NVIDIA Quadro RTX 4000 vs NVIDIA Tesla M40
What is the difference between NVIDIA Quadro RTX 4000 and NVIDIA Tesla M40. Find out which graphics card has better performance.
Graphics Processor (GPU)
| TU104 | GPU Name | GM200 |
| TU104-850-A1 | Model number | GM200-895-A1 |
| Turing | Architecture | Maxwell 2.0 |
| TSMC | Foundry | TSMC |
| 12 nm | Process Size | 28 nm |
| 13,600 million | Transistors | 8,000 million |
| 545 mm² | Die Size | 601 mm² |
Graphics Card
| Nov 13th, 2018 | Release Date | Nov 10th, 2015 |
| Quadro (Tx000) | Family | Tesla (Mxx) |
| Active | Production | Active |
| PCIe 3.0 x16 | Bus Interface | PCIe 3.0 x16 |
Memory
| 8 GB | Memory Size | 12 GB |
| GDDR6 | Memory Type | GDDR5 |
| 256 bit | Memory Bus | 384 bit |
| 416.0 GB/s | Bandwidth | 288.4 GB/s |
Performance
| 98.88 GPixel/s | Pixel fillrate | 106.9 GPixel/s |
| 222.5 GTexel/s | Texture fillrate | 213.9 GTexel/s |
| 7.119 TFLOPS | FP32 (float) performance | 6.844 TFLOPS |
| 222.5 GFLOPS (1:32) | FP64 (double) performance | 213.9 GFLOPS (1:32) |
Clock Speeds
| 1005 MHz | Base Clock | 948 MHz |
| 1545 MHz | Boost Clock | 1114 MHz |
| 1625 MHz 13 Gbps effective | Memory Clock | 1502 MHz 6 Gbps effective |
Render Config
| 2304 | Shading Units | 3072 |
| 144 | TMUs | 192 |
| 64 | ROPs | 96 |
| 64 KB (per SM) | L1 Cache | 48 KB (per SMM) |
| 4 MB | L2 Cache | 3 MB |
Board Design
| Single-slot | Slot Width | Dual-slot |
| 241 mm 9.5 inches | Length | 267 mm 10.5 inches |
| 160 W | Thermal design power (TDP) | 250 W |
| 450 W | Suggested PSU | 600 W |
| 3x DisplayPort 1x USB Type-C | Display Connectors | No outputs |
| 1x 8-pin | Power Connectors | 1x 6-pin + 1x 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 | 1.1 |
| 6.6 | Shader Model | 6.4 |
| 7.5 | CUDA | 5.2 |