NVIDIA P102-101 vs AMD Radeon Pro W6600
What is the difference between NVIDIA P102-101 and AMD Radeon Pro W6600. Find out which graphics card has better performance.
Graphics Processor (GPU)
| GP102 | GPU Name | Navi 23 |
| Pascal | Architecture | RDNA 2.0 |
| TSMC | Foundry | TSMC |
| 16 nm | Process Size | 7 nm |
| 11,800 million | Transistors | 11,060 million |
| 471 mm² | Die Size | 237 mm² |
Graphics Card
| 2018 | Release Date | Jun 8th, 2021 |
| Mining GPUs | Family | Radeon Pro (Navi II Series) |
| Active | Production | Active |
| PCIe 3.0 x4 | Bus Interface | PCIe 4.0 x16 |
Memory
| 10 GB | Memory Size | 8 GB |
| GDDR5 | Memory Type | GDDR6 |
| 320 bit | Memory Bus | 128 bit |
| 320.3 GB/s | Bandwidth | 224.0 GB/s |
Performance
| 133.6 GPixel/s | Pixel fillrate | 185.8 GPixel/s |
| 334.0 GTexel/s | Texture fillrate | 325.1 GTexel/s |
| 167.0 GFLOPS (1:64) | FP16 (half) performance | 20.81 TFLOPS (2:1) |
| 10.69 TFLOPS | FP32 (float) performance | 10.40 TFLOPS |
| 334.0 GFLOPS (1:32) | FP64 (double) performance | 650.3 GFLOPS (1:16) |
Clock Speeds
| 1557 MHz | Base Clock | 2331 MHz |
| 1670 MHz | Boost Clock | 2903 MHz |
| 2002 MHz 8 Gbps effective | Memory Clock | 1750 MHz 14 Gbps effective |
Render Config
| 3200 | Shading Units | 1792 |
| 200 | TMUs | 112 |
| 80 | ROPs | 64 |
| 48 KB (per SM) | L1 Cache | 128 KB per Array |
| 2.5 MB | L2 Cache | 2 MB |
Board Design
| Dual-slot | Slot Width | Single-slot |
| 267 mm 10.5 inches | Length | 241 mm 9.5 inches |
| 250 W | Thermal design power (TDP) | 100 W |
| 600 W | Suggested PSU | 300 W |
| No outputs | Display Connectors | 4x DisplayPort |
| 2x 8-pin | Power Connectors | 1x 6-pin |
API support
| 12 (12_1) | DirectX | 12.0 Ultimate (12_2) |
| 4.6 | OpenGL | 4.6 |
| 3.0 | OpenCL | 2.1 |
| 1.2 | Vulkan | 1.2 |
| 6.4 | Shader Model | 6.5 |