Quick/Comparisons
The Nvidia RTX A2000 Laptop takes the lead in gaming performance with a 5-point advantage, thanks to its higher score of 17. Its Ampere architecture and GA106 codename give it an edge over the Intel Arc A380's 12.
The Nvidia RTX A2000 Laptop outperforms the Intel Arc A380 in content creation with a significant 8-point gap, driven by its higher score of 29 and the power of its Ampere architecture.
The Nvidia RTX A2000 Laptop takes the lead in AI and machine learning with a 5-point advantage, thanks to its higher score of 18 and the capabilities of its Ampere architecture and dedicated AI tensor cores.
12 | Gaming | 17 |
21 | Workstation | 29 |
13 | AI/ML |
Compare with something else?
Compare Intel Arc A380 with another →18 |
71 | Energy Efficiency | 59 |
16 | Quick Comparison Final Score | 27 |
| DG2-128 | Graphics Processor | GA106 |
| 1024 | Cores | 2560 |
| 64 / 32 | TMUs / ROPs | 80 / 48 |
| 461.7 | Blender GPU | 1262.73 |
| 30 | Forza Horizon 5 | 44 |
| 40 | The Witcher 3 | 47 |
| 35 | Counter-Strike 2 | 74 |
| 37 | Far Cry 6 | 50 |
| 15 | Hogwarts Legacy | 26 |
| 30 | Call of Duty | 36 |
| 19 | Ghost of Tsushima | 23 |
| 24 | Cyberpunk 2077 | 33 |
| 35 | Tomb Raider | 56 |
| 29 | Average FPS | 43 |
| 38 | 1080p High | 55 |
| 29 | 1080p Ultra | 43 |
| 19 | 1440p Ultra | 30 |
| 11 | 4K Ultra | 14 |
| Low | Margin of Error | Low |
| 39896 | GB6 Compute Score | 57201 |
| 81.3 img/sec | Background Blur | 92.8 img/sec |
| 38.4 img/sec | Face Detection | 54.2 img/sec |
| 1.18 Gpixels/sec | Horizon Detection | 2.47 Gpixels/sec |
| 1.65 Gpixels/sec | Edge Detection | 3.32 Gpixels/sec |
| 2.45 Gpixels/sec | Gaussian Blur | 2.63 Gpixels/sec |
| 0.46 Gpixels/sec | Feature Matching | 0.7 Gpixels/sec |
| 146.5 Gpixels/sec | Stereo Matching | 236.9 Gpixels/sec |
| 7107.7 FPS | Particle Physics | 7148.8 FPS |
| OpenCL | API | OpenCL |
| 6288 | G3D Mark Score | 9487 |
| 627 | G2D Mark | 505 |
| 37 FPS | DirectX 11 | 65 FPS |
| 35 FPS | DirectX 12 | 47 FPS |
| 2765 Ops/s | GPU Compute | 4252 Ops/s |
| 5656 | GB6 ML Single Precision | 9891 |
| 6112 | GB6 ML Half Precision | 18270 |
| 4218 | GB6 ML Quantized | 6987 |
| 3198 | Image Classification (SP) | 4240 |
| 3938 | Image Segmentation (HP) | 9190 |
| 5735 | Image Super Resolution (Q) | 9374 |
| 5634 | Face Detection (HP) | 18335 |
| 20620 | Pose Estimation (Q) | 36989 |
| 798 | Text Classification (SP) | 2035 |
| 1098 | Machine Translation (HP) | 2687 |
| 3460 | Object Detection (SP) | 5174 |
| 11598 | Depth Estimation (Q) | 16537 |
| 55429 | Style Transfer (SP) | 77854 |
| ONNX | Framework | ONNX |
| DirectML | Backend | DirectML |
| 66 GPixel/s | Pixel Fill Rate | 50-81 GPixel/s |
| 131 GTexel/s | Texture Fill Rate | 83-136 GTexel/s |
| 4.2 TFLOPS | FLOPS (FP32) | 5.3-8.7 TFLOPS |
| GDDR6 | Memory Type | GDDR6 |
| 6 GB | Memory Size | 4 GB |
| 1937 MHz | Memory Clock | 1500 MHz |
| 15500 Mbps | Effective Memory Speed | 12000 Mbps |
| 96-bit | Bus | 128-bit |
| No | ECC | No |
| 186 GB/s | Memory Bandwidth | 192 GB/s |
| PCIe 4.0 x8 | Interface | PCIe 4.0 x16 |
| 75 W | TGP | 60-95 W (configurable) |
| TSMC | Manufacturing | Samsung |
| 6 nm | Fabrication Process | 8 nm |
| 157 mm² | Die Size | 276 mm² |
| 7 billion | Transistor Count | 12 billion |
| 44.59 MTr/mm² | Transistor Density | 43.48 MTr/mm² |
| 12 | DirectX | 12 |
| 1.3 | Vulkan | 1.3 |
| 4.6 | OpenGL | 4.6 |
| 3 | OpenCL | 3 |
| — | CUDA | 8.6 |
| Yes | Ray Tracing | Yes |
| No | DLSS | DLSS 2 |
| 2 | DisplayPort | 1.4a |
| Intel | Vendor | Nvidia |
| Discrete | Build | Discrete |
| January 14, 2022 | Released | April 12, 2021 |
| Desktop | Case | Laptop |
| Gaming | Purpose | Professional |
| Mid-range | Segment | Mid-range |
| Generation 12.7 | Architecture | Ampere |
| DG2-128 | GPU Codename | GA106 |
| -Intel Core i5 12400or above | Recommended CPU | -Intel Core i7 12800Hor above |
| 3439 | Steel Nomad Lite Score | 4397 |
| 4242 | Time Spy | 4723 |
| 14978 | Solar Bay | 19912 |
| 1499 | Port Royal | 2895 |
| 9982 | Fire Strike | 11357 |
| 7802 | Wild Life Extreme | 8429 |
| 49173 | Night Raid | 49889 |
| 2000 MHz | Base Clock | 735-1463 MHz (configurable) |
| 2050 MHz | Boost Clock | 1035-1695 MHz (configurable) |
| 1024 | Shading Units | 2560 |
| 64 | Texture Mapping Units (TMUs) | 80 |
| 32 | Render Output Units (ROPs) | 48 |
| — | Compute Units (Pipelines) | 20 |
| 128 | Tensor Cores | 80 |
| 8 | Ray-tracing Cores | 20 |
| — | L1 Cache | 128KB per cluster |
| 4MB shared | L2 Cache | 2MB shared |
| 2 IPC | Instructions Per Cycle | 2 IPC |