Product Compare
NVIDIA Tesla M40 vs Intel Data Center GPU Max 1350
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2015 | Jan 2023 |
| Generation | Tesla Maxwell | Data Center GPU |
| Type | Professional | Professional |
| Bus Interface | PCIe 3.0 x16 | PCIe 5.0 x16 |
| Clock Speeds | ||
| Base Clock | 948 MHz | 750 MHz |
| Boost Clock | 1112 MHz | 1550 MHz |
| Memory Clock | 1502 MHz | 1200 MHz |
| Memory | ||
| Memory Size | 12GB | 96GB |
| Memory Type | GDDR5 | HBM2e |
| Memory Bus | 384bit | 8192bit |
| Bandwidth | 288.4GB/s | 2458GB/s |
| Render Config | ||
| Shading Units | 3072 | 14336 |
| TMUs | 192 | 896 |
| ROPs | 96 | 0 |
| L1 Cache | 48 KB (per SMM) | 64 KB (per EU) |
| L2 Cache | 3 MB | 408 MB |
| Tensor Cores | 896 | |
| RT Cores | 112 | |
| Theoretical Performance | ||
| Pixel Rate | 106.8 GPixel/s | 0 MPixel/s |
| Texture Rate | 213.5 GTexel/s | 1389 GTexel/s |
| FP32 (float) | 6.832 TFLOPS | 44.44 TFLOPS |
| FP64 (double) | 213.5 GFLOPS | 44.44 TFLOPS |
| FP16 (half) | 44.44 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GM200 | Ponte Vecchio |
| GPU Variant | GM200-895-A1 | |
| Architecture | Maxwell 2.0 | Generation 12.5 |
| Foundry | TSMC | Intel |
| Process Size | 28 nm | 10 nm |
| Transistors | 8 billion | 100 billion |
| Die Size | 601 mm² | 1280 mm² |
| Board Design | ||
| TDP | 250W | 450W |
| Suggested PSU | 600 W | 850 W |
| Outputs | No outputs | No outputs |
| Power Connectors | 8-pin EPS | |
| Graphics Features | ||
| DirectX | 12 (12_1) | 12 (12_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | N/A |
| CUDA | 5.2 | |
| Shader Model | 6.7 | 6.6 |