NVIDIA GRID M40 vs NVIDIA Tesla M2050
What is the difference between NVIDIA GRID M40 and NVIDIA Tesla M2050. Find out which graphics card has better performance.
Graphics Processor (GPU)
| GM107 | GPU Name | GF100 |
| Maxwell | Architecture | Fermi |
| TSMC | Foundry | TSMC |
| 28 nm | Process Size | 40 nm |
| 1,870 million | Transistors | 3,100 million |
| 148 mm² | Die Size | 529 mm² |
Graphics Card
| May 18th, 2016 | Release Date | Jul 25th, 2011 |
| GRID (Mx) | Family | Tesla (x20xx) |
| End-of-life | Production | End-of-life |
| PCIe 3.0 x16 | Bus Interface | PCIe 2.0 x16 |
Memory
| 8 GB | Memory Size | 3 GB |
| GDDR5 | Memory Type | GDDR5 |
| 128 bit | Memory Bus | 384 bit |
| 83.20 GB/s | Bandwidth | 148.4 GB/s |
Performance
| 16.53 GPixel/s | Pixel fillrate | 16.10 GPixel/s |
| 33.06 GTexel/s | Texture fillrate | 32.20 GTexel/s |
| 793.3 GFLOPS | FP32 (float) performance | 1,030 GFLOPS |
| 24.79 GFLOPS (1:32) | FP64 (double) performance | 515.2 GFLOPS (1:2) |
Clock Speeds
| 1300 MHz 5.2 Gbps effective | Memory Clock | 773 MHz 3.1 Gbps effective |
| 1033 MHz | GPU Clock | 575 MHz |
Render Config
| 384 | Shading Units | 448 |
| 32 | TMUs | 56 |
| 16 | ROPs | 48 |
| 64 KB (per SMM) | L1 Cache | 64 KB (per SM) |
| 2 MB | L2 Cache | 768 KB |
Board Design
| Dual-slot | Slot Width | Dual-slot |
| 50 W | Thermal design power (TDP) | 225 W |
| 250 W | Suggested PSU | 550 W |
| No outputs | Display Connectors | No outputs |
API support
| 12 (11_0) | DirectX | 12 (11_0) |
| 4.6 | OpenGL | 4.6 |
| 3.0 | OpenCL | 1.1 |
| 1.1 | Vulkan | N/A |
| 5.1 | Shader Model | 5.1 |
| 5.0 | CUDA | 2.0 |