NVIDIA GeForce RTX 4090 vs AMD Radeon RX 570

VS

NVIDIA GeForce RTX 4090 AMD Radeon RX 570

We compared two Desktop platform GPUs: 24GB VRAM GeForce RTX 4090 and 4GB VRAM Radeon RX 570 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA GeForce RTX 4090 's Advantages

Released 5 years and 5 months late

Boost Clock has increased by 103% (2520MHz vs 1244MHz)

More VRAM (24GB vs 4GB)

14336 additional rendering cores

AMD Radeon RX 570 's Advantages

Larger VRAM bandwidth (224.0TB/s vs 1.01TB/s)

Lower TDP (150W vs 450W)

Score

Benchmark

FP32 (float)

GeForce RTX 4090 +1520%

82.58 TFLOPS

Radeon RX 570

5.095 TFLOPS

3DMark Time Spy

GeForce RTX 4090 +846%

36549

Radeon RX 570

3860

Shadow of the Tomb Raider 2160p

GeForce RTX 4090 +927%

185

Radeon RX 570

18

Shadow of the Tomb Raider 1440p

GeForce RTX 4090 +723%

280

Radeon RX 570

34

Shadow of the Tomb Raider 1080p

GeForce RTX 4090 +484%

304

Radeon RX 570

52

Battlefield 5 2160p

GeForce RTX 4090 +588%

186

Radeon RX 570

27

Battlefield 5 1440p

GeForce RTX 4090 +298%

203

Radeon RX 570

51

Battlefield 5 1080p

GeForce RTX 4090 +208%

213

Radeon RX 570

69

GTA 5 2160p

GeForce RTX 4090 +456%

167

Radeon RX 570

30

GTA 5 1440p

GeForce RTX 4090 +224%

185

Radeon RX 570

57

GTA 5 1080p

GeForce RTX 4090 +86%

186

Radeon RX 570

100

GeForce RTX 4090

VS

Radeon RX 570

Graphics Card

Sep 2022

Release Date

Apr 2017

GeForce 40

Generation

Polaris

Desktop

Type

Desktop

PCIe 4.0 x16

Bus Interface

PCIe 3.0 x16

Clock Speeds

2235 MHz

Base Clock

1168 MHz

2520 MHz

Boost Clock

1244 MHz

1313 MHz

Memory Clock

1750 MHz

Memory

24GB

Memory Size

4GB

GDDR6X

Memory Type

GDDR5

384bit

Memory Bus

256bit

1.01TB/s

Bandwidth

224.0GB/s

Render Config

128

SM Count

-

Compute Units

32

16384

Shading Units

2048

512

TMUs

128

176

ROPs

32

512

Tensor Cores

-

128

RT Cores

-

128 KB (per SM)

L1 Cache

16 KB (per CU)

72 MB

L2 Cache

2 MB

Theoretical Performance

443.5 GPixel/s

Pixel Rate

39.81 GPixel/s

1290 GTexel/s

Texture Rate

159.2 GTexel/s

82.58 TFLOPS

FP16 (half)

5.095 TFLOPS

82.58 TFLOPS

FP32 (float)

5.095 TFLOPS

1290 GFLOPS

FP64 (double)

318.5 GFLOPS

Graphics Processor

AD102

GPU Name

Polaris 20

AD102-300-A1

GPU Variant

Polaris 20 XL (215-0910052)

Ada Lovelace

Architecture

GCN 4.0

TSMC

Foundry

GlobalFoundries

5 nm

Process Size

14 nm

76.3 billion

Transistors

5.7 billion

609 mm²

Die Size

232 mm²

Board Design

450W

TDP

150W

850 W

Suggested PSU

450 W

1x HDMI 2.1 3x DisplayPort 1.4a

Outputs

1x DVI 1x HDMI 2.0b 3x DisplayPort 1.4a

1x 16-pin

Power Connectors

1x 6-pin

Graphics Features

12 Ultimate (12_2)

DirectX

12 (12_0)

4.6

OpenGL

4.6

3.0

OpenCL

2.1

1.3

Vulkan

1.2

8.9

CUDA

-

6.7

Shader Model

6.4

Related GPU Comparisons

1

NVIDIA GeForce RTX 4090 vs NVIDIA A100 PCIe 80 GB

2

NVIDIA GeForce RTX 4090 vs NVIDIA RTX A6000

3

NVIDIA GeForce RTX 4090 vs NVIDIA Tesla V100 PCIe 32 GB

4

NVIDIA GeForce RTX 4080 SUPER vs NVIDIA GeForce RTX 4090

5

NVIDIA GeForce RTX 4090 vs NVIDIA RTX 6000 Ada

6

NVIDIA GeForce RTX 4090 vs NVIDIA H100 SXM5

7

NVIDIA Tesla T4 vs NVIDIA GeForce RTX 4090

8

NVIDIA GeForce RTX 4090 vs ATI Radeon HD 4670 X2

9

NVIDIA GeForce RTX 4090 vs ATI Radeon HD 4720

10

NVIDIA GeForce RTX 4090 vs NVIDIA GeForce 205 OEM