Intel Xe DG1 vs NVIDIA GeForce GTX 950
Graphics Processor
| GPU model | DG1 | GM206 |
|---|---|---|
| Architecture | Generation 12.1 | Maxwell 2.0 |
| Foundry | Intel | TSMC |
| Manufacturing process | 10 nm | 28 nm |
| Number of transistors | unknown | 2,940 million |
| Die size | 95 mm² | 228 mm² |
| GPU variant | — | GM206-250-A1 |
Graphics Card
| Release date | Never Released | Aug 20th, 2015 |
|---|---|---|
| Generation | Xe Graphics | GeForce 900 |
| Production | Active | End-of-life |
| Interface | PCIe 3.0 x4 | PCIe 3.0 x16 |
| Launch price | — | 159 USD |
| Reviews | — | 76 in our database |
| Predecessor | — | GeForce 700 |
| Successor | — | GeForce 10 |
Clocks
| Base clock | 900 MHz | 1024 MHz |
|---|---|---|
| Boost clock | 1550 MHz | 1188 MHz |
| Memory clock | 2133 MHz 4.3 Gbps effective | 1653 MHz 6.6 Gbps effective |
Memory Configuration
| Memory size | 4 GB | 2 GB |
|---|---|---|
| Memory type | LPDDR4X | GDDR5 |
| Memory bus width | 128 bit | 128 bit |
| Bandwidth | 68.26 GB/s | 105.8 GB/s |
Render Configuration
| Shading units | 640 | 768 |
|---|---|---|
| TMUs | 40 | 48 |
| ROPs | 20 | 32 |
| Execution units | 80 | — |
| Cache L2 | 1024 KB | 1024 KB |
| gpu.details.l3-cache | 16 MB | — |
| SMM count | — | 6 |
| Cache L1 | — | 48 KB (per SMM) |
Performance
| Pixel rate | 31.00 GPixel/s | 38.02 GPixel/s |
|---|---|---|
| Texture rate | 62.00 GTexel/s | 57.02 GTexel/s |
| FP16 (half) performance | 3.968 TFLOPS (2:1) | — |
| FP32 (float) performance | 1.984 TFLOPS | 1.825 TFLOPS |
| FP64 (double) performance | 496.0 GFLOPS (1:4) | 57.02 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | Dual-slot | Dual-slot |
|---|---|---|
| Length | 178 mm 7 inches | 202 mm 8 inches |
| TDP | 30 W | 90 W |
| Suggested PSU | 200 W | 250 W |
| Outputs | 1x HDMI3x DisplayPort | 1x DVI1x HDMI3x DisplayPort |
| Power connectors | None | 1x 6-pin |
API Support & Features
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| Shader model | 6.4 | 6.4 |
| CUDA | — | 5.2 |