AMD Radeon Pro W6900X vs NVIDIA A100 SXM4 80 GB
What is the difference between AMD Radeon Pro W6900X and NVIDIA A100 SXM4 80 GB. Find out which graphics card has better performance.
Graphics Processor (GPU)
| Navi 21 | GPU Name | GA100 |
| RDNA 2.0 | Architecture | Ampere |
| TSMC | Foundry | TSMC |
| 7 nm | Process Size | 7 nm |
| 26,800 million | Transistors | 54,200 million |
| 520 mm² | Die Size | 826 mm² |
Graphics Card
| Aug 3rd, 2021 | Release Date | Nov 16th, 2020 |
| Radeon Pro Mac (Navi II Series) | Family | Tesla (Axx) |
| Active | Production | Active |
| PCIe 4.0 x16 | Bus Interface | PCIe 4.0 x16 |
Memory
| 32 GB | Memory Size | 80 GB |
| GDDR6 | Memory Type | HBM2e |
| 256 bit | Memory Bus | 5120 bit |
| 512.0 GB/s | Bandwidth | 2,039 GB/s |
Performance
| 275.2 GPixel/s | Pixel fillrate | 225.6 GPixel/s |
| 688.0 GTexel/s | Texture fillrate | 609.1 GTexel/s |
| 44.03 TFLOPS (2:1) | FP16 (half) performance | 77.97 TFLOPS (4:1) |
| 22.02 TFLOPS | FP32 (float) performance | 19.49 TFLOPS |
| 1,376 GFLOPS (1:16) | FP64 (double) performance | 9.746 TFLOPS (1:2) |
Clock Speeds
| 1825 MHz | Base Clock | 1275 MHz |
| 2150 MHz | Boost Clock | 1410 MHz |
| 2000 MHz 16 Gbps effective | Memory Clock | 1593 MHz 3.2 Gbps effective |
Render Config
| 5120 | Shading Units | 6912 |
| 320 | TMUs | 432 |
| 128 | ROPs | 160 |
| 128 KB per Array | L1 Cache | 192 KB (per SM) |
| 4 MB | L2 Cache | 40 MB |
Board Design
| Quad-slot | Slot Width | IGP |
| 300 W | Thermal design power (TDP) | 400 W |
| 700 W | Suggested PSU | 800 W |
| 1x HDMI 4x Thunderbolt | Display Connectors | No outputs |
| None | Power Connectors | None |
API support
| 12 Ultimate (12_2) | DirectX | N/A |
| 4.6 | OpenGL | N/A |
| 2.1 | OpenCL | 3.0 |
| 1.2 | Vulkan | N/A |
| 6.5 | Shader Model | N/A |