Product Compare
NVIDIA Tesla T40 24 GB vs NVIDIA A800 SXM4 80 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Unknown | Aug 2022 |
| Generation | Tesla Turing | Ampere |
| Type | Professional | AI GPU |
| Bus Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1305 MHz | 1155 MHz |
| Boost Clock | 1560 MHz | 1410 MHz |
| Memory Clock | 1625 MHz | 1593 MHz |
| Memory | ||
| Memory Size | 24GB | 80GB |
| Memory Type | GDDR6 | HBM2e |
| Memory Bus | 384bit | 5120bit |
| Bandwidth | 624.0GB/s | 2039GB/s |
| Render Config | ||
| SM Count | 72 | 108 |
| Shading Units | 4608 | 6912 |
| TMUs | 288 | 432 |
| ROPs | 96 | 160 |
| Tensor Cores | 576 | 432 |
| RT Cores | 72 | |
| L1 Cache | 64 KB (per SM) | 192 KB (per SM) |
| L2 Cache | 6 MB | 40 MB |
| Theoretical Performance | ||
| Pixel Rate | 149.8 GPixel/s | 225.6 GPixel/s |
| Texture Rate | 449.3 GTexel/s | 609.1 GTexel/s |
| FP16 (half) | 28.75 TFLOPS | 77.97 TFLOPS |
| FP32 (float) | 14.38 TFLOPS | 19.49 TFLOPS |
| FP64 (double) | 449.3 GFLOPS | 9.746 TFLOPS |
| Graphics Processor | ||
| GPU Name | TU102 | GA100 |
| Architecture | Turing | Ampere |
| Foundry | TSMC | TSMC |
| Process Size | 12 nm | 7 nm |
| Transistors | 18.6 billion | 54.2 billion |
| Die Size | 754 mm² | 826 mm² |
| Board Design | ||
| TDP | 250W | 400W |
| Suggested PSU | 600 W | 800 W |
| Outputs | No outputs | No outputs |
| Power Connectors | 1x 8-pin | None |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | N/A |
| CUDA | 7.5 | 8.0 |
| Shader Model | 6.8 | N/A |