AMD Radeon RX 580 vs Intel Arc A580
AMD Radeon RX 580
Polaris 20
Intel Arc A580
DG2-512
We compared two discrete desktop gaming GPUs: the Radeon RX 580 with 2304 shaders against the 6 years and 7 months newer Intel Arc A580 that utilizes 3072 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 Intel Arc A580
- Performs significantly better (up to 2.2x) in 3DMark Steel Nomad Lite
- Manufactured using a more efficient 6 nm process technology
- Shows 89% higher average frame rate in modern games at QHD resolution – 51 vs 27 FPS
- 2x higher maximum theoretical performance (12.3 vs 6.2 TFLOPS)
- Ray-tracing support with 24 dedicated RT cores
Gaming Performance
Frame rate comparison across popular AAA titles at different resolutionsGames
| Forza Horizon 5 | 76 39 31 17 |
105 62 51 34 |
| The Witcher 3 | 50 41 22 12 |
114 97 68 37 |
| Counter-Strike 2 | 74 55 38 15 |
140 101 72 35 |
| Far Cry 6 | 59 49 35 17 |
89 83 56 29 |
| Hogwarts Legacy | 34 26 20 9 |
54 45 34 18 |
| CoD: Modern Warfare III | 48 42 27 15 |
60 58 42 22 |
| Ghost of Tsushima | 33 23 19 10 |
59 46 36 18 |
| Cyberpunk 2077 | 33 27 16 - |
70 60 41 18 |
| Shadow of the Tomb Raider | 60 52 32 15 |
98 84 61 32 |
| 1080p High | 52 | 88 |
| 1080p Ultra | 39 | 71 |
| 1440p Ultra | 27 | 51 |
| 4K Ultra | 13 | 27 |
| Margin of Error | Low | Low |
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Time Spy | 4354 | 10812 |
| Solar Bay | - | 39946 |
| Port Royal | 527 | 5628 |
| Fire Strike | 14980 | 25225 |
| Wild Life Extreme | 8907 | 21117 |
| Night Raid | 56859 | 103973 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 59.5 img/sec | 135.5 img/sec |
| Face Detection | 33.8 img/sec | 76.3 img/sec |
| Horizon Detection | 1.56 Gpixels/sec | 2.81 Gpixels/sec |
| Edge Detection | 3.1 Gpixels/sec | 4.37 Gpixels/sec |
| Gaussian Blur | 2.92 Gpixels/sec | 6.43 Gpixels/sec |
| Feature Matching | 0.33 Gpixels/sec | 0.8 Gpixels/sec |
| Stereo Matching | 161.8 Gpixels/sec | 417.1 Gpixels/sec |
| Particle Physics | 5395.1 FPS | 17700.8 FPS |
| API | OpenCL | OpenCL |
Passmark Graphics
G3D Mark Score
| G2D Mark | 770 | 739 |
| DirectX 11 | 60 FPS | 71 FPS |
| DirectX 12 | 43 FPS | 64 FPS |
| GPU Compute | 3409 Ops/s | 4887 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) | 3143 | 4014 |
| Image Segmentation (HP) | 3955 | 7656 |
| Image Super Resolution (Q) | 7872 | 10138 |
| Face Detection (HP) | 11922 | 12636 |
| Pose Estimation (Q) | 41162 | 50065 |
| Text Classification (SP) | 1199 | 672 |
| Machine Translation (HP) | 1773 | 1569 |
| Object Detection (SP) | 3620 | 5323 |
| Depth Estimation (Q) | 13995 | 20334 |
| Style Transfer (SP) | 84083 | 132558 |
| Framework | ONNX | ONNX |
| Backend | DirectML | DirectML |
Specifications
Technical specifications of Radeon RX 580 and Intel Arc A580General
| Vendor | Amd | Intel |
| Build | Discrete | Discrete |
| Released | April 18, 2017 | October 10, 2023 |
| Launch price (MSRP) | $229 | $179 |
| Case | Desktop | Desktop |
| Purpose | Gaming | Gaming |
| Segment | High-end | Mid-range |
| Architecture | GCN 4.0 | Generation 12.7 |
| GPU Codename | Polaris 20 | DG2-512 |
| Rival Equivalent | - GeForce GTX 1060 | - GeForce GTX 1660 SUPER |
| Successor | - | - Intel Arc B580 |
| Recommended CPU | - Intel Core i5 8500 or above | - Intel Core i5 13400 or above |
Desktop GPU rating (83rd and 67th place)
Graphics Processing Unit
| Base Clock | 1257 MHz | 1700 MHz |
| Boost Clock | 1340 MHz | 2000 MHz |
| Shading Units | 2304 | 3072 |
| Texture Mapping Units (TMUs) | 144 | 192 |
| Render Output Units (ROPs) | 32 | 96 |
| Tensor Cores | No | 384 |
| Ray-tracing Cores | No | 24 |
| L1 Cache | 16KB per cluster | - |
| L2 Cache | 2MB shared | 8MB shared |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 43 GPixel/s | 192 GPixel/s |
| Texture Fill Rate | 193 GTexel/s | 384 GTexel/s |
FLOPS (FP32)
Physical
| Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| TGP | 185 W | 175 W |
| Manufacturing | GlobalFoundries | TSMC |
| Fabrication Process | 14 nm | 6 nm |
| Die Size | 232 mm² | 406 mm² |
| Transistor Count | 5 billion | 21 billion |
| Transistor Density | 21.55 MTr/mm² | 51.72 MTr/mm² |
Memory
| Memory Type | GDDR5 | GDDR6 |
| Memory Size | 8 GB | 8 GB |
| Memory Clock | 2000 MHz | 2000 MHz |
| Effective Memory Speed | 8000 Mbps | 16000 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 | 3.0 |
| Ray Tracing | No | Yes |
| DLSS | No | No |
| DisplayPort | 1.4a | 2.0 |
Cast your vote
Total votes: 30