applications.
Further reading: GV100 Architecture Whitepaper

Graphics Processor

GPU Name
GV100
Codename
NV140
Architecture
Volta
Foundry
TSMC
Process Size
12 nm
Transistors
21,100 million
Density
25.9M / mm²
Die Size
815 mm²
Released
Jun 21st, 2017

Graphics Features

DirectX
12.0 (12_1)
OpenGL
4.6
OpenCL
1.2
Vulkan
1.1.122
CUDA
7.0
Shader Model
6.4
PureVideo HD
VP9
VDPAU
Feature Set I

Render Config

Shading Units
5120
TMUs
320
ROPs
128
SM Count
80
SFUs
1280
TPCs
40
GPCs
6
Tensor Cores
640
L1 Cache
128 KB per SM
L2 Cache
6144 KB
Max. TDP
300 W

All Volta GPUs

Graphics cards using the NVIDIA GV100 GPU

Name Chip Memory Shaders TMUs ROPs Base Clock Boost Clock Memory Clock
NVIDIA Tesla V100 PCIe 16 GB 16 GB 5120 320 128 1246 MHz 1380 MHz 876 MHz
NVIDIA Tesla V100 SXM2 16 GB 16 GB 5120 320 128 1312 MHz 1530 MHz 876 MHz
NVIDIA TITAN V GV100-400-A1 12 GB 5120 320 96 1200 MHz 1455 MHz 848 MHz
NVIDIA Quadro GV100 32 GB 5120 320 128 1132 MHz 1627 MHz 848 MHz
NVIDIA Tesla V100 PCIe 32 GB 32 GB 5120 320 128 1230 MHz 1380 MHz 876 MHz
NVIDIA Tesla V100 SXM2 32 GB 32 GB 5120 320 128 1290 MHz 1530 MHz 876 MHz
NVIDIA Tesla V100 DGXS 32 GB 5120 320 128 1297 MHz 1530 MHz 876 MHz
NVIDIA Tesla V100 FHHL 16 GB 5120 320 128 937 MHz 1290 MHz 876 MHz
NVIDIA TITAN V CEO Edition 32 GB 5120 320 128 1200 MHz 1455 MHz 848 MHz