Intel UHD Graphics P630 vs NVIDIA Jetson AGX Xavier GPU
Graphics Processor
| GPU model | Coffee Lake GT2 | GV10B |
|---|---|---|
| Architecture | Generation 9.5 | Volta |
| Foundry | Intel | TSMC |
| Manufacturing process | 14 nm+++ | 12 nm |
| Number of transistors | unknown | 9,000 million |
| Die size | unknown | 350 mm² |
Integrated Graphics
| Release date | May 24th, 2018 | Oct 2018 |
|---|---|---|
| Generation | HD Graphics-W (Coffee Lake) | Tegra |
| Production | Active | End-of-life |
| Interface | Ring Bus | IGP |
| Reviews | 1 in our database | — |
| Launch price | — | 899 USD |
Clocks
| Base clock | 350 MHz | 854 MHz |
|---|---|---|
| Boost clock | 1100 MHz | 1377 MHz |
| Memory clock | System Shared | System Shared |
Memory Configuration
| Memory size | System Shared | System Shared |
|---|---|---|
| Memory type | System Shared | System Shared |
| Memory bus width | System Shared | System Shared |
| Bandwidth | System Dependent | System Dependent |
Render Configuration
| Shading units | 192 | 512 |
|---|---|---|
| TMUs | 24 | 32 |
| ROPs | 3 | 16 |
| Execution units | 24 | — |
| SM count | — | 8 |
| Tensor cores | — | 64 |
| Cache L1 | — | 128 KB (per SM) |
| Cache L2 | — | 512 KB |
Performance
| Pixel rate | 3.300 GPixel/s | 22.03 GPixel/s |
|---|---|---|
| Texture rate | 26.40 GTexel/s | 44.06 GTexel/s |
| FP16 (half) performance | 844.8 GFLOPS (2:1) | 2.820 TFLOPS (2:1) |
| FP32 (float) performance | 422.4 GFLOPS | 1,410 GFLOPS |
| FP64 (double) performance | 105.6 GFLOPS (1:4) | 705.0 GFLOPS (1:2) |
Dimensions & Outputs
| Slot width | IGP | IGP |
|---|---|---|
| TDP | 15 W | 30 W |
| Outputs | No outputs | No outputs |
| Length | — | 100 mm 3.9 inches |
| Width | — | 87 mm 3.4 inches |
API Support & Features
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 1.2 |
| Vulkan | 1.2 | 1.2 |
| Shader model | 6.4 | 6.4 |
| CUDA | — | 7.2 |
