NVIDIA P102-100 vs AMD Radeon Pro Vega 64
What is the difference between NVIDIA P102-100 and AMD Radeon Pro Vega 64. Find out which graphics card has better performance.
Graphics Processor (GPU)
| GP102 | GPU Name | Vega 10 |
| GP102-100-A1 | Model number | Vega 10 XT (215-0894200) |
| Pascal | Architecture | GCN 5.0 |
| TSMC | Foundry | GlobalFoundries |
| 16 nm | Process Size | 14 nm |
| 11,800 million | Transistors | 12,500 million |
| 471 mm² | Die Size | 495 mm² |
Graphics Card
| Feb 12th, 2018 | Release Date | Jun 27th, 2017 |
| Mining GPUs | Family | Radeon Pro Mac (Vega Series) |
| Active | Production | Active |
| PCIe 3.0 x4 | Bus Interface | PCIe 3.0 x16 |
Memory
| 5 GB | Memory Size | 16 GB |
| GDDR5X | Memory Type | HBM2 |
| 320 bit | Memory Bus | 2048 bit |
| 440.3 GB/s | Bandwidth | 402.4 GB/s |
Performance
| 134.6 GPixel/s | Pixel fillrate | 86.40 GPixel/s |
| 336.6 GTexel/s | Texture fillrate | 345.6 GTexel/s |
| 168.3 GFLOPS (1:64) | FP16 (half) performance | 22.12 TFLOPS (2:1) |
| 10.77 TFLOPS | FP32 (float) performance | 11.06 TFLOPS |
| 336.6 GFLOPS (1:32) | FP64 (double) performance | 691.2 GFLOPS (1:16) |
Clock Speeds
| 1582 MHz | Base Clock | 1250 MHz |
| 1683 MHz | Boost Clock | 1350 MHz |
| 1376 MHz 11 Gbps effective | Memory Clock | 786 MHz 1572 Mbps effective |
Render Config
| 3200 | Shading Units | 4096 |
| 200 | TMUs | 256 |
| 80 | ROPs | 64 |
| 48 KB (per SM) | L1 Cache | 16 KB (per CU) |
| 2.5 MB | L2 Cache | 4 MB |
Board Design
| Dual-slot | Slot Width | IGP |
| 250 W | Thermal design power (TDP) | 250 W |
| No outputs | Display Connectors | No outputs |
| 2x 8-pin | Power Connectors | None |
API support
| 12 (12_1) | DirectX | 12 (12_1) |
| 4.6 | OpenGL | 4.6 |
| 3.0 | OpenCL | 2.1 |
| 1.2 | Vulkan | 1.2 |
| 6.4 | Shader Model | 6.4 |