NVIDIA Quadro M5000 vs NVIDIA Tesla M40 24 GB
Graphics Processor
| GPU model | GM204 | GM200 |
|---|---|---|
| GPU variant | GM204-875-A1 | GM200-895-A1 |
| Architecture | Maxwell 2.0 | Maxwell 2.0 |
| Foundry | TSMC | TSMC |
| Manufacturing process | 28 nm | 28 nm |
| Number of transistors | 5,200 million | 8,000 million |
| Die size | 398 mm² | 601 mm² |
Graphics Card
| Release date | Jun 29th, 2015 | Nov 10th, 2015 |
|---|---|---|
| Generation | Quadro | Tesla |
| Production | End-of-life | End-of-life |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Clocks
| Base clock | 861 MHz | 948 MHz |
|---|---|---|
| Boost clock | 1038 MHz | 1112 MHz |
| Memory clock | 1653 MHz 6.6 Gbps effective | 1502 MHz 6 Gbps effective |
Memory Configuration
| Memory size | 8 GB | 24 GB |
|---|---|---|
| Memory type | GDDR5 | GDDR5 |
| Memory bus width | 256 bit | 384 bit |
| Bandwidth | 211.6 GB/s | 288.4 GB/s |
Render Configuration
| Shading units | 2048 | 3072 |
|---|---|---|
| TMUs | 128 | 192 |
| ROPs | 64 | 96 |
| SMM count | 16 | 24 |
| Cache L1 | 48 KB (per SMM) | 48 KB (per SMM) |
| Cache L2 | 2 MB | 3 MB |
Performance
| Pixel rate | 66.43 GPixel/s | 106.8 GPixel/s |
|---|---|---|
| Texture rate | 132.9 GTexel/s | 213.5 GTexel/s |
| FP32 (float) performance | 4.252 TFLOPS | 6.832 TFLOPS |
| FP64 (double) performance | 132.9 GFLOPS (1:32) | 213.5 GFLOPS (1:32) |
Dimensions & Outputs
| Slot width | Dual-slot | Dual-slot |
|---|---|---|
| Length | 267 mm 10.5 inches | 267 mm 10.5 inches |
| Width | 111 mm 4.4 inches | — |
| TDP | 150 W | 250 W |
| Suggested PSU | 450 W | 600 W |
| Outputs | 1x DVI4x DisplayPort | No outputs |
| Power connectors | 1x 6-pin | 1x 6-pin + 1x 8-pin |
| Board number | PG400 SKU 500 | PG600 SKU 202 |
API Support & Features
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.1 | 1.1 |
| CUDA | 5.2 | 5.2 |
| Shader model | 6.4 | 6.4 |
