Product Compare
AMD Radeon Pro W6900X vs NVIDIA CMP 170HX 10 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Aug 2021 | Sep 2021 |
| Generation | Radeon Pro Mac | Mining GPUs |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 4.0 x16 | PCIe 1.0 x4 |
| Clock Speeds | ||
| Base Clock | 1825 MHz | 1140 MHz |
| Boost Clock | 2150 MHz | 1410 MHz |
| Memory Clock | 2000 MHz | 1215 MHz |
| Memory | ||
| Memory Size | 32GB | 10GB |
| Memory Type | GDDR6 | HBM2e |
| Memory Bus | 256bit | 5120bit |
| Bandwidth | 512.0GB/s | 1.56TB/s |
| Render Config | ||
| Compute Units | 80 | |
| Shading Units | 5120 | 4480 |
| TMUs | 320 | 280 |
| ROPs | 128 | 128 |
| RT Cores | 80 | |
| L1 Cache | 128 KB per Array | 192 KB (per SM) |
| L2 Cache | 4 MB | 10 MB |
| L3 Cache | 128 MB | |
| SM Count | 70 | |
| Tensor Cores | 280 | |
| Theoretical Performance | ||
| Pixel Rate | 275.2 GPixel/s | 180.5 GPixel/s |
| Texture Rate | 688.0 GTexel/s | 394.8 GTexel/s |
| FP16 (half) | 44.03 TFLOPS | 50.53 TFLOPS |
| FP32 (float) | 22.02 TFLOPS | 12.63 TFLOPS |
| FP64 (double) | 1376 GFLOPS | 6.317 TFLOPS |
| Graphics Processor | ||
| GPU Name | Navi 21 | GA100 |
| GPU Variant | Navi 21 Pro-XTA | GA100-105A-A1 |
| Architecture | RDNA 2.0 | Ampere |
| Foundry | TSMC | TSMC |
| Process Size | 7 nm | 7 nm |
| Transistors | 26.8 billion | 54.2 billion |
| Die Size | 520 mm² | 826 mm² |
| Board Design | ||
| TDP | 300W | 250W |
| Suggested PSU | 700 W | 600 W |
| Outputs | 1x HDMI 2.14x Thunderbolt | No outputs |
| Power Connectors | None | 2x 8-pin |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.3 | N/A |
| Shader Model | 6.5 | N/A |
| CUDA | 8.0 | |