Product Compare
NVIDIA A100 SXM4 80 GB vs NVIDIA GeForce RTX 3060 8 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2020 | Oct 2022 |
| Generation | Tesla Ampere | GeForce 30 |
| Type | AI GPU | Desktop |
| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1275 MHz | 1320 MHz |
| Boost Clock | 1410 MHz | 1777 MHz |
| Memory Clock | 1593 MHz | 1875 MHz |
| Memory | ||
| Memory Size | 80GB | 8GB |
| Memory Type | HBM2e | GDDR6 |
| Memory Bus | 5120bit | 128bit |
| Bandwidth | 2039GB/s | 240.0GB/s |
| Render Config | ||
| SM Count | 108 | 28 |
| Shading Units | 6912 | 3584 |
| TMUs | 432 | 112 |
| ROPs | 160 | 48 |
| Tensor Cores | 432 | 112 |
| L1 Cache | 192 KB (per SM) | 128 KB (per SM) |
| L2 Cache | 40 MB | 3 MB |
| RT Cores | 28 | |
| Theoretical Performance | ||
| Pixel Rate | 225.6 GPixel/s | 85.30 GPixel/s |
| Texture Rate | 609.1 GTexel/s | 199.0 GTexel/s |
| FP16 (half) | 77.97 TFLOPS | 12.74 TFLOPS |
| FP32 (float) | 19.49 TFLOPS | 12.74 TFLOPS |
| FP64 (double) | 9.746 TFLOPS | 199.0 GFLOPS |
| Graphics Processor | ||
| GPU Name | GA100 | GA106 |
| Architecture | Ampere | Ampere |
| Foundry | TSMC | Samsung |
| Process Size | 7 nm | 8 nm |
| Transistors | 54.2 billion | 12 billion |
| Die Size | 826 mm² | 276 mm² |
| GPU Variant | GA106-302-A1 | |
| Board Design | ||
| TDP | 400W | 170W |
| Suggested PSU | 800 W | 450 W |
| Outputs | No outputs | 1x HDMI 2.13x DisplayPort 1.4a |
| Power Connectors | None | 1x 12-pin |
| Graphics Features | ||
| DirectX | N/A | 12 Ultimate (12_2) |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | N/A | 1.3 |
| CUDA | 8.0 | 8.6 |
| Shader Model | N/A | 6.6 |