Product Compare
NVIDIA A800 PCIe 40 GB vs AMD Radeon HD 6990M
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Nov 2022 | Jul 2011 |
| Generation | Ampere | Vancouver |
| Type | AI GPU | Mobile |
| Bus Interface | PCIe 4.0 x16 | MXM-B (3.0) |
| Clock Speeds | ||
| Base Clock | 765 MHz | |
| Boost Clock | 1410 MHz | |
| Memory Clock | 1215 MHz | 900 MHz |
| Memory | ||
| Memory Size | 40GB | 2GB |
| Memory Type | HBM2e | GDDR5 |
| Memory Bus | 5120bit | 256bit |
| Bandwidth | 1555GB/s | 115.2GB/s |
| Render Config | ||
| SM Count | 108 | |
| Shading Units | 6912 | 1120 |
| TMUs | 432 | 56 |
| ROPs | 160 | 32 |
| Tensor Cores | 432 | |
| L1 Cache | 192 KB (per SM) | 8 KB (per CU) |
| L2 Cache | 40 MB | 512 KB |
| Compute Units | 14 | |
| Theoretical Performance | ||
| Pixel Rate | 225.6 GPixel/s | 22.88 GPixel/s |
| Texture Rate | 609.1 GTexel/s | 40.04 GTexel/s |
| FP16 (half) | 77.97 TFLOPS | |
| FP32 (float) | 19.49 TFLOPS | 1.602 TFLOPS |
| FP64 (double) | 9.746 TFLOPS | |
| Graphics Processor | ||
| GPU Name | GA100 | Blackcomb |
| Architecture | Ampere | TeraScale 2 |
| Foundry | TSMC | TSMC |
| Process Size | 7 nm | 40 nm |
| Transistors | 54.2 billion | 1.7 billion |
| Die Size | 826 mm² | 212 mm² |
| GPU Variant | Blackcomb XTX(216-0811030) | |
| Board Design | ||
| TDP | 250W | 100W |
| Suggested PSU | 600 W | |
| Outputs | No outputs | No outputs |
| Power Connectors | 8-pin EPS | None |
| Graphics Features | ||
| DirectX | N/A | 11.2 (11_0) |
| OpenGL | N/A | 4.4 |
| OpenCL | 3.0 | 1.2 |
| Vulkan | N/A | N/A |
| CUDA | 8.0 | |
| Shader Model | N/A | 5.0 |