Report an Error

NVIDIA G92B

Default
G92B
G92-159-B1
G92-159-B1
G92-168-B1
G92-168-B1
G92-280-B1
G92-280-B1
G92-420-B1
G92-420-B1
G92-421-B1
G92-421-B1
G92-426-B1
G92-426-B1
G92-428-B1
G92-428-B1
N10E-GLM3-B2
N10E-GLM3-B2
N10E-GTX1-B1
N10E-GTX1-B1
G92 BGA
G92 BGA
Die Shot
Die Shot
TPC Diagram
TPC Diagram
NVIDIA's G92B GPU uses the Tesla architecture and is made using a 55 nm production process at TSMC. With a die size of 260 mm² and a transistor count of 754 million it is a medium-sized chip. G92B supports DirectX 11.1 (Feature Level 10_0). For GPU compute applications, OpenCL version 1.1 and CUDA 1.1 can be used. It features 128 shading units, 64 texture mapping units and 16 ROPs.
Further reading: Tesla Architecture Whitepaper

Graphics Processor

Released
Jul 21st, 2008
GPU Name
G92B
Codename
NV92
Architecture
Tesla
Foundry
TSMC
Process Size
55 nm
Transistors
754 million
Density
2.9M / mm²
Die Size
260 mm²
Package
FCBGA-1148

Graphics Features

DirectX
11.1 (10_0)
OpenGL
3.3
OpenCL
1.1
Vulkan
N/A
CUDA
1.1
Shader Model
4.0
WDDM
1.2
PureVideo HD
VP2
VDPAU
Feature Set A

Render Config

Shading Units
128
TMUs
64
ROPs
16
SM Count
16
SFUs
32
TPCs
8
Tex L1 Cache
16 KB per TPC
L2 Cache
64 KB
Max. TDP
150 W

All Tesla GPUs

NVIDIA GPU Architecture History

Graphics cards using the NVIDIA G92B GPU

Name Chip Memory Shaders TMUs ROPs GPU Clock Memory Clock
G92-420-B1 512 MB 128 64 16 738 MHz 1100 MHz
G92-428-B1 1024 MB 128 64 16 702 MHz 1000 MHz
G92-240-B1 1024 MB 112 56 16 675 MHz 1100 MHz
N10E-GTX1-B1 1024 MB 128 64 16 600 MHz 1000 MHz
G92-159-B1 1536 MB 96 48 12 500 MHz 500 MHz
N10E-GLM3-B2 1024 MB 128 64 16 675 MHz 1000 MHz
N10E-GLM-B2 1024 MB 96 48 16 600 MHz 1000 MHz
G92-168-B1 256 MB 96 48 16 500 MHz 510 MHz
G92-280-B1 512 MB 112 56 16 600 MHz 900 MHz
G92-426-B1 1024 MB 128 64 16 675 MHz 1008 MHz

G92B GPU Notes

PureVideo HD: VP2
VDPAU: Feature Set A
Apr 26th, 2024 23:06 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts