NVIDIA Tesla V100 DGXS 32 GB vs NVIDIA Tesla V100 SXM2 16 GB
What is the difference between NVIDIA Tesla V100 DGXS 32 GB and NVIDIA Tesla V100 SXM2 16 GB. Find out which graphics card has better performance.
Graphics Processor (GPU)
| GV100 | GPU Name | GV100 |
| Volta | Architecture | Volta |
| TSMC | Foundry | TSMC |
| 12 nm | Process Size | 12 nm |
| 21,100 million | Transistors | 21,100 million |
| 815 mm² | Die Size | 815 mm² |
Graphics Card
| Mar 27th, 2018 | Release Date | Jun 21st, 2017 |
| Tesla (Vxx) | Family | Tesla (Vxx) |
| Active | Production | Active |
| PCIe 3.0 x16 | Bus Interface | PCIe 3.0 x16 |
Memory
| 32 GB | Memory Size | 16 GB |
| HBM2 | Memory Type | HBM2 |
| 4096 bit | Memory Bus | 4096 bit |
| 897.0 GB/s | Bandwidth | 897.0 GB/s |
Performance
| 195.8 GPixel/s | Pixel fillrate | 195.8 GPixel/s |
| 489.6 GTexel/s | Texture fillrate | 489.6 GTexel/s |
| 31.33 TFLOPS (2:1) | FP16 (half) performance | 31.33 TFLOPS (2:1) |
| 15.67 TFLOPS | FP32 (float) performance | 15.67 TFLOPS |
| 7.834 TFLOPS (1:2) | FP64 (double) performance | 7.834 TFLOPS (1:2) |
Clock Speeds
| 1297 MHz | Base Clock | 1312 MHz |
| 1530 MHz | Boost Clock | 1530 MHz |
| 876 MHz 1752 Mbps effective | Memory Clock | 876 MHz 1752 Mbps effective |
Render Config
| 5120 | Shading Units | 5120 |
| 320 | TMUs | 320 |
| 128 | ROPs | 128 |
| 128 KB (per SM) | L1 Cache | 128 KB (per SM) |
| 6 MB | L2 Cache | 6 MB |
| 80 | SM Count | 80 |
| 640 | Tensor Cores | 640 |
Board Design
| Dual-slot | Slot Width | Dual-slot |
| 250 W | Thermal design power (TDP) | 250 W |
| 600 W | Suggested PSU | 600 W |
| No outputs | Display Connectors | No outputs |
| None | Power Connectors | None |
API support
| 12 (12_1) | DirectX | 12 (12_1) |
| 4.6 | OpenGL | 4.6 |
| 3.0 | OpenCL | 3.0 |
| 1.2 | Vulkan | 1.2 |
| 6.6 | Shader Model | 6.6 |
| 7.0 | CUDA | 7.0 |