Product Compare
NVIDIA GRID A100A vs NVIDIA Tesla K40s
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | May 2020 | Nov 2013 |
| Generation | GRID | Tesla Kepler |
| Type | Professional | Professional |
| Bus Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 1095 MHz | 706 MHz |
| Boost Clock | 1410 MHz | 706 MHz |
| Memory Clock | 1215 MHz | 1502 MHz |
| Memory | ||
| Memory Size | 32GB | 12GB |
| Memory Type | HBM2e | GDDR5 |
| Memory Bus | 6144bit | 384bit |
| Bandwidth | 1.87TB/s | 288.4GB/s |
| Render Config | ||
| SM Count | 108 | |
| Shading Units | 6912 | 2880 |
| TMUs | 432 | 240 |
| ROPs | 192 | 48 |
| Tensor Cores | 432 | |
| L1 Cache | 192 KB (per SM) | 16 KB (per SMX) |
| L2 Cache | 32 MB | 1536 KB |
| Theoretical Performance | ||
| Pixel Rate | 270.7 GPixel/s | 42.36 GPixel/s |
| Texture Rate | 609.1 GTexel/s | 169.4 GTexel/s |
| FP16 (half) | 77.97 TFLOPS | |
| FP32 (float) | 19.49 TFLOPS | 4.067 TFLOPS |
| FP64 (double) | 9.746 TFLOPS | 1355.5 GFLOPS |
| Graphics Processor | ||
| GPU Name | GA100 | GK110B |
| Architecture | Ampere | Kepler |
| Foundry | TSMC | TSMC |
| Process Size | 7 nm | 28 nm |
| Transistors | 54.2 billion | 7.08 billion |
| Die Size | 826 mm² | 561 mm² |
| Board Design | ||
| TDP | 400W | 245W |
| Suggested PSU | 800 W | 550 W |
| Outputs | No outputs | No outputs |
| Power Connectors | None | |
| Graphics Features | ||
| DirectX | N/A | 12 (11_1) |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | 1.2.175 |
| CUDA | 8.0 | 3.5 |
| Shader Model | N/A | 6.5 (5.1) |