Product Compare
AMD Radeon Instinct MI100 vs NVIDIA GeForce RTX 3060
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2020 | Jan 2021 |
| Generation | Radeon Instinct | GeForce 30 |
| Type | Professional | Desktop |
| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1000 MHz | 1320 MHz |
| Boost Clock | 1502 MHz | 1777 MHz |
| Memory Clock | 1200 MHz | 1875 MHz |
| Memory | ||
| Memory Size | 32GB | 12GB |
| Memory Type | HBM2 | GDDR6 |
| Memory Bus | 4096bit | 192bit |
| Bandwidth | 1229GB/s | 360.0GB/s |
| Render Config | ||
| Compute Units | 120 | |
| Shading Units | 7680 | 3584 |
| TMUs | 480 | 112 |
| ROPs | 64 | 48 |
| L1 Cache | 16 KB (per CU) | 128 KB (per SM) |
| L2 Cache | 8 MB | 3 MB |
| SM Count | 28 | |
| Tensor Cores | 112 | |
| RT Cores | 28 | |
| Theoretical Performance | ||
| Pixel Rate | 96.13 GPixel/s | 85.30 GPixel/s |
| Texture Rate | 721.0 GTexel/s | 199.0 GTexel/s |
| FP16 (half) | 184.6 TFLOPS | 12.74 TFLOPS |
| FP32 (float) | 23.07 TFLOPS | 12.74 TFLOPS |
| FP64 (double) | 11.54 TFLOPS | 199.0 GFLOPS |
| Graphics Processor | ||
| GPU Name | Arcturus | GA106 |
| GPU Variant | Arcturus XL | GA106-300-A1 |
| Architecture | CDNA 1.0 | Ampere |
| Foundry | TSMC | Samsung |
| Process Size | 7 nm | 8 nm |
| Transistors | 25.6 billion | 12 billion |
| Die Size | 750 mm² | 276 mm² |
| Board Design | ||
| TDP | 300W | 170W |
| Suggested PSU | 700 W | 450 W |
| Outputs | No outputs | 1x HDMI 2.13x DisplayPort 1.4a |
| Power Connectors | 2x 8-pin | 1x 12-pin |
| Graphics Features | ||
| DirectX | N/A | 12 Ultimate (12_2) |
| OpenGL | N/A | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | N/A | 1.3 |
| Shader Model | N/A | 6.6 |
| CUDA | 8.6 | |