Product Compare
NVIDIA Tesla P6 vs NVIDIA Tesla M40
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Mar 2017 | Nov 2015 |
| Generation | Tesla | Tesla Maxwell |
| Type | Professional | Professional |
| Bus Interface | MXM-B (3.0) | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 1012 MHz | 948 MHz |
| Boost Clock | 1506 MHz | 1112 MHz |
| Memory Clock | 1502 MHz | 1502 MHz |
| Memory | ||
| Memory Size | 16GB | 12GB |
| Memory Type | GDDR5 | GDDR5 |
| Memory Bus | 256bit | 384bit |
| Bandwidth | 192.3GB/s | 288.4GB/s |
| Render Config | ||
| SM Count | 16 | |
| Shading Units | 2048 | 3072 |
| TMUs | 128 | 192 |
| ROPs | 64 | 96 |
| L1 Cache | 48 KB (per SM) | 48 KB (per SMM) |
| L2 Cache | 2 MB | 3 MB |
| Theoretical Performance | ||
| Pixel Rate | 96.38 GPixel/s | 106.8 GPixel/s |
| Texture Rate | 192.8 GTexel/s | 213.5 GTexel/s |
| FP16 (half) | 96.38 GFLOPS | |
| FP32 (float) | 6.169 TFLOPS | 6.832 TFLOPS |
| FP64 (double) | 192.8 GFLOPS | 213.5 GFLOPS |
| Graphics Processor | ||
| GPU Name | GP104 | GM200 |
| GPU Variant | GP104-995-A1 | GM200-895-A1 |
| Architecture | Pascal | Maxwell 2.0 |
| Foundry | TSMC | TSMC |
| Process Size | 16 nm | 28 nm |
| Transistors | 7.2 billion | 8 billion |
| Die Size | 314 mm² | 601 mm² |
| Board Design | ||
| TDP | 90W | 250W |
| Suggested PSU | 250 W | 600 W |
| Outputs | No outputs | No outputs |
| Power Connectors | None | 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 | 1.3 |
| CUDA | 6.1 | 5.2 |
| Shader Model | 6.4 | 6.7 |