Product Compare
NVIDIA Tesla M40 24 GB vs NVIDIA Tesla K80
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2015 | Nov 2014 |
| Generation | Tesla Maxwell | Tesla |
| Type | Professional | Professional |
| Bus Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 948 MHz | 562 MHz |
| Boost Clock | 1112 MHz | 824 MHz |
| Memory Clock | 1502 MHz | 1253 MHz |
| Memory | ||
| Memory Size | 24GB | 12GB |
| Memory Type | GDDR5 | GDDR5 |
| Memory Bus | 384bit | 384bit |
| Bandwidth | 288.4GB/s | 240.6GB/s |
| Render Config | ||
| Shading Units | 3072 | 2496 |
| TMUs | 192 | 208 |
| ROPs | 96 | 48 |
| L1 Cache | 48 KB (per SMM) | 16 KB (per SMX) |
| L2 Cache | 3 MB | 1536 KB |
| Theoretical Performance | ||
| Pixel Rate | 106.8 GPixel/s | 42.85 GPixel/s |
| Texture Rate | 213.5 GTexel/s | 171.4 GTexel/s |
| FP32 (float) | 6.832 TFLOPS | 4.113 TFLOPS |
| FP64 (double) | 213.5 GFLOPS | 1371 GFLOPS |
| Graphics Processor | ||
| GPU Name | GM200 | GK210 |
| GPU Variant | GM200-895-A1 | GK210-885-A1 |
| Architecture | Maxwell 2.0 | Kepler 2.0 |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 28 nm |
| Transistors | 8 billion | 7.1 billion |
| Die Size | 601 mm² | 561 mm² |
| Board Design | ||
| TDP | 250W | 300W |
| Suggested PSU | 600 W | 700 W |
| Outputs | No outputs | No outputs |
| Power Connectors | 8-pin EPS | 1x 8-pin |
| Graphics Features | ||
| DirectX | 12 (12_1) | 12 (11_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | 1.1 |
| CUDA | 5.2 | 3.7 |
| Shader Model | 6.7 | 5.1 |