Product Compare
AMD Radeon Instinct MI355X vs NVIDIA H800 PCIe 80 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jun 2025 | Mar 2023 |
| Generation | Radeon Instinct | Tesla Hopper |
| Type | Professional | AI GPU |
| Bus Interface | PCIe 5.0 x16 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 1000 MHz | 1095 MHz |
| Boost Clock | 2400 MHz | 1755 MHz |
| Memory Clock | 2000 MHz | 1593 MHz |
| Memory | ||
| Memory Size | 288GB | 80GB |
| Memory Type | HBM3e | HBM2e |
| Memory Bus | 8192bit | 5120bit |
| Bandwidth | 8.19TB/s | 2039GB/s |
| Render Config | ||
| Compute Units | 256 | |
| Shading Units | 16384 | 14592 |
| TMUs | 1024 | 456 |
| ROPs | 0 | 24 |
| Tensor Cores | 1216 | 456 |
| L1 Cache | 32 KB (per CU) | 256 KB (per SM) |
| L2 Cache | 32 MB | 50 MB |
| L3 Cache | 256 MB | |
| SM Count | 114 | |
| Theoretical Performance | ||
| Pixel Rate | 0 MPixel/s | 42.12 GPixel/s |
| Texture Rate | 2457.6 GTexel/s | 800.3 GTexel/s |
| FP16 (half) | 78.64 TFLOPS | 204.9 TFLOPS |
| FP32 (float) | 78.64 TFLOPS | 51.22 TFLOPS |
| FP64 (double) | 39.32 TFLOPS | 25.61 TFLOPS |
| Graphics Processor | ||
| GPU Name | MI350 256CU | GH100 |
| Architecture | CDNA 4.0 | Hopper |
| Foundry | TSMC | TSMC |
| Process Size | 3 nm | 4 nm |
| Transistors | 185 billion | 80 billion |
| Die Size | Unknown | 814 mm² |
| Board Design | ||
| TDP | 1400W | 350W |
| Suggested PSU | 1800 W | 750 W |
| Outputs | No outputs | No outputs |
| Power Connectors | None | 1x 16-pin |
| Graphics Features | ||
| DirectX | N/A | N/A |
| OpenGL | N/A | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | N/A |
| Shader Model | N/A | N/A |
| CUDA | 9.0 | |