AMD Radeon Instinct MI60 vs NVIDIA GeForce RTX 3080
What is the difference between AMD Radeon Instinct MI60 and NVIDIA GeForce RTX 3080. Find out which graphics card has better performance.
Graphics Processor (GPU)
| Vega 20 | GPU Name | GA102 |
| Vega 20 GL | Model number | GA102-200-KD-A1 |
| GCN 5.1 | Architecture | Ampere |
| TSMC | Foundry | Samsung |
| 7 nm | Process Size | 8 nm |
| 13,230 million | Transistors | 28,300 million |
| 331 mm² | Die Size | 628 mm² |
Graphics Card
| Nov 18th, 2018 | Release Date | Sep 1st, 2020 |
| Radeon Instinct (MIx) | Family | GeForce 30 |
| Active | Production | Active |
| PCIe 4.0 x16 | Bus Interface | PCIe 4.0 x16 |
Memory
| 32 GB | Memory Size | 10 GB |
| HBM2 | Memory Type | GDDR6X |
| 4096 bit | Memory Bus | 320 bit |
| 1,024 GB/s | Bandwidth | 760.3 GB/s |
Performance
| 115.2 GPixel/s | Pixel fillrate | 164.2 GPixel/s |
| 460.8 GTexel/s | Texture fillrate | 465.1 GTexel/s |
| 29.49 TFLOPS (2:1) | FP16 (half) performance | 29.77 TFLOPS (1:1) |
| 14.75 TFLOPS | FP32 (float) performance | 29.77 TFLOPS |
| 7.373 TFLOPS (1:2) | FP64 (double) performance | 465.1 GFLOPS (1:64) |
Clock Speeds
| 1200 MHz | Base Clock | 1440 MHz |
| 1800 MHz | Boost Clock | 1710 MHz |
| 1000 MHz 2 Gbps effective | Memory Clock | 1188 MHz 19 Gbps effective |
Render Config
| 4096 | Shading Units | 8704 |
| 256 | TMUs | 272 |
| 64 | ROPs | 96 |
| 16 KB (per CU) | L1 Cache | 128 KB (per SM) |
| 4 MB | L2 Cache | 5 MB |
Board Design
| Dual-slot | Slot Width | Dual-slot |
| 267 mm 10.5 inches | Length | 285 mm 11.2 inches |
| 111 mm 4.4 inches | Width | 112 mm 4.4 inches |
| 300 W | Thermal design power (TDP) | 320 W |
| 700 W | Suggested PSU | 700 W |
| 1x mini-DisplayPort | Display Connectors | 1x HDMI 3x DisplayPort |
| 1x 6-pin + 1x 8-pin | Power Connectors | 1x 12-pin |
API support
| 12 (12_1) | DirectX | 12 Ultimate (12_2) |
| 4.6 | OpenGL | 4.6 |
| 2.1 | OpenCL | 3.0 |
| 1.2 | Vulkan | 1.2 |
| 6.4 | Shader Model | 6.6 |