Product Compare
Moore Threads MTT S80 vs NVIDIA H100 CNX
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Oct 2023 | Mar 2023 |
| Generation | MUSA-Chunxiao | Tesla Hopper |
| Type | Desktop | AI GPU |
| Bus Interface | PCIe 5.0 x16 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 1800 MHz | 690 MHz |
| Boost Clock | 0 MHz | 1845 MHz |
| Memory Clock | 1750 MHz | 1593 MHz |
| Memory | ||
| Memory Size | 16GB | 80GB |
| Memory Type | GDDR6 | HBM2e |
| Memory Bus | 256bit | 5120bit |
| Bandwidth | 448.0GB/s | 2039GB/s |
| Render Config | ||
| Compute Units | 32 | |
| Shading Units | 4096 | 14592 |
| TMUs | 256 | 456 |
| ROPs | 256 | 24 |
| L2 Cache | 4 MB | 50 MB |
| SM Count | 114 | |
| Tensor Cores | 456 | |
| L1 Cache | 256 KB (per SM) | |
| Theoretical Performance | ||
| Pixel Rate | 460.8 GPixel/s | 44.28 GPixel/s |
| Texture Rate | 460.8 GTexel/s | 841.3 GTexel/s |
| FP16 (half) | 29.49 TFLOPS | 215.4 TFLOPS |
| FP32 (float) | 14.75 TFLOPS | 53.84 TFLOPS |
| FP64 (double) | 230.4 GFLOPS | 26.92 TFLOPS |
| Graphics Processor | ||
| GPU Name | MTT Gen 2 | GH100 |
| Architecture | MUSA-Chunxiao | Hopper |
| Foundry | TSMC | TSMC |
| Process Size | 12 nm | 4 nm |
| Transistors | 22 billion | 80 billion |
| Die Size | Unknown | 814 mm² |
| Board Design | ||
| TDP | 255W | 350W |
| Suggested PSU | 600 W | 750 W |
| Outputs | 1x HDMI 2.13x DisplayPort 1.4a | No outputs |
| Power Connectors | 1x 8-pin | 8-pin EPS |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.4 | N/A |
| Shader Model | 6.5 | N/A |
| CUDA | 9.0 | |