Product Compare
NVIDIA B100 vs AMD Radeon R9 Nano
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Unknown | Aug 2015 |
| Generation | Server Blackwell | Pirate Islands |
| Type | Desktop | Desktop |
| Bus Interface | PCIe 5.0 x16 | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 700 MHz | |
| Boost Clock | 975 MHz | |
| Memory Clock | 2000 MHz | 500 MHz |
| Memory | ||
| Memory Size | 96GB | 4GB |
| Memory Type | HBM3e | HBM |
| Memory Bus | 4096bit | 4096bit |
| Bandwidth | 4.10TB/s | 512.0GB/s |
| Render Config | ||
| SM Count | 132 | |
| Shading Units | 16896 | 4096 |
| TMUs | 528 | 256 |
| ROPs | 24 | 64 |
| Tensor Cores | 528 | |
| L1 Cache | 256 KB (per SM) | 16 KB (per CU) |
| L2 Cache | 50 MB | 2 MB |
| Compute Units | 64 | |
| Theoretical Performance | ||
| Pixel Rate | 23.40 GPixel/s | 64.00 GPixel/s |
| Texture Rate | 514.8 GTexel/s | 256.0 GTexel/s |
| FP16 (half) | 131.8 TFLOPS | 8.192 TFLOPS |
| FP32 (float) | 32.95 TFLOPS | 8.192 TFLOPS |
| FP64 (double) | 16.47 TFLOPS | 512.0 GFLOPS |
| Graphics Processor | ||
| GPU Name | GB102 | Fiji |
| Architecture | Blackwell | GCN 3.0 |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 28 nm |
| Transistors | 104 billion | 8.9 billion |
| Die Size | Unknown | 596 mm² |
| GPU Variant | Fiji XT CA(215-0862120) | |
| Board Design | ||
| TDP | 1000W | 175W |
| Suggested PSU | 1400 W | 450 W |
| Outputs | No outputs | 1x HDMI 1.4a3x DisplayPort 1.2 |
| Power Connectors | 1x 8-pin | |
| Graphics Features | ||
| DirectX | N/A | 12 (12_0) |
| OpenGL | N/A | 4.6 |
| OpenCL | 3.0 | 2.0 |
| Vulkan | N/A | 1.2 |
| CUDA | 10.1 | |
| Shader Model | N/A | 6.3 |