Product Compare
NVIDIA Quadro GP100 vs NVIDIA H100 PCIe
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Oct 2016 | Mar 2022 |
| Generation | Quadro | Tesla Hopper |
| Type | Professional | AI GPU |
| Bus Interface | PCIe 3.0 x16 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 1304 MHz | 1095 MHz |
| Boost Clock | 1442 MHz | 1755 MHz |
| Memory Clock | 715 MHz | 1593 MHz |
| Memory | ||
| Memory Size | 16GB | 80GB |
| Memory Type | HBM2 | HBM2e |
| Memory Bus | 4096bit | 5120bit |
| Bandwidth | 732.2GB/s | 2039GB/s |
| Render Config | ||
| SM Count | 56 | 114 |
| Shading Units | 3584 | 14592 |
| TMUs | 224 | 456 |
| ROPs | 96 | 24 |
| L1 Cache | 24 KB (per SM) | 256 KB (per SM) |
| L2 Cache | 4 MB | 50 MB |
| Tensor Cores | 456 | |
| Theoretical Performance | ||
| Pixel Rate | 138.4 GPixel/s | 42.12 GPixel/s |
| Texture Rate | 323.0 GTexel/s | 800.3 GTexel/s |
| FP16 (half) | 20.67 TFLOPS | 204.9 TFLOPS |
| FP32 (float) | 10.34 TFLOPS | 51.22 TFLOPS |
| FP64 (double) | 5.168 TFLOPS | 25.61 TFLOPS |
| Graphics Processor | ||
| GPU Name | GP100 | GH100 |
| Architecture | Pascal | Hopper |
| Foundry | TSMC | TSMC |
| Process Size | 16 nm | 4 nm |
| Transistors | 15.3 billion | 80 billion |
| Die Size | 610 mm² | 814 mm² |
| Board Design | ||
| TDP | 235W | 350W |
| Suggested PSU | 550 W | 750 W |
| Outputs | 1x DVI4x DisplayPort 1.4a | No outputs |
| Power Connectors | 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 | 6.0 | 9.0 |
| Shader Model | 6.4 | N/A |