Report an Error

NVIDIA TU116B

Default
TU116B
Die Shot
Die Shot
Block Diagram
Block Diagram
SM Diagram
SM Diagram
NVIDIA's TU116B GPU uses the Turing architecture and is made using a 12 nm production process at TSMC. With a die size of 284 mm² and a transistor count of 6,600 million it is a medium-sized chip. TU116B supports DirectX 12 (Feature Level 12_1). For GPU compute applications, OpenCL version 3.0 and CUDA 7.5 can be used. It features 1536 shading units, 96 texture mapping units and Unknown ROPs.
Further reading: Turing Architecture Whitepaper

Graphics Processor

Released
Unknown
GPU Name
TU116B
Codename
NV168
Architecture
Turing
Foundry
TSMC
Process Type
12FFN FinFET
Process Size
12 nm
Transistors
6,600 million
Density
23.2M / mm²
Die Size
284 mm²
Package
BGA-2228
Package Size
37.5 mm × 37.5 mm

Graphics Features

DirectX
12 (12_1)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
7.5
Shader Model
6.7
WDDM
3.1
NVENC
7th Gen
NVDEC
4th Gen
PureVideo HD
VP10
VDPAU
Feature Set J

Render Config

Shading Units
1536
TMUs
96
ROPs
Unknown
SM Count
24
FP16 Units
3072
FP64 Units
48
SFUs
384
TPCs
12
GPCs
3
Tex L1 Cache
32 KB per SM

All Turing GPUs

NVIDIA GPU Architecture History

TU116B GPU Notes

NVENC: 7th Gen
NVDEC: 4th Gen
PureVideo HD: VP10
VDPAU: Feature Set J
May 15th, 2024 23:41 EDT change timezone

Latest GPU Drivers

New Forum Posts

Popular Reviews

Controversial News Posts