Product Compare
AMD Radeon Instinct MI250 vs NVIDIA GeForce RTX 2050 Mobile
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2021 | Dec 2021 |
| Generation | Radeon Instinct | GeForce 20 Mobile |
| Type | Professional | Mobile |
| Bus Interface | PCIe 4.0 x16 | PCIe 3.0 x8 |
| Clock Speeds | ||
| Base Clock | 1000 MHz | 1185 MHz |
| Boost Clock | 1700 MHz | 1477 MHz |
| Memory Clock | 1600 MHz | 1750 MHz |
| Memory | ||
| Memory Size | 128GB | 4GB |
| Memory Type | HBM2e | GDDR6 |
| Memory Bus | 8192bit | 64bit |
| Bandwidth | 3277GB/s | 112.0GB/s |
| Render Config | ||
| Compute Units | 208 | |
| Shading Units | 13312 | 2048 |
| TMUs | 832 | 64 |
| ROPs | 0 | 32 |
| L1 Cache | 16 KB (per CU) | 64 KB (per SM) |
| L2 Cache | 16 MB | 2 MB |
| SM Count | 16 | |
| Tensor Cores | 64 | |
| RT Cores | 32 | |
| Theoretical Performance | ||
| Pixel Rate | 0 MPixel/s | 47.26 GPixel/s |
| Texture Rate | 1414 GTexel/s | 94.53 GTexel/s |
| FP16 (half) | 362.1 TFLOPS | 12.10 TFLOPS |
| FP32 (float) | 45.26 TFLOPS | 6.050 TFLOPS |
| FP64 (double) | 45.26 TFLOPS | 189.1 GFLOPS |
| Graphics Processor | ||
| GPU Name | Aldebaran | GA107 |
| GPU Variant | Aldebaran | |
| Architecture | CDNA 2.0 | Ampere |
| Foundry | TSMC | Samsung |
| Process Size | 6 nm | 8 nm |
| Transistors | 58.2 billion | Unknown |
| Die Size | Unknown | Unknown |
| Board Design | ||
| TDP | 500W | 45W |
| Suggested PSU | 900 W | |
| Outputs | No outputs | 1x DVI1x HDMI 2.12x DisplayPort 1.4a |
| Power Connectors | 2x 8-pin | 1x 6-pin |
| Graphics Features | ||
| DirectX | N/A | 12 Ultimate (12_2) |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | 1.3 |
| Shader Model | N/A | 6.6 |
| CUDA | 8.6 | |