GPU Comparison

A

AMD

RADEON

AMD Radeon HD 6970M

CORE STATE Blackcomb

VRAM 1024 MB

CLOCK SPEED —

TDP 75 W

BUS WIDTH 256 bit

ARCHITECTURE TeraScale 2

nm

PROCESS 40 nm

LAUNCH DATE 2011

VS

NVIDIA

GEFORCE

GeForce RTX 2080 SUPER

CORE STATE TU104

VRAM 8 GB

CLOCK SPEED 1815 MHz

TDP 250 W

BUS WIDTH 256 bit

ARCHITECTURE Turing

nm

PROCESS 12 nm

LAUNCH DATE 2019

PERFORMANCE BENCHMARKS

geekbench_opencl

1,262

114,190

3dmark_3dmark_steel_nomad_dx12

N/A

1,882

geekbench_vulkan

N/A

108,401

passmark_directx_10

N/A

140

passmark_directx_11

N/A

165

passmark_directx_12

N/A

75

passmark_directx_9

N/A

227

passmark_g2d

N/A

920

passmark_g3d

N/A

19,490

passmark_gpu_compute

N/A

8,290

DETAILED SPECIFICATIONS

SPECIFICATION

HD 6970M

RTX 2080 SUPER

Core Specs

Shading Units

960

3,072 +220.0%

Shaders

960

3,072 +220.0%

TMUs

48

192 +300.0%

ROPs

32

64 +100.0%

Compute Units

12

—

SM Count

—

48

Clocks

Base Clock

—

1650 MHz

Boost Clock

—

1815 MHz

GPU Clock

680 MHz

—

Memory Clock

900 MHz 3.6 Gbps effective

1937 MHz 15.5 Gbps effective

Memory

Memory Size

1024 MB

8 GB

VRAM (MB)

1,024

8,192 +700.0%

Memory Type

GDDR5

GDDR6

Memory Bus

256 bit

256 bit

Bandwidth

115.2 GB/s

495.9 GB/s

Cache

L1 Cache

8 KB (per CU)

64 KB (per SM)

L2 Cache

512 KB

4 MB

Performance

Pixel Rate

21.76 GPixel/s

116.2 GPixel/s

Texture Rate

32.64 GTexel/s

348.5 GTexel/s

FP32 (TFLOPS)

1,305.6 GFLOPS

11.15 TFLOPS

FP64 (TFLOPS)

—

348.5 GFLOPS (1:32)

FP16 (TFLOPS)

—

22.30 TFLOPS (2:1)

AI/RT

RT Cores

—

48

Tensor Cores

—

384

Power

TDP

75 W

250 W

TDP (W)

75

250 +233.3%

Suggested PSU

—

600 W

Power Connectors

None

1x 6-pin + 1x 8-pin

Architecture

Architecture

TeraScale 2

Turing

GPU Name

Blackcomb

TU104

Generation

Vancouver (HD 6900M)

GeForce 20

Process Size

40 nm

12 nm

Transistors

1,700 million

13,600 million

Die Size

212 mm²

545 mm²

Foundry

TSMC

TSMC

Density

8.0M / mm²

25.0M / mm²

API Support

DirectX

11.2 (11_0)

12 Ultimate (12_2)

OpenGL

4.4

4.6

Vulkan

—

1.4

OpenCL

1.2

3.0

CUDA

—

7.5

Shader Model

5.0

6.8

Physical

Slot Width

MXM Module

Dual-slot

Length

—

267 mm 10.5 inches

Height

—

116 mm 4.6 inches

Outputs

Portable Device Dependent

1x HDMI 2.03x DisplayPort 1.4a1x USB Type-C

Bus Interface

MXM-B (3.0)

PCIe 3.0 x16

Other

Launch Price

—

699 USD

Production

End-of-life

End-of-life

Predecessor

Manhattan

GeForce 10

Successor

London

GeForce 30

View Radeon HD 6970M Details View GeForce RTX 2080 SUPER Details