Product Compare
NVIDIA Jetson AGX Orin 32 GB vs NVIDIA L40
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Feb 2023 | Oct 2022 |
| Generation | Tegra | Tesla Ada |
| Type | Professional | Professional |
| Bus Interface | PCIe 4.0 x4 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Memory Clock | 800 MHz | 2250 MHz |
| Base Clock | 735 MHz | |
| Boost Clock | 2490 MHz | |
| Memory | ||
| Memory Size | 32GB | 48GB |
| Memory Type | LPDDR5 | GDDR6 |
| Memory Bus | 256bit | 384bit |
| Bandwidth | 204.8GB/s | 864.0GB/s |
| Render Config | ||
| SM Count | 14 | 142 |
| Shading Units | 1792 | 18176 |
| TMUs | 56 | 568 |
| ROPs | 24 | 192 |
| Tensor Cores | 56 | 568 |
| L1 Cache | 128 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 6 MB | 96 MB |
| RT Cores | 142 | |
| Theoretical Performance | ||
| Pixel Rate | 22.32 GPixel/s | 478.1 GPixel/s |
| Texture Rate | 52.08 GTexel/s | 1414 GTexel/s |
| FP16 (half) | 6.666 TFLOPS | 90.52 TFLOPS |
| FP32 (float) | 3.333 TFLOPS | 90.52 TFLOPS |
| FP64 (double) | 1.667 TFLOPS | 1414 GFLOPS |
| Graphics Processor | ||
| GPU Name | GA10B | AD102 |
| Architecture | Ampere | Ada Lovelace |
| Foundry | Samsung | TSMC |
| Process Size | 8 nm | 4 nm |
| Transistors | Unknown | 76.3 billion |
| Die Size | 200 mm² | 608 mm² |
| GPU Variant | AD102-895-A1 | |
| Board Design | ||
| TDP | 40W | 300W |
| Outputs | Portable Device Dependent | 4x DisplayPort 1.4a |
| Suggested PSU | 700 W | |
| Power Connectors | 1x 16-pin | |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.4 | 1.3 |
| CUDA | 8.7 | 8.9 |
| Shader Model | 6.8 | 6.6 |