NVIDIA Tesla M40 24 GB vs NVIDIA Tesla X2070
Graphics Processor
| GPU model | GM200 | GF110 |
|---|---|---|
| GPU variant | GM200-895-A1 | — |
| Architecture | Maxwell 2.0 | Fermi 2.0 |
| Foundry | TSMC | TSMC |
| Manufacturing process | 28 nm | 40 nm |
| Number of transistors | 8,000 million | 3,000 million |
| Die size | 601 mm² | 520 mm² |
Graphics Card
| Release date | Nov 10th, 2015 | Jul 25th, 2011 |
|---|---|---|
| Generation | Tesla | Tesla |
| Production | End-of-life | End-of-life |
| Interface | PCIe 3.0 x16 | PCIe 2.0 x16 |
Clocks
| Base clock | 948 MHz | — |
|---|---|---|
| Boost clock | 1112 MHz | — |
| Memory clock | 1502 MHz 6 Gbps effective | 924 MHz 3.7 Gbps effective |
| GPU clock | — | 651 MHz |
| Shader clock | — | 1301 MHz |
Memory Configuration
| Memory size | 24 GB | 6 GB |
|---|---|---|
| Memory type | GDDR5 | GDDR5 |
| Memory bus width | 384 bit | 384 bit |
| Bandwidth | 288.4 GB/s | 177.4 GB/s |
Render Configuration
| Shading units | 3072 | 512 |
|---|---|---|
| TMUs | 192 | 64 |
| ROPs | 96 | 48 |
| SMM count | 24 | — |
| Cache L1 | 48 KB (per SMM) | 64 KB (per SM) |
| Cache L2 | 3 MB | 768 KB |
| SM count | — | 16 |
Performance
| Pixel rate | 106.8 GPixel/s | 20.83 GPixel/s |
|---|---|---|
| Texture rate | 213.5 GTexel/s | 41.66 GTexel/s |
| FP32 (float) performance | 6.832 TFLOPS | 1,332 GFLOPS |
| FP64 (double) performance | 213.5 GFLOPS (1:32) | 666.1 GFLOPS (1:2) |
Dimensions & Outputs
| Slot width | Dual-slot | MXM Module |
|---|---|---|
| Length | 267 mm 10.5 inches | — |
| TDP | 250 W | 225 W |
| Suggested PSU | 600 W | 550 W |
| Outputs | No outputs | No outputs |
| Power connectors | 1x 6-pin + 1x 8-pin | — |
| Board number | PG600 SKU 202 | — |
API Support & Features
| DirectX | 12 (12_1) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 1.1 |
| Vulkan | 1.1 | — |
| CUDA | 5.2 | 2.0 |
| Shader model | 6.4 | 5.1 |
