Product Compare
NVIDIA GeForce RTX 3090 vs NVIDIA A100 SXM4 40 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Sep 2020 | May 2020 |
| Generation | GeForce 30 | Tesla Ampere |
| Type | Desktop | AI GPU |
| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1395 MHz | 1095 MHz |
| Boost Clock | 1695 MHz | 1410 MHz |
| Memory Clock | 1219 MHz | 1215 MHz |
| Memory | ||
| Memory Size | 24GB | 40GB |
| Memory Type | GDDR6X | HBM2e |
| Memory Bus | 384bit | 5120bit |
| Bandwidth | 936.2GB/s | 1555GB/s |
| Render Config | ||
| SM Count | 82 | 108 |
| Shading Units | 10496 | 6912 |
| TMUs | 328 | 432 |
| ROPs | 112 | 160 |
| Tensor Cores | 328 | 432 |
| RT Cores | 82 | |
| L1 Cache | 128 KB (per SM) | 192 KB (per SM) |
| L2 Cache | 6 MB | 40 MB |
| Theoretical Performance | ||
| Pixel Rate | 189.8 GPixel/s | 225.6 GPixel/s |
| Texture Rate | 556.0 GTexel/s | 609.1 GTexel/s |
| FP16 (half) | 35.58 TFLOPS | 77.97 TFLOPS |
| FP32 (float) | 35.58 TFLOPS | 19.49 TFLOPS |
| FP64 (double) | 556.0 GFLOPS | 9.746 TFLOPS |
| Graphics Processor | ||
| GPU Name | GA102 | GA100 |
| GPU Variant | GA102-300-A1 | |
| Architecture | Ampere | Ampere |
| Foundry | Samsung | TSMC |
| Process Size | 8 nm | 7 nm |
| Transistors | 28.3 billion | 54.2 billion |
| Die Size | 628 mm² | 826 mm² |
| Board Design | ||
| TDP | 350W | 400W |
| Suggested PSU | 750 W | 800 W |
| Outputs | 1x HDMI 2.13x DisplayPort 1.4a | No outputs |
| Power Connectors | 1x 12-pin | None |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.3 | N/A |
| CUDA | 8.6 | 8.0 |
| Shader Model | 6.6 | N/A |