NVIDIA GRID A100B vs AMD Radeon Pro Vega II
What is the difference between NVIDIA GRID A100B and AMD Radeon Pro Vega II. Find out which graphics card has better performance.
Graphics Processor (GPU)
| GA100 | GPU Name | Vega 20 |
| Ampere | Architecture | GCN 5.1 |
| TSMC | Foundry | TSMC |
| 7 nm | Process Size | 7 nm |
| 54,200 million | Transistors | 13,230 million |
| 826 mm² | Die Size | 331 mm² |
Graphics Card
| May 14th, 2020 | Release Date | Jun 3rd, 2019 |
| GRID (Ax) | Family | Radeon Pro Mac (Vega Series) |
| Active | Production | Active |
| PCIe 4.0 x16 | Bus Interface | PCIe 3.0 x16 |
Memory
| 48 GB | Memory Size | 32 GB |
| HBM2e | Memory Type | HBM2 |
| 6144 bit | Memory Bus | 4096 bit |
| 1,866 GB/s | Bandwidth | 825.3 GB/s |
Performance
| 193.0 GPixel/s | Pixel fillrate | 110.1 GPixel/s |
| 434.2 GTexel/s | Texture fillrate | 440.3 GTexel/s |
| 55.57 TFLOPS (4:1) | FP16 (half) performance | 28.18 TFLOPS (2:1) |
| 13.89 TFLOPS | FP32 (float) performance | 14.09 TFLOPS |
| 6.947 TFLOPS (1:2) | FP64 (double) performance | 880.6 GFLOPS (1:16) |
Clock Speeds
| 900 MHz | Base Clock | 1574 MHz |
| 1005 MHz | Boost Clock | 1720 MHz |
| 1215 MHz 2.4 Gbps effective | Memory Clock | 806 MHz 1612 Mbps effective |
Render Config
| 6912 | Shading Units | 4096 |
| 432 | TMUs | 256 |
| 192 | ROPs | 64 |
| 192 KB (per SM) | L1 Cache | 16 KB (per CU) |
| 48 MB | L2 Cache | 4 MB |
Board Design
| IGP | Slot Width | Quad-slot |
| 400 W | Thermal design power (TDP) | 475 W |
| 800 W | Suggested PSU | 850 W |
| No outputs | Display Connectors | 1x HDMI 4x Thunderbolt |
| None | Power Connectors | None |
API support
| N/A | DirectX | 12 (12_1) |
| N/A | OpenGL | 4.6 |
| 3.0 | OpenCL | 2.1 |
| N/A | Vulkan | 1.2 |
| N/A | Shader Model | 6.4 |