AMD Radeon HD 6870 vs NVIDIA GeForce RTX 4090

GPU Specs Compare

G

AMD Radeon HD 6870

AMD 2010-10
G

NVIDIA GeForce RTX 4090

NVIDIA 2022-09

Graphics Card

Release Date
Oct 2010
Sep 2022
Generation
Northern Islands
GeForce 40
Type
Desktop
Desktop
Bus Interface
PCIe 2.0 x16
PCIe 4.0 x16

Clock Speeds

Memory Clock
1050 MHz
1313 MHz
Base Clock
-
2235 MHz
Boost Clock
-
2520 MHz

Memory

Memory Size
1024MB
24GB
Memory Type
GDDR5
GDDR6X
Memory Bus
256bit
384bit
Bandwidth
134.4GB/s
1.01TB/s

Render Config

Compute Units
14
-
Shading Units
1120
16384
TMUs
56
512
ROPs
32
176
L1 Cache
8 KB (per CU)
128 KB (per SM)
L2 Cache
512 KB
72 MB
SM Count
-
128
Tensor Cores
-
512
RT Cores
-
128

Theoretical Performance

Pixel Rate
28.80 GPixel/s
443.5 GPixel/s
Texture Rate
50.40 GTexel/s
1290.2 GTexel/s
FP32 (float)
2.016 TFLOPS
82.58 TFLOPS
FP16 (half)
-
82.58 TFLOPS
FP64 (double)
-
1290.2 GFLOPS

Graphics Processor

GPU Name
Barts
AD102
GPU Variant
Barts XT(215-0798000)
AD102-300-A1
Architecture
TeraScale 2
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
40 nm
5 nm
Transistors
1.7 billion
76.3 billion
Die Size
255 mm²
609 mm²

Board Design

TDP
151W
450W
Suggested PSU
450 W
850 W
Outputs
2x DVI1x HDMI 1.3a2x mini-DisplayPort 1.1
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
2x 6-pin
1x 16-pin

Graphics Features

DirectX
11.2 (11_0)
12 Ultimate (12_2)
OpenGL
4.4
4.6
OpenCL
1.2
3.0
Vulkan
N/A
1.4
Shader Model
5.0
6.8
CUDA
-
8.9