GeForce GTX 1070 Ti and Tesla A100 - video card comparison

GeForce GTX 1070 Ti

Tesla A100

Architecture

Pascal (2016−2021)

Ampere (2020−2022)

GPU code name

Pascal GP104

GA100

Market segment

Desktop

Workstation

Release date

November 2017

-

Interface

PCIe 3.0 x16

PCIe 4.0 x16

Supplementary power connectors

1x 8-pin

None

Boost clock speed

1683 MHz

-

Core clock speed

1607 MHz

1110 MHz

Floating-point performance

8,186 gflops

-

Manufacturing process technology

16 nm

7 nm

Number of transistors

7,200 million

38,000 million

Pipelines / CUDA cores

2432

7936

Power consumption (TDP)

180 Watt

260 Watt

Texture fill rate

255.8

550.6

Memory type

GDDR5

HBM2e

Maximum RAM amount

8 GB

32 GB

Memory bus width

256 Bit

4096 Bit

Memory clock speed

8000 MHz

2400 MHz

Memory bandwidth

256.3 GB/s

1,229 GB/s

Shared memory

-

-

Display Connectors

1x DVI, 1x HDMI, 3x DisplayPort

No outputs

HDMI

+

-

G-SYNC support

+

-

DirectX

12 (12_1)

12 (12_1)

CUDA

6.1

-

OpenCL

1.2

-

OpenGL

4.6

4.6

Shader Model

6.4

-

Vulkan

1.2.131

-

VR Ready

+

-