Product Compare
AMD Radeon E8950 vs NVIDIA Tesla T40 24 GB
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Sep 2015 | Unknown |
| Generation | Embedded | Tesla Turing |
| Type | Mobile | Professional |
| Bus Interface | MXM-B (3.0) | PCIe 3.0 x16 |
| Clock Speeds | ||
| Base Clock | 735 MHz | 1305 MHz |
| Boost Clock | 1000 MHz | 1560 MHz |
| Memory Clock | 1500 MHz | 1625 MHz |
| Memory | ||
| Memory Size | 8GB | 24GB |
| Memory Type | GDDR5 | GDDR6 |
| Memory Bus | 256bit | 384bit |
| Bandwidth | 192.0GB/s | 624.0GB/s |
| Render Config | ||
| Compute Units | 32 | |
| Shading Units | 2048 | 4608 |
| TMUs | 128 | 288 |
| ROPs | 32 | 96 |
| L1 Cache | 16 KB (per CU) | 64 KB (per SM) |
| L2 Cache | 512 KB | 6 MB |
| SM Count | 72 | |
| Tensor Cores | 576 | |
| RT Cores | 72 | |
| Theoretical Performance | ||
| Pixel Rate | 32.00 GPixel/s | 149.8 GPixel/s |
| Texture Rate | 128.0 GTexel/s | 449.3 GTexel/s |
| FP16 (half) | 4.096 TFLOPS | 28.75 TFLOPS |
| FP32 (float) | 4.096 TFLOPS | 14.38 TFLOPS |
| FP64 (double) | 256.0 GFLOPS | 449.3 GFLOPS |
| Graphics Processor | ||
| GPU Name | Amethyst | TU102 |
| GPU Variant | E8950 | |
| Architecture | GCN 3.0 | Turing |
| Foundry | TSMC | TSMC |
| Process Size | 28 nm | 12 nm |
| Transistors | 5 billion | 18.6 billion |
| Die Size | 366 mm² | 754 mm² |
| Board Design | ||
| TDP | 95W | 250W |
| Outputs | No outputs | No outputs |
| Power Connectors | None | 1x 8-pin |
| Suggested PSU | 600 W | |
| Graphics Features | ||
| DirectX | 12 (12_0) | 12 Ultimate (12_2) |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 3.0 |
| Vulkan | 1.2 | 1.3 |
| Shader Model | 6.3 | 6.8 |
| CUDA | 7.5 | |