GeForce GT 430 and Data Center GPU Max Subsystem - video card comparison

GeForce GT 430

Data Center GPU Max Subsystem

Architecture

Fermi (2010−2014)

Generation 12.5 (2021−2022)

GPU code name

GF108

Ponte Vecchio

Market segment

Desktop

Release date

October 2010

January 2023

Bus support

PCI-E 2.0 x 16

Interface

PCIe 2.0 x16

PCIe 5.0 x16

Supplementary power connectors

None

1x 16-pin

Boost clock speed

1600 MHz

Core clock speed

700 MHz

CUDA cores per GPU

Floating-point performance

268.8 gflops

Manufacturing process technology

40 nm

10 nm

Number of transistors

585 million

100,000 million

Pipelines / CUDA cores

16384

Power consumption (TDP)

49 Watt

2400 Watt

Maximum GPU temperature

98 °C

Texture fill rate

11.2 billion/sec

1,638

Memory type

GDDR3

HBM2e

Maximum RAM amount

1 GB

128 GB

Memory bus width

128 Bit

8192 Bit

Memory clock speed

800 - 900 MHz (1600 - 1800 data rate)

3.1 GB/s

Memory bandwidth

25.6 - 28.8 GB/s

3,205 GB/s

Display Connectors

HDMIVGA (optional)Mini HDMIDual Link DVI

No outputs

HDMI

Maximum VGA resolution

2048x1536

Audio input for HDMI

Internal

DirectX

12 (11_0)

12 (12_1)

CUDA

OpenCL

1.1

3.0

OpenGL

4.2

4.6

Shader Model

5.1

6.6

Vulkan

N/A