GeForce GTX 1050 and GeForce 8800 GTS 640 - video card comparison

GeForce GTX 1050

GeForce 8800 GTS 640

Architecture

Pascal (2016−2021)

Tesla (2006−2010)

GPU code name

N17P-G1

G80

Market segment

Desktop

Desktop

Release date

October 2016

November 2006

Bus support

PCIe 3.0

-

Interface

PCIe 3.0 x16

PCIe 1.0 x16

Recommended system power (PSU)

300 Watt

-

Supplementary power connectors

None

1x 6-pin

SLI

-

-

SLI options

-

-

Boost clock speed

1392 MHz

-

Core clock speed

1290 MHz

513 MHz

CUDA cores

640

-

Floating-point performance

1,862 gflops

228.1 gflops

Manufacturing process technology

14 nm

90 nm

Number of transistors

3,300 million

681 million

Pipelines / CUDA cores

640

96

Power consumption (TDP)

75 Watt

143 Watt

Maximum GPU temperature

97 °C

-

Texture fill rate

58.20

24.62

Memory type

GDDR5

GDDR3

Maximum RAM amount

2 GB

640 MB

Memory bus width

128 Bit

320 Bit

Memory clock speed

7008 MHz

1584 MHz

Memory bandwidth

112 GB/s

63.36 GB/s

Shared memory

-

-

Display Connectors

DP 1.4, HDMI 2.0b, Dual Link-DVI

2x DVI, 1x S-Video

Multi monitor support

+

-

HDMI

+

-

HDCP

2.2

-

G-SYNC support

+

-

DirectX

12 (12_1)

11.1 (10_0)

CUDA

+

+

OpenCL

1.2

1.1

OpenGL

4.5

3.3

Shader Model

6.4

4.0

Vulkan

1.2.131

N/A

Ansel

+

-

GameStream

+

-

GPU Boost

3.0

-

VR Ready

+

-