AMD Radeon RX 580 vs RX 570

We compared two discrete desktop gaming GPUs: the Radeon RX 580 8 GB with 2304 shaders against the RX 570 4 GB that utilizes 2048 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.

Review

General comparison of performance in games, applications, power efficiency, and other metrics
Gaming
Performance in DirectX, OpenCL, and Vulkan games
15
12
Workstation
Perf. in 3D modeling, video editing and rendering apps
24
22
AI/ML
Capabilities for machine learning and AI-related tasks
14
12
Energy Efficiency
Power consumption efficiency in different scenarios
24
32
NanoReview Final Score
Overall video card score
18
16

Value for money (Beta)

We use average GPU prices from all manufacturers by default. Enter the current price of a specific card for better accuracy.
Currency
8 GB GDDR5
VS
4 GB GDDR5
48.2
(Average)
Value Index
21.5
(Mediocre)

Key differences

Key distinctions and advantages of RX 570 over RX 580
Reasons to consider the Radeon RX 580
  • Performs slightly better (up to 13%) in 3DMark Steel Nomad Lite
  • Shows 23% higher average frame rate in modern games at QHD resolution – 27 vs 22 FPS
  • 22% higher maximum theoretical performance (6.2 vs 5.1 TFLOPS)
  • Includes 4 GB more video memory

Gaming Performance

Frame rate comparison across popular AAA titles at different resolutions
GPU
vs

Games

FPS Table
Forza Horizon 5
76
39
31
17
67
34
28
15
The Witcher 3
50
41
22
12
42
37
19
12
Counter-Strike 2
74
55
38
15
64
45
29
13
Far Cry 6
59
49
35
17
49
41
30
15
Hogwarts Legacy
34
26
20
9
29
23
15
-
CoD: Modern Warfare III
48
42
27
15
42
35
25
13
Ghost of Tsushima
33
23
19
10
29
19
13
9
Cyberpunk 2077
33
27
16
-
28
24
14
-
Shadow of the Tomb Raider
60
52
32
15
50
45
26
13
Average FPS by Resolution
1080p High 52 44
1080p Ultra 39 34
1440p Ultra 27 22
4K Ultra 13 12
Margin of Error Low Low

Benchmarks

Graphics cards’ performance in recent benchmarking apps

3D Mark

Multiplatform graphics benchmark suite that directly correlates with performance in modern games
Steel Nomad Lite Score
RX 580 +13%
4183
3701
Time Spy 4354 3855
Port Royal 527 -
Fire Strike 14980 13443
Wild Life Extreme 8907 7938
Night Raid 56859 50382
Sources: 3DMark [1], [2]

GeekBench 6 OpenCL

GPU test for computational tasks (image processing, photography, computer vision, and ML)
GB6 Compute Score
RX 580 +9%
40514
37147
Background Blur 59.5 img/sec 55.7 img/sec
Face Detection 33.8 img/sec 31.3 img/sec
Horizon Detection 1.56 Gpixels/sec 1.41 Gpixels/sec
Edge Detection 3.1 Gpixels/sec 2.82 Gpixels/sec
Gaussian Blur 2.92 Gpixels/sec 2.57 Gpixels/sec
Feature Matching 0.33 Gpixels/sec 0.31 Gpixels/sec
Stereo Matching 161.8 Gpixels/sec 143.2 Gpixels/sec
Particle Physics 5395.1 FPS 5080.1 FPS
API OpenCL OpenCL
Sources: Geekbench [3], [4]

Passmark Graphics

Videocard test that focuses on compute shaders, multi-texturing, tessellation, and other features
G3D Mark Score
RX 580 +11%
8782
7909
G2D Mark 770 725
DirectX 11 60 FPS 55 FPS
DirectX 12 43 FPS 39 FPS
GPU Compute 3409 Ops/s 2869 Ops/s
Sources: PassMark [5], [6] – 33466 & 24077 samples

Blender

Rendering performance test for 3D modeling
Blender GPU
RX 580 +19%
391.86
329.21
Sources: Blender [9], [10] – 91 & 22 samples

Artificial Intelligence Tests

Performance in machine learning and artificial intelligence tasks

GeekBench 6 ML

Tests throughput of AI operations in single, half, and quantized precision
GB6 ML Single Precision
RX 580 +15%
7905
6885
GB6 ML Half Precision
RX 580 +10%
8166
7446
GB6 ML Quantized
RX 580 +14%
5642
4931
Image Classification (SP) 3143 2676
Image Segmentation (HP) 3955 3757
Image Super Resolution (Q) 7872 6179
Face Detection (HP) 11922 10752
Pose Estimation (Q) 41162 35488
Text Classification (SP) 1199 1051
Machine Translation (HP) 1773 1933
Object Detection (SP) 3620 3048
Depth Estimation (Q) 13995 12040
Style Transfer (SP) 84083 71201
Framework ONNX ONNX
Backend DirectML DirectML
Sources: Geekbench [9], [10]

Specifications

Technical specifications of Radeon RX 580 and RX 570

General

Vendor Amd Amd
Build Discrete Discrete
Released April 18, 2017 April 18, 2017
Launch price (MSRP) $229 $169
Case Desktop Desktop
Purpose Gaming Gaming
Segment High-end Mid-range
Architecture GCN 4.0 GCN 4.0
GPU Codename Polaris 20 Polaris 20
Rival Equivalent - GeForce GTX 1060 - GeForce GTX 1050 Ti
Recommended CPU - Intel Core i5 8500 or above - Intel Core i5 8500 or above
Desktop GPU rating (83rd and 85th place)

Graphics Processing Unit

Base Clock 1257 MHz 1168 MHz
Boost Clock 1340 MHz 1244 MHz
Shading Units 2304 2048
Texture Mapping Units (TMUs) 144 128
Render Output Units (ROPs) 32 32
Tensor Cores No No
Ray-tracing Cores No No
L1 Cache 16KB per cluster 16KB per cluster
L2 Cache 2MB shared 2MB shared
Instructions Per Cycle 2 IPC 2 IPC

Raw Performance

Pixel Fill Rate 43 GPixel/s 40 GPixel/s
Texture Fill Rate 193 GTexel/s 159 GTexel/s
FLOPS (FP32)
RX 580 +22%
6.2 TFLOPS
5.1 TFLOPS

Physical

Interface PCIe 3.0 x16 PCIe 3.0 x16
TGP 185 W 150 W
Manufacturing GlobalFoundries GlobalFoundries
Fabrication Process 14 nm 14 nm
Die Size 232 mm² 232 mm²
Transistor Count 5 billion 5 billion
Transistor Density 21.55 MTr/mm² 21.55 MTr/mm²

Memory

Memory Type GDDR5 GDDR5
Memory Size 8 GB 4 GB
Memory Clock 2000 MHz 1750 MHz
Effective Memory Speed 8000 Mbps 7000 Mbps
Bus 256-bit 256-bit
ECC No No
Memory Bandwidth
RX 580 +14%
256 GB/s
224 GB/s

API

DirectX 12 12
Vulkan 1.3 1.3
OpenGL 4.6 4.6
OpenCL 2.1 2.1
Ray Tracing No No
DLSS No No
DisplayPort 1.4a 1.4a

Cast your vote

Choose between two graphics cards
40 (59.7%)
27 (40.3%)
Total votes: 67

User opinions

You can share your opinion or ask a question in the comments below
🌐 Register your profile and become part of NanoReview community!