Product Compare
NVIDIA GeForce RTX 5090 vs AMD Radeon PRO W7900D
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2025 | Nov 2025 |
| Generation | GeForce 50 | Radeon Pro Navi |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 2017 MHz | 1327 MHz |
| Boost Clock | 2407 MHz | 2156 MHz |
| Memory Clock | 1750 MHz | 2250 MHz |
| Memory | ||
| Memory Size | 32GB | 48GB |
| Memory Type | GDDR7 | GDDR6 |
| Memory Bus | 512bit | 384bit |
| Bandwidth | 1.79TB/s | 864.0GB/s |
| Render Config | ||
| SM Count | 170 | |
| Shading Units | 21760 | 6144 |
| TMUs | 680 | 384 |
| ROPs | 176 | 192 |
| Tensor Cores | 680 | |
| RT Cores | 170 | 96 |
| L1 Cache | 128 KB (per SM) | 256 KB per Array |
| L2 Cache | 96 MB | 6 MB |
| Compute Units | 96 | |
| L3 Cache | 96 MB | |
| Theoretical Performance | ||
| Pixel Rate | 423.6 GPixel/s | 414.0 GPixel/s |
| Texture Rate | 1636.8 GTexel/s | 827.9 GTexel/s |
| FP16 (half) | 104.8 TFLOPS | 106.0 TFLOPS |
| FP32 (float) | 104.8 TFLOPS | 52.99 TFLOPS |
| FP64 (double) | 1.637 TFLOPS | 1.656 TFLOPS |
| Graphics Processor | ||
| GPU Name | GB202 | Navi 31 |
| GPU Variant | GB202-300-A1 | Navi 31 |
| Architecture | Blackwell 2.0 | RDNA 3.0 |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 5 nm |
| Transistors | 92.2 billion | 57.7 billion |
| Die Size | 750 mm² | 529 mm² |
| Board Design | ||
| TDP | 575W | 295W |
| Suggested PSU | 950 W | 600 W |
| Outputs | 1x HDMI 2.1b3x DisplayPort 2.1b | 3x DisplayPort 2.11x mini-DisplayPort 2.1 |
| Power Connectors | 1x 16-pin | 2x 8-pin |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 2.2 |
| Vulkan | 1.4 | 1.4 |
| CUDA | 12.0 | |
| Shader Model | 6.9 | 6.9 |