AMD Radeon RX 580 vs Nvidia GeForce RTX 4070
18
out 100
VS
55
out 100
Compared 2 processors: AMD Radeon RX 580, vs Nvidia GeForce RTX 4070. Below are specs, tests, pros and cons for each device
Review
Games
Performance in DirectX, OpenCL, Vulkan
AI/ML
AI workload testing
Professional Apps
3D modeling, video editing, rendering
Energy Efficiency
Power usage in various scenarios
Tests & specs
Specs & test comparisonGames
| Game title | 1080p (High) 1080p (Ultra) 1440p (Ultra) 4K (Ultra) | |
 Forza Horizon 5 | 76 38 33 15 | 170 113 105 79 |
 The Witcher 3 | 52 40 23 13 | 191 160 114 61 |
 Counter-Strike 2 | 78 56 37 16 | 262 207 148 82 |
 Far Cry 6 | 58 49 34 17 | 148 135 112 71 |
 Hogwarts Legacy | 33 23 20 10 | 120 96 78 43 |
 COD Modern Warfare 3 | 47 41 27 15 | 154 141 110 72 |
 Ghost of Tsushima | 33 24 16 9 | 104 87 74 40 |
 Cyberpunk 2077 | 30 27 13 n/a | 133 115 78 34 |
 Shadow of the Tomb Raider | 60 51 31 18 | 209 194 148 81 |
| 1080p High | 52 | 166 |
| 1080p Ultra | 39 | 139 |
| 1440p Ultra | 26 | 107 |
| 4K Ultra | 13 | 63 |
| Deviation | Low | Low |
Benchmarks
| Time Spy | 4353 | 17825 |
| Solar Bay | n/a | 82645 |
| Port Royal | 527 | 11149 |
| Fire Strike | 14979 | 44109 |
| Night Raid | 56876 | 152587 |
| Background Blur | 59.5 frames/s | 233 frames/s |
| Face Detection | 33.8 frames/s | 141.7 frames/s |
| Horizon Detection | 1.56 Gpix/sec | 6.62 Gpix/sec |
| Edge Detection | 3.1 Gpix/sec | 9.19 Gpix/sec |
| Gaussian Blur | 2.92 Gpix/sec | 9.2 Gpix/sec |
| Feature Matching | 0.33 Gpix/sec | 1.78 Gpix/sec |
| Stereo Matching | 161.8 Gpix/sec | 845.4 Gpix/sec |
| Particle Physics | 5395.1 fps | 25043.9 fps |
| API | OpenCL | OpenCL |
| G2D Mark | 767 | 1165 |
| DirectX 11 | 60 fps | 245 fps |
| DirectX 12 | 43 fps | 102 fps |
| GPU Compute | 3529 Ops/s | 14820 Ops/s |
| Aztec Ruins (Normal) | n/a | 1039 fps |
| Car Chase | n/a | 900 fps |
| Manhattan 3.1.1 (1440p) | n/a | 761.2 fps |
| T-Rex | n/a | 3848.1 fps |
| ALU 2 | n/a | 5980.8 fps |
| Driver Overhead 2 | n/a | 296.7 fps |
| API | n/a | OpenGL |
| OS | n/a | Windows |
| Tessellation | n/a | 6200.7 |
Tech Specs
Specs & test comparisonGeneral Info
| Manufacturer | AMD | Nvidia |
| Build | Discrete | Discrete |
| Announced | April, 18, 2017 | April, 13, 2023 |
| Form Factor | PC use | PC use |
| Use case | Gaming | Gaming |
| Segment | High-end | Mid-range |
| Architecture | GCN 4.0 | Ada Lovelace |
| Codename | Polaris 20 | AD104 |
| Price | 229 | 599 |
GPU
| GPU Frequency | 1257 MHz | 1920 MHz |
| Boost GPU Frequency | 1340 MHz | 2475 MHz |
| Shader Units | 2304 | 5888 |
| TMUs | 144 | 184 |
| ROPs | 32 | 64 |
| Execution Units | n/a | 46 |
| Ray Tracing Cores | No | 46 |
| Tensor Cores | No | 184 |
| L1 cache | 16 KB/core | 128 KB/core |
| L2 cache | 2000 KB/core | 36000 KB/core |
| Instructions per Clock | 2 IPC | 2 IPC |
Performance
| Pixel Fill Rate | 43 Gpix/sec | 158 Gpix/sec |
| Texture Fill Rate | 193 GTex/s | 455 GTex/s |
| FLOPS | 6.2 TFLOPS | 29.1 TFLOPS |
Process
| Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| TGP | 185 W | 200 W |
| Process | GlobalFoundries | TSMC |
| Process tech. | 14 nm | 5 nm |
| Transistor Size | 232 mm² | 294 mm² |
| Transistor count | 5 billion | 35 billion |
| Transistor density | 21.55 MTr/mm² | 119.05 MTr/mm² |
Memory
| Interface | GDDR5 | GDDR6X |
| Memory Frequency | 2000 MHz | 1313 MHz |
| Bus | 256 bit | 192 bit |
| ECC support | No | No |
| Effective Memory Speed | 8000 MB/s | 21000 MB/s |
| Memory Size | 8 GB | 12 GB |
Max Throughput
API
| DirectX | 12 | 12 |
| Vulkan | 1.3 | 1.3 |
| OpenGL | 4.6 | 4.6 |
| CUDA | n/a | 8.9 |
| DisplayPort | 1.4a | 1.4a |
| Ray Tracing | No | Yes |
| DLSS | No | DLSS 3 |
Results
After analyzing the data, we consider Nvidia GeForce RTX 4070 the clear winner in this comparison.
Survey
Total Votes: 1
