Product Compare
AMD Radeon Pro Vega 16 vs NVIDIA CMP 50HX
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2018 | Jun 2021 |
| Generation | Radeon Pro Mac | Mining GPUs |
| Type | Mobile | Desktop |
| Bus Interface | PCIe 3.0 x16 | PCIe 1.0 x4 |
| Clock Speeds | ||
| Base Clock | 815 MHz | 1350 MHz |
| Boost Clock | 1190 MHz | 1545 MHz |
| Memory Clock | 1200 MHz | 1750 MHz |
| Memory | ||
| Memory Size | 4GB | 10GB |
| Memory Type | HBM2 | GDDR6 |
| Memory Bus | 1024bit | 320bit |
| Bandwidth | 307.2GB/s | 560.0GB/s |
| Render Config | ||
| Compute Units | 16 | |
| Shading Units | 1024 | 3584 |
| TMUs | 64 | 192 |
| ROPs | 32 | 80 |
| L1 Cache | 16 KB (per CU) | 64 KB (per SM) |
| L2 Cache | 1024 KB | 5 MB |
| SM Count | 56 | |
| Tensor Cores | 448 | |
| RT Cores | 56 | |
| Theoretical Performance | ||
| Pixel Rate | 38.08 GPixel/s | 123.6 GPixel/s |
| Texture Rate | 76.16 GTexel/s | 296.6 GTexel/s |
| FP16 (half) | 4.874 TFLOPS | 22.15 TFLOPS |
| FP32 (float) | 2.437 TFLOPS | 11.07 TFLOPS |
| FP64 (double) | 152.3 GFLOPS | 346.1 GFLOPS |
| Graphics Processor | ||
| GPU Name | Vega 12 | TU102 |
| GPU Variant | Vega 12 XLA | TU102-100-A1 |
| Architecture | GCN 5.0 | Turing |
| Foundry | GlobalFoundries | TSMC |
| Process Size | 14 nm | 12 nm |
| Transistors | Unknown | 18.6 billion |
| Die Size | Unknown | 754 mm² |
| Board Design | ||
| TDP | 75W | 250W |
| Outputs | No outputs | No outputs |
| Suggested PSU | 600 W | |
| Power Connectors | 2x 8-pin | |
| Graphics Features | ||
| DirectX | 12 (12_1) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.3 |
| Shader Model | 6.3 | 6.8 |
| CUDA | 7.5 | |