NVIDIA GeForce RTX 3080 vs AMD Radeon Pro Vega II
What is the difference between NVIDIA GeForce RTX 3080 and AMD Radeon Pro Vega II. Find out which graphics card has better performance.
Benchmarks
| 24437 | PassMark G3D | 14738 |
| 1003 | PassMark G2D | 827 |
Graphics Processor (GPU)
| GA102 | GPU Name | Vega 20 |
| GA102-200-KD-A1 | Model number | Vega 20 XT |
| Ampere | Architecture | GCN 5.1 |
| Samsung | Foundry | TSMC |
| 8 nm | Process Size | 7 nm |
| 28,300 million | Transistors | 13,230 million |
| 628 mm² | Die Size | 331 mm² |
Graphics Card
| Sep 1st, 2020 | Release Date | Jun 3rd, 2019 |
| GeForce 30 | Family | Radeon Pro Mac (Vega Series) |
| Active | Production | Active |
| PCIe 4.0 x16 | Bus Interface | PCIe 3.0 x16 |
Memory
| 10 GB | Memory Size | 32 GB |
| GDDR6X | Memory Type | HBM2 |
| 320 bit | Memory Bus | 4096 bit |
| 760.3 GB/s | Bandwidth | 825.3 GB/s |
Performance
| 164.2 GPixel/s | Pixel fillrate | 110.1 GPixel/s |
| 465.1 GTexel/s | Texture fillrate | 440.3 GTexel/s |
| 29.77 TFLOPS (1:1) | FP16 (half) performance | 28.18 TFLOPS (2:1) |
| 29.77 TFLOPS | FP32 (float) performance | 14.09 TFLOPS |
| 465.1 GFLOPS (1:64) | FP64 (double) performance | 880.6 GFLOPS (1:16) |
Clock Speeds
| 1440 MHz | Base Clock | 1574 MHz |
| 1710 MHz | Boost Clock | 1720 MHz |
| 1188 MHz 19 Gbps effective | Memory Clock | 806 MHz 1612 Mbps effective |
Render Config
| 8704 | Shading Units | 4096 |
| 272 | TMUs | 256 |
| 96 | ROPs | 64 |
| 128 KB (per SM) | L1 Cache | 16 KB (per CU) |
| 5 MB | L2 Cache | 4 MB |
Board Design
| Dual-slot | Slot Width | Quad-slot |
| 320 W | Thermal design power (TDP) | 475 W |
| 700 W | Suggested PSU | 850 W |
| 1x HDMI 3x DisplayPort | Display Connectors | 1x HDMI 4x Thunderbolt |
| 1x 12-pin | Power Connectors | None |
| PG132 SKU 30 | Board Number | MW672ZM/A |
API support
| 12 Ultimate (12_2) | DirectX | 12 (12_1) |
| 4.6 | OpenGL | 4.6 |
| 3.0 | OpenCL | 2.1 |
| 1.2 | Vulkan | 1.2 |
| 6.6 | Shader Model | 6.4 |