AMD Radeon RX 560 896SP vs NVIDIA GeForce GTX 1050 Ti
What is the difference between AMD Radeon RX 560 896SP and NVIDIA GeForce GTX 1050 Ti. Find out which graphics card has better performance.
Graphics Processor (GPU)
| Polaris 21 | GPU Name | GP107 |
| Polaris 21 XL | Model number | GP107-400-A1 |
| GCN 4.0 | Architecture | Pascal |
| GlobalFoundries | Foundry | Samsung |
| 14 nm | Process Size | 14 nm |
| 3,000 million | Transistors | 3,300 million |
| 123 mm² | Die Size | 132 mm² |
Graphics Card
| Jul 4th, 2017 | Release Date | Oct 25th, 2016 |
| Polaris (RX 500) | Family | GeForce 10 |
| Active | Production | Active |
| Arctic Islands | Predecessor | GeForce 900 |
| PCIe 3.0 x8 | Bus Interface | PCIe 3.0 x16 |
Memory
| 4 GB | Memory Size | 4 GB |
| GDDR5 | Memory Type | GDDR5 |
| 128 bit | Memory Bus | 128 bit |
| 112.0 GB/s | Bandwidth | 112.1 GB/s |
Performance
| 18.80 GPixel/s | Pixel fillrate | 44.54 GPixel/s |
| 65.80 GTexel/s | Texture fillrate | 66.82 GTexel/s |
| 2.106 TFLOPS (1:1) | FP16 (half) performance | 33.41 GFLOPS (1:64) |
| 2.106 TFLOPS | FP32 (float) performance | 2.138 TFLOPS |
| 131.6 GFLOPS (1:16) | FP64 (double) performance | 66.82 GFLOPS (1:32) |
Clock Speeds
| 1090 MHz | Base Clock | 1291 MHz |
| 1175 MHz | Boost Clock | 1392 MHz |
| 1750 MHz 7 Gbps effective | Memory Clock | 1752 MHz 7 Gbps effective |
Render Config
| 896 | Shading Units | 768 |
| 56 | TMUs | 48 |
| 16 | ROPs | 32 |
| 16 KB (per CU) | L1 Cache | 48 KB (per SM) |
| 1024 KB | L2 Cache | 1024 KB |
Board Design
| Dual-slot | Slot Width | Dual-slot |
| 170 mm 6.7 inches | Length | 145 mm 5.7 inches |
| 45 W | Thermal design power (TDP) | 75 W |
| 200 W | Suggested PSU | 250 W |
| 1x DVI 1x HDMI 1x DisplayPort | Display Connectors | 1x DVI 1x HDMI 1x DisplayPort |
| None | Power Connectors | None |
| C981-21 C994-71 | Board Number | PG210 |
API support
| 12 (12_0) | DirectX | 12 (12_1) |
| 4.6 | OpenGL | 4.6 |
| 2.1 | OpenCL | 3.0 |
| 1.2 | Vulkan | 1.2 |
| 6.4 | Shader Model | 6.4 |