Product Compare
NVIDIA CMP 100HX-210 vs NVIDIA H100 PCIe
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jan 2020 | Mar 2022 |
| Generation | Mining GPUs | Tesla Hopper |
| Type | Desktop | AI GPU |
| Bus Interface | PCIe 1.0 x1 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 555 MHz | 1095 MHz |
| Boost Clock | 1147 MHz | 1755 MHz |
| Memory Clock | 810 MHz | 1593 MHz |
| Memory | ||
| Memory Size | 16GB | 80GB |
| Memory Type | HBM2 | HBM2e |
| Memory Bus | 4096bit | 5120bit |
| Bandwidth | 829.4GB/s | 2039GB/s |
| Render Config | ||
| SM Count | 80 | 114 |
| Shading Units | 5120 | 14592 |
| TMUs | 320 | 456 |
| ROPs | 128 | 24 |
| Tensor Cores | 640 | 456 |
| L1 Cache | 96 KB (per SM) | 256 KB (per SM) |
| L2 Cache | 6 MB | 50 MB |
| Theoretical Performance | ||
| Pixel Rate | 146.8 GPixel/s | 42.12 GPixel/s |
| Texture Rate | 367.0 GTexel/s | 800.3 GTexel/s |
| FP16 (half) | 23.49 TFLOPS | 204.9 TFLOPS |
| FP32 (float) | 11.75 TFLOPS | 51.22 TFLOPS |
| FP64 (double) | 5.873 TFLOPS | 25.61 TFLOPS |
| Graphics Processor | ||
| GPU Name | GV100 | GH100 |
| Architecture | Volta | Hopper |
| Foundry | TSMC | TSMC |
| Process Size | 12 nm | 4 nm |
| Transistors | 21.1 billion | 80 billion |
| Die Size | 815 mm² | 814 mm² |
| Board Design | ||
| TDP | 250W | 350W |
| Suggested PSU | 600 W | 750 W |
| Outputs | No outputs | No outputs |
| Power Connectors | 1x 6-pin + 1x 8-pin | 1x 16-pin |
| Graphics Features | ||
| DirectX | 12 (12_1) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | N/A |
| CUDA | 7.0 | 9.0 |
| Shader Model | 6.8 | N/A |