GeForce GTX 650 and Tesla M2070 - video card comparison

GeForce GTX 650

Tesla M2070

Architecture

Kepler (2012−2018)

Fermi (2010−2014)

GPU code name

GK107

GF100

Market segment

Desktop

Workstation

Release date

September 2012

July 2011

Bus support

PCI Express 3.0

Interface

PCIe 3.0 x16

PCIe 2.0 x16

Supplementary power connectors

One 6-pin

1x 6-pin + 1x 8-pin

Core clock speed

1058 MHz

574 MHz

CUDA cores

384

Floating-point performance

812.5 gflops

1,030.4 gflops

Manufacturing process technology

28 nm

40 nm

Number of transistors

1,270 million

3,100 million

Pipelines / CUDA cores

384

448

Power consumption (TDP)

64 Watt

225 Watt

Texture fill rate

33.9 billion/sec

32.14

Memory type

GDDR5

Maximum RAM amount

2 GB

6 GB

Memory bus width

128-bit GDDR5

384 Bit

Memory clock speed

5.0 GB/s

3132 MHz

Memory bandwidth

80.0 GB/s

150.3 GB/s

Display Connectors

One Dual Link DVI-I, One Dual Link DVI-D, One Mini HDMI

No outputs

Multi monitor support

4 displays

HDMI

HDCP

Maximum VGA resolution

2048x1536

Audio input for HDMI

Internal

DirectX

12 (11_0)

CUDA

2.0

OpenCL

1.2

1.1

OpenGL

4.3

4.6

Shader Model

5.1

Vulkan

1.1.126

N/A

3D Blu-Ray

3D Gaming

3D Vision