Product Compare
NVIDIA GeForce RTX 4080 vs AMD Radeon Instinct MI25
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Sep 2022 | Jun 2017 |
| Generation | GeForce 40 | Radeon Instinct |
| Type | Desktop | Professional |
| Bus Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 2205 MHz | 1400 MHz |
| Boost Clock | 2505 MHz | 1500 MHz |
| Memory Clock | 1400 MHz | 852 MHz |
| Memory | ||
| Memory Size | 16GB | 16GB |
| Memory Type | GDDR6X | HBM2 |
| Memory Bus | 256bit | 2048bit |
| Bandwidth | 716.8GB/s | 436.2GB/s |
| Render Config | ||
| SM Count | 76 | |
| Shading Units | 9728 | 4096 |
| TMUs | 304 | 256 |
| ROPs | 112 | 64 |
| Tensor Cores | 304 | |
| RT Cores | 76 | |
| L1 Cache | 128 KB (per SM) | 16 KB (per CU) |
| L2 Cache | 64 MB | 4 MB |
| Compute Units | 64 | |
| Theoretical Performance | ||
| Pixel Rate | 280.6 GPixel/s | 96.00 GPixel/s |
| Texture Rate | 761.5 GTexel/s | 384.0 GTexel/s |
| FP16 (half) | 48.74 TFLOPS | 24.58 TFLOPS |
| FP32 (float) | 48.74 TFLOPS | 12.29 TFLOPS |
| FP64 (double) | 761.5 GFLOPS | 768.0 GFLOPS |
| Graphics Processor | ||
| GPU Name | AD103 | Vega 10 |
| GPU Variant | AD103-300-A1 | Vega 10 XT GL(215-0894124) |
| Architecture | Ada Lovelace | GCN 5.0 |
| Foundry | TSMC | GlobalFoundries |
| Process Size | 5 nm | 14 nm |
| Transistors | 45.9 billion | 12.5 billion |
| Die Size | 379 mm² | 495 mm² |
| Board Design | ||
| TDP | 320W | 300W |
| Suggested PSU | 700 W | 700 W |
| Outputs | 1x HDMI 2.13x DisplayPort 1.4a | No outputs |
| Power Connectors | 1x 16-pin | 2x 8-pin |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | 12 (12_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 2.1 |
| Vulkan | 1.3 | 1.2 |
| CUDA | 8.9 | |
| Shader Model | 6.7 | 6.4 |