Product Compare
NVIDIA CMP 90HX vs NVIDIA L40S
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Jul 2021 | Oct 2022 |
| Generation | Mining GPUs | Server Ada |
| Type | Desktop | Professional |
| Bus Interface | PCIe 1.0 x4 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1500 MHz | 1065 MHz |
| Boost Clock | 1710 MHz | 2520 MHz |
| Memory Clock | 1188 MHz | 2250 MHz |
| Memory | ||
| Memory Size | 10GB | 48GB |
| Memory Type | GDDR6X | GDDR6 |
| Memory Bus | 320bit | 384bit |
| Bandwidth | 760.3GB/s | 864.0GB/s |
| Render Config | ||
| SM Count | 50 | 142 |
| Shading Units | 6400 | 18176 |
| TMUs | 200 | 568 |
| ROPs | 80 | 192 |
| Tensor Cores | 200 | 568 |
| RT Cores | 50 | 142 |
| L1 Cache | 128 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 5 MB | 48 MB |
| Theoretical Performance | ||
| Pixel Rate | 136.8 GPixel/s | 483.8 GPixel/s |
| Texture Rate | 342.0 GTexel/s | 1431.4 GTexel/s |
| FP16 (half) | 21.89 TFLOPS | 91.61 TFLOPS |
| FP32 (float) | 21.89 TFLOPS | 91.61 TFLOPS |
| FP64 (double) | 342.0 GFLOPS | 1431.4 GFLOPS |
| Graphics Processor | ||
| GPU Name | GA102 | AD102 |
| GPU Variant | GA102-100-A1 | AD102-896-A1 |
| Architecture | Ampere | Ada Lovelace |
| Foundry | Samsung | TSMC |
| Process Size | 8 nm | 5 nm |
| Transistors | 28.3 billion | 76.3 billion |
| Die Size | 628 mm² | 609 mm² |
| Board Design | ||
| TDP | 320W | 350W |
| Suggested PSU | 700 W | 750 W |
| Outputs | No outputs | 4x DisplayPort 1.4a |
| Power Connectors | 2x 8-pin | 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 | 1.3 | 1.4 |
| CUDA | 8.6 | 8.9 |
| Shader Model | 6.8 | 6.9 |