GPU model | GF108 | XG42 |
---|---|---|
GPU variant | GF108-400-A1 | XG42 V3XT |
Architecture | Fermi | XG4 |
Foundry | TSMC | UMC |
Manufacturing process | 40 nm | 130 nm |
Number of transistors | 585 million | 25 million |
Die size | 116 mm² | unknown |
Release date | Feb 9th, 2011 | Sep 15th, 2003 |
---|---|---|
Generation | GeForce 400 | XG40 |
Production | End-of-life | End-of-life |
Interface | PCIe 1.0 x16 | AGP 8x |
Reviews | 5 in our database | 2 in our database |
Predecessor | GeForce 200 | — |
Successor | GeForce 500 | — |
GPU clock | 810 MHz | 250 MHz |
---|---|---|
Shader clock | 1620 MHz | — |
Memory clock | 667 MHz 1334 Mbps effective | 207 MHz 414 Mbps effective |
Memory size | 1024 MB | 128 MB |
---|---|---|
Memory type | DDR3 | DDR |
Memory bus width | 128 bit | 128 bit |
Bandwidth | 21.34 GB/s | 6.624 GB/s |
Shading units | 96 | — |
---|---|---|
TMUs | 16 | 4 |
ROPs | 4 | 2 |
SM count | 2 | — |
Cache L1 | 64 KB (per SM) | — |
Cache L2 | 256 KB | — |
Pixel shaders | — | 2 |
Vertex shaders | — | 1 |
Pixel rate | 3.240 GPixel/s | 500.0 MPixel/s |
---|---|---|
Texture rate | 12.96 GTexel/s | 1.000 GTexel/s |
FP32 (float) performance | 311.0 GFLOPS | — |
FP64 (double) performance | 25.92 GFLOPS (1:12) | — |
Vertex rate | — | 62.50 MVertices/s |
Slot width | Single-slot | Single-slot |
---|---|---|
Length | 145 mm 5.7 inches | — |
TDP | 65 W | unknown |
Suggested PSU | 250 W | 200 W |
Outputs | 1x DVI1x HDMI1x VGA | 1x DVI1x VGA1x S-Video |
Power connectors | None | — |
Board number | P1071 | D134 |
DirectX | 12 (11_0) | 8.1 |
---|---|---|
OpenGL | 4.6 | 1.3 |
OpenCL | 1.1 | — |
Vulkan | — | — |
CUDA | 2.1 | — |
Shader model | 5.1 | — |
Pixel shader | — | 1.3 |
Vertex shader | — | 1.1 |