Product Compare
NVIDIA Tesla K40st vs NVIDIA GeForce GTX 1070 Max Q
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2013 | Jun 2017 |
| Generation | Tesla | GeForce 10 Mobile |
| Type | Professional | Mobile |
| Bus Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Memory Clock | 1502 MHz | 2002 MHz |
| Base Clock | 1215 MHz | |
| Boost Clock | 1379 MHz | |
| Memory | ||
| Memory Size | 12GB | 8GB |
| Memory Type | GDDR5 | GDDR5 |
| Memory Bus | 384bit | 256bit |
| Bandwidth | 288.4GB/s | 256.3GB/s |
| Render Config | ||
| Shading Units | 2880 | 2048 |
| TMUs | 240 | 128 |
| ROPs | 48 | 64 |
| L1 Cache | 16 KB (per SMX) | 48 KB (per SM) |
| L2 Cache | 1536 KB | 2 MB |
| SM Count | 16 | |
| Theoretical Performance | ||
| Pixel Rate | 34.50 GPixel/s | 88.26 GPixel/s |
| Texture Rate | 138.0 GTexel/s | 176.5 GTexel/s |
| FP32 (float) | 3.312 TFLOPS | 5.648 TFLOPS |
| FP64 (double) | 1104 GFLOPS | 176.5 GFLOPS |
| FP16 (half) | 88.26 GFLOPS | |
| Graphics Processor | ||
| GPU Name | GK110B | GP104 |
| Architecture | Kepler | Pascal |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 16 nm |
| Transistors | 7.08 billion | 7.2 billion |
| Die Size | 561 mm² | 314 mm² |
| GPU Variant | N17E-G2-A1 | |
| Board Design | ||
| TDP | 245W | 115W |
| Suggested PSU | 550 W | |
| Outputs | No outputs | No outputs |
| Power Connectors | None | |
| Graphics Features | ||
| DirectX | 12 (11_1) | 12 (12_1) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.1 | 1.3 |
| CUDA | 3.5 | 6.1 |
| Shader Model | 5.1 | 6.4 |