NVIDIA GeForce GTS 150 OEM vs NVIDIA Tesla M2070-Q
Graphics Processor
| GPU model | G92 | GF100 |
|---|---|---|
| Architecture | Tesla | Fermi |
| Foundry | TSMC | TSMC |
| Manufacturing process | 65 nm | 40 nm |
| Number of transistors | 754 million | 3,100 million |
| Die size | 324 mm² | 529 mm² |
| GPU variant | — | GF100-876-A1 |
Graphics Card
| Release date | Mar 10th, 2009 | Jul 25th, 2011 |
|---|---|---|
| Generation | GeForce 100 | Tesla |
| Production | End-of-life | End-of-life |
| Interface | PCIe 2.0 x16 | PCIe 2.0 x16 |
| Predecessor | GeForce 9 | — |
| Successor | GeForce 200 | — |
| Launch price | — | 5,489 USD |
Clocks
| GPU clock | 738 MHz | 574 MHz |
|---|---|---|
| Shader clock | 1836 MHz | 1147 MHz |
| Memory clock | 1000 MHz 2 Gbps effective | 783 MHz 3.1 Gbps effective |
Memory Configuration
| Memory size | 1024 MB | 6 GB |
|---|---|---|
| Memory type | GDDR3 | GDDR5 |
| Memory bus width | 256 bit | 384 bit |
| Bandwidth | 64.00 GB/s | 150.3 GB/s |
Render Configuration
| Shading units | 128 | 448 |
|---|---|---|
| TMUs | 64 | 56 |
| ROPs | 16 | 48 |
| SM count | 16 | 14 |
| Cache L2 | 64 KB | 768 KB |
| Cache L1 | — | 64 KB (per SM) |
Performance
| Pixel rate | 11.81 GPixel/s | 16.07 GPixel/s |
|---|---|---|
| Texture rate | 47.23 GTexel/s | 32.14 GTexel/s |
| FP32 (float) performance | 470.0 GFLOPS | 1,028 GFLOPS |
| FP64 (double) performance | — | 513.9 GFLOPS (1:2) |
Dimensions & Outputs
| Slot width | Dual-slot | Dual-slot |
|---|---|---|
| Length | 267 mm 10.5 inches | 248 mm 9.8 inches |
| TDP | 141 W | 225 W |
| Suggested PSU | 300 W | 550 W |
| Outputs | 2x DVI1x S-Video | No outputs |
| Power connectors | 2x 6-pin | 1x 6-pin + 1x 8-pin |
API Support & Features
| DirectX | 11.1 (10_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 3.3 | 4.6 |
| OpenCL | 1.1 | 1.1 |
| Vulkan | — | — |
| CUDA | 1.1 | 2.0 |
| Shader model | 4.0 | 5.1 |
