GeForce GTX 580 and Tesla K20X - video card comparison

GeForce GTX 580

Tesla K20X

Architecture

Fermi (2010−2014)

Kepler (2012−2018)

GPU code name

GF110

GK110

Market segment

Desktop

Workstation

Release date

November 2010

November 2012

Bus support

PCI-E 2.0 x 16

-

Interface

PCIe 2.0 x16

PCIe 3.0 x16

Supplementary power connectors

One 6-pin and One 8-pin

1x 6-pin + 1x 8-pin

SLI options

+

-

Core clock speed

772 MHz

732 MHz

CUDA cores

512

-

Floating-point performance

1,581.1 gflops

3,935 gflops

Manufacturing process technology

40 nm

28 nm

Number of transistors

3,000 million

7,080 million

Pipelines / CUDA cores

512

2688

Power consumption (TDP)

244 Watt

235 Watt

Maximum GPU temperature

97 °C

-

Texture fill rate

49.4 billion/sec

164.0

Memory type

GDDR5

GDDR5

Maximum RAM amount

1536 MB

6 GB

Memory bus width

384 Bit

384 Bit

Memory clock speed

2004 MHz (4008 data rate)

5200 MHz

Memory bandwidth

192.4 GB/s

249.6 GB/s

Display Connectors

Mini HDMITwo Dual Link DVI

No outputs

Multi monitor support

+

-

HDMI

+

-

Maximum VGA resolution

2048x1536

-

Audio input for HDMI

Internal

-

DirectX

12 (11_0)

12 (11_0)

CUDA

+

3.5

OpenCL

1.1

1.2

OpenGL

4.2

4.6

Shader Model

5.1

5.1

Vulkan

+

1.1.126