Product Compare
AMD Radeon Instinct MI250X vs NVIDIA Tesla T10
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2021 | Unknown |
| Generation | Radeon Instinct | Tesla |
| Type | Professional | Professional |
| Bus Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 1000 MHz | 1305 MHz |
| Boost Clock | 1700 MHz | 1560 MHz |
| Memory Clock | 1600 MHz | 1625 MHz |
| Memory | ||
| Memory Size | 128GB | 24GB |
| Memory Type | HBM2e | GDDR6 |
| Memory Bus | 8192bit | 384bit |
| Bandwidth | 3277GB/s | 624.0GB/s |
| Render Config | ||
| Compute Units | 220 | |
| Shading Units | 14080 | 4608 |
| TMUs | 880 | 288 |
| ROPs | 0 | 96 |
| L1 Cache | 16 KB (per CU) | 64 KB (per SM) |
| L2 Cache | 16 MB | 6 MB |
| SM Count | 72 | |
| Tensor Cores | 576 | |
| RT Cores | 72 | |
| Theoretical Performance | ||
| Pixel Rate | 0 MPixel/s | 149.8 GPixel/s |
| Texture Rate | 1496 GTexel/s | 449.3 GTexel/s |
| FP16 (half) | 383.0 TFLOPS | 28.75 TFLOPS |
| FP32 (float) | 47.87 TFLOPS | 14.38 TFLOPS |
| FP64 (double) | 47.87 TFLOPS | 449.3 GFLOPS |
| Graphics Processor | ||
| GPU Name | Aldebaran | TU102 |
| GPU Variant | Aldebaran XT | |
| Architecture | CDNA 2.0 | Turing |
| Foundry | TSMC | TSMC |
| Process Size | 6 nm | 12 nm |
| Transistors | 58.2 billion | 18.6 billion |
| Die Size | Unknown | 754 mm² |
| Board Design | ||
| TDP | 500W | 260W |
| Suggested PSU | 900 W | 600 W |
| Outputs | No outputs | No outputs |
| Power Connectors | 2x 8-pin | 1x 6-pin + 1x 8-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 | 7.5 | |