Product Compare
NVIDIA H800 PCIe 80 GB vs NVIDIA CMP 170HX
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Mar 2023 | Sep 2021 |
| Generation | Tesla Hopper | Mining GPUs |
| Type | AI GPU | Desktop |
| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x4 |
| Clock Speeds | ||
| Base Clock | 1095 MHz | 1140 MHz |
| Boost Clock | 1755 MHz | 1410 MHz |
| Memory Clock | 1593 MHz | 1458 MHz |
| Memory | ||
| Memory Size | 80GB | 16GB |
| Memory Type | HBM2e | HBM2e |
| Memory Bus | 5120bit | 4096bit |
| Bandwidth | 2039GB/s | 1493GB/s |
| Render Config | ||
| SM Count | 114 | 70 |
| Shading Units | 14592 | 4480 |
| TMUs | 456 | 280 |
| ROPs | 24 | 128 |
| Tensor Cores | 456 | 280 |
| L1 Cache | 256 KB (per SM) | 192 KB (per SM) |
| L2 Cache | 50 MB | 8 MB |
| Theoretical Performance | ||
| Pixel Rate | 42.12 GPixel/s | 180.5 GPixel/s |
| Texture Rate | 800.3 GTexel/s | 394.8 GTexel/s |
| FP16 (half) | 204.9 TFLOPS | 50.53 TFLOPS |
| FP32 (float) | 51.22 TFLOPS | 12.63 TFLOPS |
| FP64 (double) | 25.61 TFLOPS | 6.317 TFLOPS |
| Graphics Processor | ||
| GPU Name | GH100 | GA100 |
| Architecture | Hopper | Ampere |
| Foundry | TSMC | TSMC |
| Process Size | 4 nm | 7 nm |
| Transistors | 80 billion | 54.2 billion |
| Die Size | 814 mm² | 826 mm² |
| GPU Variant | GA100-105F-A1 | |
| Board Design | ||
| TDP | 350W | 250W |
| Suggested PSU | 750 W | 600 W |
| Outputs | No outputs | No outputs |
| Power Connectors | 1x 16-pin | 2x 8-pin |
| Graphics Features | ||
| DirectX | N/A | N/A |
| OpenGL | N/A | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | N/A |
| CUDA | 9.0 | 8.0 |
| Shader Model | N/A | N/A |