AMD Radeon RX 590 vs RX 580
AMD Radeon RX 590
Polaris 30
AMD Radeon RX 580
Polaris 20
We compared two discrete desktop gaming GPUs: the Radeon RX 590 with 2304 shaders against the 1 year and 7 months older RX 580 that utilizes 2304 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score
Value for money (Beta)
Key differences
Reasons to consider the Radeon RX 590
- Manufactured using a more efficient 12 nm process technology
- 15% higher maximum theoretical performance (7.1 vs 6.2 TFLOPS)
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 80 42 33 20 |
76 39 31 17 |
| The Witcher 3 | 58 46 29 15 |
50 41 22 12 |
| Counter-Strike 2 | 92 66 42 20 |
74 55 38 15 |
| Far Cry 6 | 61 53 38 19 |
59 49 35 17 |
| Hogwarts Legacy | 37 29 22 10 |
34 26 20 9 |
| CoD: Modern Warfare III | 51 43 31 16 |
48 42 27 15 |
| Ghost of Tsushima | 36 26 18 9 |
33 23 19 10 |
| Cyberpunk 2077 | 33 33 18 - |
33 27 16 - |
| Shadow of the Tomb Raider | 65 56 35 16 |
60 52 32 15 |
| 1080p High | 57 | 52 |
| 1080p Ultra | 44 | 39 |
| 1440p Ultra | 30 | 27 |
| 4K Ultra | 15 | 13 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 4778 | 4354 |
| Port Royal | - | 527 |
| Fire Strike | 16527 | 14980 |
| Wild Life Extreme | 9737 | 8907 |
| Night Raid | 62043 | 56859 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 69 img/sec | 59.5 img/sec |
| Face Detection | 38.2 img/sec | 33.8 img/sec |
| Horizon Detection | 1.75 Gpixels/sec | 1.56 Gpixels/sec |
| Edge Detection | 3.31 Gpixels/sec | 3.1 Gpixels/sec |
| Gaussian Blur | 3.31 Gpixels/sec | 2.92 Gpixels/sec |
| Feature Matching | 0.38 Gpixels/sec | 0.33 Gpixels/sec |
| Stereo Matching | 180.5 Gpixels/sec | 161.8 Gpixels/sec |
| Particle Physics | 6238 FPS | 5395.1 FPS |
| API | OpenCL | OpenCL |
Passmark Graphics
G3D Mark Score
| G2D Mark | 789 | 770 |
| DirectX 11 | 65 FPS | 60 FPS |
| DirectX 12 | 45 FPS | 43 FPS |
| GPU Compute | 3732 Ops/s | 3409 Ops/s |
Blender
Blender GPU
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | 3307 | 3143 |
| Image Segmentation (HP) | 4895 | 3955 |
| Image Super Resolution (Q) | 9072 | 7872 |
| Face Detection (HP) | 12467 | 11922 |
| Pose Estimation (Q) | 43468 | 41162 |
| Text Classification (SP) | 1547 | 1199 |
| Machine Translation (HP) | 2504 | 1773 |
| Object Detection (SP) | 3746 | 3620 |
| Depth Estimation (Q) | 15075 | 13995 |
| Style Transfer (SP) | 96813 | 84083 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 590 and RX 580General
| Vendor | Amd | Amd |
| Build | Discrete | Discrete |
| Released | November 15, 2018 | April 18, 2017 |
| Launch price (MSRP) | $279 | $229 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | High-end |
| Architecture | GCN 4.0 | GCN 4.0 |
| GPU Codename | Polaris 30 | Polaris 20 |
| Rival Equivalent | - GeForce GTX 1060 | - GeForce GTX 1060 |
| Recommended CPU | - Intel Core i5 8500 or above | - Intel Core i5 8500 or above |
Desktop GPU rating (80th and 83rd place)
Graphics Processing Unit
| Base Clock | 1469 MHz | 1257 MHz |
| Boost Clock | 1545 MHz | 1340 MHz |
| Shading Units | 2304 | 2304 |
| Texture Mapping Units (TMUs) | 144 | 144 |
| 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 | 49 GPixel/s | 43 GPixel/s |
| Texture Fill Rate | 222 GTexel/s | 193 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| TGP | 175 W | 185 W |
| Manufacturing | GlobalFoundries | GlobalFoundries |
| Fabrication Process | 12 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 | 8 GB |
| Memory Clock | 2000 MHz | 2000 MHz |
| Effective Memory Speed | 8000 Mbps | 8000 Mbps |
| Bus | 256-bit | 256-bit |
| ECC | No | No |
Memory Bandwidth
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
Total votes: 138