Report an Error

NVIDIA GK20A

Default
GK20A
Block Diagram
Block Diagram
SMX Diagram
SMX Diagram
NVIDIA's GK20A GPU uses the Kepler 2.0 architecture and is made using a 28 nm production process at TSMC. GK20A supports DirectX 12 (Feature Level 11_0). For GPU compute applications, OpenCL version N/A and CUDA 3.2 can be used. It features 192 shading units, 8 texture mapping units and 4 ROPs.
Further reading: Tegra K1 Architecture Whitepaper

Graphics Processor

GPU Name
GK20A
Codename
NVEA
Architecture
Kepler 2.0
Foundry
TSMC
Process Size
28 nm
Transistors
unknown
Die Size
unknown
Released
Oct 15th, 2014

Graphics Features

DirectX
12 (11_0)
OpenGL
ES 3.1
OpenCL
N/A
Vulkan
1.1
CUDA
3.2
Shader Model
5.1
PureVideo HD
VP5
VDPAU
Feature Set D

Render Config

Shading Units
192
TMUs
8
ROPs
4
SMX Count
1
GPCs
1
Tex L1 Cache
48 KB per SMX
L1 Cache
16 KB per SMX
L2 Cache
128 KB
Max. TDP
8 W
SFUs
32

All Kepler 2.0 GPUs

NVIDIA GPU Architecture History

Graphics cards using the NVIDIA GK20A GPU

Name Chip Memory Shaders TMUs ROPs Base Clock Boost Clock Memory Clock
NVIDIA Jetson TK1 GPU System Shared 192 8 4 756 MHz 951 MHz System Shared

GK20A GPU Notes

L1 Cache is configurable from 16 KB up to 48 KB per SMX
Jul 5th, 2022 02:26 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts