Product Compare
AMD Radeon Instinct MI250X vs NVIDIA RTX 2000 Max-Q Ada Generation
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2021 | Mar 2023 |
| Generation | Radeon Instinct | Quadro Ada-M |
| Type | Professional | Mobile |
| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1000 MHz | 930 MHz |
| Boost Clock | 1700 MHz | 1455 MHz |
| Memory Clock | 1600 MHz | 2000 MHz |
| Memory | ||
| Memory Size | 128GB | 8GB |
| Memory Type | HBM2e | GDDR6 |
| Memory Bus | 8192bit | 128bit |
| Bandwidth | 3277GB/s | 256.0GB/s |
| Render Config | ||
| Compute Units | 220 | |
| Shading Units | 14080 | 3072 |
| TMUs | 880 | 96 |
| ROPs | 0 | 48 |
| L1 Cache | 16 KB (per CU) | 128 KB (per SM) |
| L2 Cache | 16 MB | 12 MB |
| SM Count | 24 | |
| Tensor Cores | 96 | |
| RT Cores | 24 | |
| Theoretical Performance | ||
| Pixel Rate | 0 MPixel/s | 69.84 GPixel/s |
| Texture Rate | 1496 GTexel/s | 139.7 GTexel/s |
| FP16 (half) | 383.0 TFLOPS | 8.940 TFLOPS |
| FP32 (float) | 47.87 TFLOPS | 8.940 TFLOPS |
| FP64 (double) | 47.87 TFLOPS | 139.7 GFLOPS |
| Graphics Processor | ||
| GPU Name | Aldebaran | AD107 |
| GPU Variant | Aldebaran XT | |
| Architecture | CDNA 2.0 | Ada Lovelace |
| Foundry | TSMC | TSMC |
| Process Size | 6 nm | 5 nm |
| Transistors | 58.2 billion | 18.9 billion |
| Die Size | Unknown | 159 mm² |
| Board Design | ||
| TDP | 500W | 35W |
| Suggested PSU | 900 W | |
| Outputs | No outputs | Portable Device Dependent |
| Power Connectors | 2x 8-pin | None |
| 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 | 6.7 |
| CUDA | 8.9 | |