Product Compare
NVIDIA GeForce RTX 4080 SUPER vs AMD Radeon Instinct MI355X
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2024 | Jun 2025 |
| Generation | GeForce 40 | Radeon Instinct |
| Type | Desktop | Professional |
| Bus Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 2295 MHz | 1000 MHz |
| Boost Clock | 2550 MHz | 2400 MHz |
| Memory Clock | 1438 MHz | 2000 MHz |
| Memory | ||
| Memory Size | 16GB | 288GB |
| Memory Type | GDDR6X | HBM3e |
| Memory Bus | 256bit | 8192bit |
| Bandwidth | 736.3GB/s | 8.19TB/s |
| Render Config | ||
| SM Count | 80 | |
| Shading Units | 10240 | 16384 |
| TMUs | 320 | 1024 |
| ROPs | 112 | 0 |
| Tensor Cores | 320 | 1216 |
| RT Cores | 80 | |
| L1 Cache | 128 KB (per SM) | 32 KB (per CU) |
| L2 Cache | 64 MB | 32 MB |
| Compute Units | 256 | |
| L3 Cache | 256 MB | |
| Theoretical Performance | ||
| Pixel Rate | 285.6 GPixel/s | 0 MPixel/s |
| Texture Rate | 816.0 GTexel/s | 2457.6 GTexel/s |
| FP16 (half) | 52.22 TFLOPS | 78.64 TFLOPS |
| FP32 (float) | 52.22 TFLOPS | 78.64 TFLOPS |
| FP64 (double) | 816.0 GFLOPS | 39.32 TFLOPS |
| Graphics Processor | ||
| GPU Name | AD103 | MI350 256CU |
| GPU Variant | AD103-400-A1 | |
| Architecture | Ada Lovelace | CDNA 4.0 |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 3 nm |
| Transistors | 45.9 billion | 185 billion |
| Die Size | 379 mm² | Unknown |
| Board Design | ||
| TDP | 320W | 1400W |
| Suggested PSU | 700 W | 1800 W |
| Outputs | 1x HDMI 2.13x DisplayPort 1.4a | No outputs |
| Power Connectors | 1x 16-pin | None |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | N/A |
| CUDA | 8.9 | |
| Shader Model | 6.8 | N/A |