Product Compare
NVIDIA GRID A100B vs NVIDIA RTX A2000 Max-Q
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | May 2020 | Apr 2021 |
| Generation | GRID | Ampere-MW |
| Type | Professional | Mobile |
| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 900 MHz | 682 MHz |
| Boost Clock | 1005 MHz | 1207 MHz |
| Memory Clock | 1215 MHz | 1375 MHz |
| Memory | ||
| Memory Size | 48GB | 4GB |
| Memory Type | HBM2e | GDDR6 |
| Memory Bus | 6144bit | 128bit |
| Bandwidth | 1.87TB/s | 176.0GB/s |
| Render Config | ||
| SM Count | 108 | 20 |
| Shading Units | 6912 | 2560 |
| TMUs | 432 | 80 |
| ROPs | 192 | 48 |
| Tensor Cores | 432 | 80 |
| L1 Cache | 192 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 48 MB | 2 MB |
| RT Cores | 20 | |
| Theoretical Performance | ||
| Pixel Rate | 193.0 GPixel/s | 57.94 GPixel/s |
| Texture Rate | 434.2 GTexel/s | 96.56 GTexel/s |
| FP16 (half) | 55.57 TFLOPS | 6.180 TFLOPS |
| FP32 (float) | 13.89 TFLOPS | 6.180 TFLOPS |
| FP64 (double) | 6.947 TFLOPS | 96.56 GFLOPS |
| Graphics Processor | ||
| GPU Name | GA100 | GA107 |
| Architecture | Ampere | Ampere |
| Foundry | TSMC | Samsung |
| Process Size | 7 nm | 8 nm |
| Transistors | 54.2 billion | 8.7 billion |
| Die Size | 826 mm² | 200 mm² |
| Board Design | ||
| TDP | 400W | 95W |
| Suggested PSU | 800 W | |
| Outputs | No outputs | Portable Device Dependent |
| Power Connectors | None | None |
| Graphics Features | ||
| DirectX | N/A | 12 Ultimate (12_2) |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | 1.3 |
| CUDA | 8.0 | 8.6 |
| Shader Model | N/A | 6.8 |