Product Compare
NVIDIA L40S vs Intel Arc A780
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Oct 2022 | Unknown |
| Generation | Server Ada | Alchemist(Arc 7) |
| Type | Professional | Desktop |
| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1065 MHz | 2200 MHz |
| Boost Clock | 2520 MHz | 2200 MHz |
| Memory Clock | 2250 MHz | 1093 MHz |
| Memory | ||
| Memory Size | 48GB | 16GB |
| Memory Type | GDDR6 | GDDR6X |
| Memory Bus | 384bit | 256bit |
| Bandwidth | 864.0GB/s | 559.6GB/s |
| Render Config | ||
| SM Count | 142 | |
| Shading Units | 18176 | 4096 |
| TMUs | 568 | 256 |
| ROPs | 192 | 128 |
| Tensor Cores | 568 | 512 |
| RT Cores | 142 | 32 |
| L1 Cache | 128 KB (per SM) | |
| L2 Cache | 48 MB | 16 MB |
| Theoretical Performance | ||
| Pixel Rate | 483.8 GPixel/s | 281.6 GPixel/s |
| Texture Rate | 1431.4 GTexel/s | 563.2 GTexel/s |
| FP16 (half) | 91.61 TFLOPS | 36.04 TFLOPS |
| FP32 (float) | 91.61 TFLOPS | 18.02 TFLOPS |
| FP64 (double) | 1431.4 GFLOPS | 2.253 TFLOPS |
| Graphics Processor | ||
| GPU Name | AD102 | DG2-512 |
| GPU Variant | AD102-896-A1 | ACM-G10 |
| Architecture | Ada Lovelace | Generation 12.7 |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 6 nm |
| Transistors | 76.3 billion | 21.7 billion |
| Die Size | 609 mm² | 406 mm² |
| Board Design | ||
| TDP | 350W | 200W |
| Suggested PSU | 750 W | 550 W |
| Outputs | 4x DisplayPort 1.4a | 1x HDMI 2.13x DisplayPort 2.0 |
| Power Connectors | 1x 16-pin | 2x 8-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 | 8.9 | |
| Shader Model | 6.9 | 6.6 |