Product Compare
NVIDIA GeForce GTX 870M vs Intel Data Center GPU Flex 170
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Mar 2014 | Aug 2022 |
| Generation | GeForce 800M | Data Center GPU |
| Type | Mobile | Professional |
| Bus Interface | MXM-B (3.0) | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 941 MHz | 1950 MHz |
| Boost Clock | 967 MHz | 2050 MHz |
| Memory Clock | 1250 MHz | 2000 MHz |
| Memory | ||
| Memory Size | 3GB | 16GB |
| Memory Type | GDDR5 | GDDR6 |
| Memory Bus | 192bit | 256bit |
| Bandwidth | 120.0GB/s | 512.0GB/s |
| Render Config | ||
| Shading Units | 1344 | 4096 |
| TMUs | 112 | 256 |
| ROPs | 24 | 128 |
| L1 Cache | 16 KB (per SMX) | |
| L2 Cache | 384 KB | 16 MB |
| RT Cores | 32 | |
| Theoretical Performance | ||
| Pixel Rate | 27.08 GPixel/s | 262.4 GPixel/s |
| Texture Rate | 108.3 GTexel/s | 524.8 GTexel/s |
| FP32 (float) | 2.599 TFLOPS | 16.79 TFLOPS |
| FP64 (double) | 108.3 GFLOPS | |
| FP16 (half) | 33.59 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GK104 | DG2-512 |
| GPU Variant | N15E-GT-A2 | ACM-G10 |
| Architecture | Kepler | Generation 12.7 |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 6 nm |
| Transistors | 3.54 billion | 21.7 billion |
| Die Size | 294 mm² | 406 mm² |
| Board Design | ||
| TDP | 100W | 150W |
| Outputs | No outputs | 1x HDMI 2.13x DisplayPort 2.0 |
| Power Connectors | None | 1x 8-pin |
| Suggested PSU | 450 W | |
| Graphics Features | ||
| DirectX | 12 (11_0) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.1 | 1.3 |
| CUDA | 3.0 | |
| Shader Model | 5.1 | 6.6 |