NVIDIA A100 SXM4 40 GB vs NVIDIA Tesla V100S PCIe 32 GB
What is the difference between NVIDIA A100 SXM4 40 GB and NVIDIA Tesla V100S PCIe 32 GB. Find out which graphics card has better performance.
Graphics Processor (GPU)
| GA100 | GPU Name | GV100 |
| Ampere | Architecture | Volta |
| TSMC | Foundry | TSMC |
| 7 nm | Process Size | 12 nm |
| 54,200 million | Transistors | 21,100 million |
| 826 mm² | Die Size | 815 mm² |
Graphics Card
| May 14th, 2020 | Release Date | Nov 26th, 2019 |
| Tesla (Axx) | Family | Tesla (Vxx) |
| Active | Production | Active |
| PCIe 4.0 x16 | Bus Interface | PCIe 3.0 x16 |
Memory
| 40 GB | Memory Size | 32 GB |
| HBM2e | Memory Type | HBM2 |
| 5120 bit | Memory Bus | 4096 bit |
| 1,555 GB/s | Bandwidth | 1,133 GB/s |
Performance
| 225.6 GPixel/s | Pixel fillrate | 204.4 GPixel/s |
| 609.1 GTexel/s | Texture fillrate | 511.0 GTexel/s |
| 77.97 TFLOPS (4:1) | FP16 (half) performance | 32.71 TFLOPS (2:1) |
| 19.49 TFLOPS | FP32 (float) performance | 16.35 TFLOPS |
| 9.746 TFLOPS (1:2) | FP64 (double) performance | 8.177 TFLOPS (1:2) |
Clock Speeds
| 1095 MHz | Base Clock | 1245 MHz |
| 1410 MHz | Boost Clock | 1597 MHz |
| 1215 MHz 2.4 Gbps effective | Memory Clock | 1106 MHz 2.2 Gbps effective |
Render Config
| 6912 | Shading Units | 5120 |
| 432 | TMUs | 320 |
| 160 | ROPs | 128 |
| 192 KB (per SM) | L1 Cache | 128 KB (per SM) |
| 40 MB | L2 Cache | 6 MB |
| 108 | SM Count | 80 |
| 432 | Tensor Cores | 640 |
Board Design
| IGP | Slot Width | Dual-slot |
| 400 W | Thermal design power (TDP) | 250 W |
| 800 W | Suggested PSU | 600 W |
| No outputs | Display Connectors | No outputs |
| None | Power Connectors | 2x 8-pin |
API support
| N/A | DirectX | 12 (12_1) |
| N/A | OpenGL | 4.6 |
| 3.0 | OpenCL | 3.0 |
| N/A | Vulkan | 1.2 |
| N/A | Shader Model | 6.6 |
| 8.0 | CUDA | 7.0 |