GPU model | GF108 | G92B |
---|---|---|
GPU variant | GF108-400-A1 | G92-426-B1 |
Architecture | Fermi | Tesla |
Foundry | TSMC | TSMC |
Manufacturing process | 40 nm | 55 nm |
Number of transistors | 585 million | 754 million |
Die size | 116 mm² | 260 mm² |
Release date | Oct 11th, 2010 | Mar 4th, 2009 |
---|---|---|
Generation | GeForce 400 | GeForce 200 |
Production | End-of-life | End-of-life |
Interface | PCIe 2.0 x16 | PCIe 2.0 x16 |
Reviews | 33 in our database | 58 in our database |
Predecessor | GeForce 200 | GeForce 9 |
Successor | GeForce 500 | GeForce 400 |
Launch price | — | 199 USD |
GPU clock | 700 MHz | 675 MHz |
---|---|---|
Shader clock | 1400 MHz | 1620 MHz |
Memory clock | 800 MHz 1600 Mbps effective | 1008 MHz 2 Gbps effective |
Memory size | 2 GB | 1024 MB |
---|---|---|
Memory type | DDR3 | GDDR3 |
Memory bus width | 128 bit | 256 bit |
Bandwidth | 25.60 GB/s | 64.51 GB/s |
Shading units | 96 | 128 |
---|---|---|
TMUs | 16 | 64 |
ROPs | 4 | 16 |
SM count | 2 | 16 |
Cache L1 | 64 KB (per SM) | — |
Cache L2 | 256 KB | 64 KB |
Pixel rate | 2.800 GPixel/s | 10.80 GPixel/s |
---|---|---|
Texture rate | 11.20 GTexel/s | 43.20 GTexel/s |
FP32 (float) performance | 268.8 GFLOPS | 414.7 GFLOPS |
FP64 (double) performance | 22.40 GFLOPS (1:12) | — |
Slot width | Single-slot | Dual-slot |
---|---|---|
Length | 145 mm 5.7 inches | 229 mm 9 inches |
TDP | 49 W | 150 W |
Suggested PSU | 200 W | 450 W |
Outputs | 1x DVI1x HDMI1x VGA | 2x DVI |
Power connectors | None | 1x 6-pin |
Board number | — | P365 |
DirectX | 12 (11_0) | 11.1 (10_0) |
---|---|---|
OpenGL | 4.6 | 3.3 |
OpenCL | 1.1 | 1.1 |
Vulkan | — | — |
CUDA | 2.1 | 1.1 |
Shader model | 5.1 | 4.0 |