NVIDIA A40 PCIe vs NVIDIA Tesla V100S PCIe 32 GB
What is the difference between NVIDIA A40 PCIe and NVIDIA Tesla V100S PCIe 32 GB. Find out which graphics card has better performance.
Graphics Processor (GPU)
| GA102 | GPU Name | GV100 |
| Ampere | Architecture | Volta |
| Samsung | Foundry | TSMC |
| 8 nm | Process Size | 12 nm |
| 28,300 million | Transistors | 21,100 million |
| 628 mm² | Die Size | 815 mm² |
Graphics Card
| Oct 5th, 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
| 48 GB | Memory Size | 32 GB |
| GDDR6 | Memory Type | HBM2 |
| 384 bit | Memory Bus | 4096 bit |
| 695.8 GB/s | Bandwidth | 1,133 GB/s |
Performance
| 194.9 GPixel/s | Pixel fillrate | 204.4 GPixel/s |
| 584.6 GTexel/s | Texture fillrate | 511.0 GTexel/s |
| 37.42 TFLOPS (1:1) | FP16 (half) performance | 32.71 TFLOPS (2:1) |
| 37.42 TFLOPS | FP32 (float) performance | 16.35 TFLOPS |
| 1,169 GFLOPS (1:32) | FP64 (double) performance | 8.177 TFLOPS (1:2) |
Clock Speeds
| 1305 MHz | Base Clock | 1245 MHz |
| 1740 MHz | Boost Clock | 1597 MHz |
| 1812 MHz 14.5 Gbps effective | Memory Clock | 1106 MHz 2.2 Gbps effective |
Render Config
| 10752 | Shading Units | 5120 |
| 336 | TMUs | 320 |
| 112 | ROPs | 128 |
| 128 KB (per SM) | L1 Cache | 128 KB (per SM) |
| 6 MB | L2 Cache | 6 MB |
| 84 | SM Count | 80 |
| 336 | Tensor Cores | 640 |
Board Design
| Dual-slot | Slot Width | Dual-slot |
| 300 W | Thermal design power (TDP) | 250 W |
| 700 W | Suggested PSU | 600 W |
| 3x DisplayPort | Display Connectors | No outputs |
| 8-pin EPS | Power Connectors | 2x 8-pin |
API support
| 12 Ultimate (12_2) | 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 |
| 8.6 | CUDA | 7.0 |