GPU model | NV30 | GF108 |
---|---|---|
Architecture | Rankine | Fermi |
Foundry | TSMC | TSMC |
Manufacturing process | 130 nm | 40 nm |
Number of transistors | 125 million | 585 million |
Die size | 199 mm² | 116 mm² |
GPU variant | — | N13P-NS1 |
Release date | Mar 6th, 2003 | — |
---|---|---|
Generation | GeForce FX | — |
Production | End-of-life | — |
Launch price | 399 USD | — |
Interface | AGP 8x | — |
Predecessor | GeForce 4 Ti | — |
Successor | GeForce 6 AGP | — |
GPU clock | 500 MHz | 660 MHz |
---|---|---|
Memory clock | 500 MHz 1000 Mbps effective | 900 MHz 1800 Mbps effective |
Shader clock | — | 1320 MHz |
Memory size | 128 MB | 2 GB |
---|---|---|
Memory type | GDDR2 | GDDR3 |
Memory bus width | 128 bit | 128 bit |
Bandwidth | 16.00 GB/s | 28.80 GB/s |
Pixel shaders | 4 | — |
---|---|---|
Vertex shaders | 2 | — |
TMUs | 8 | 16 |
ROPs | 4 | 4 |
Shading units | — | 96 |
SM count | — | 2 |
Cache L1 | — | 64 KB (per SM) |
Cache L2 | — | 256 KB |
Pixel rate | 2.000 GPixel/s | 2.640 GPixel/s |
---|---|---|
Vertex rate | 250.0 MVertices/s | — |
Texture rate | 4.000 GTexel/s | 10.56 GTexel/s |
FP32 (float) performance | — | 253.4 GFLOPS |
FP64 (double) performance | — | 21.12 GFLOPS (1:12) |
Slot width | Dual-slot | MXM Module |
---|---|---|
Length | 213 mm 8.4 inches | — |
TDP | unknown | 35 W |
Suggested PSU | 200 W | — |
Outputs | 1x DVI1x VGA1x S-Video | No outputs |
Power connectors | 1x Molex | — |
DirectX | 9.0a | 12 (11_0) |
---|---|---|
OpenGL | 1.5 (2.1) | 4.6 |
OpenCL | — | 1.1 |
Vulkan | — | — |
Pixel shader | 2.0a | — |
Vertex shader | 2.0a | — |
CUDA | — | 2.1 |
Shader model | — | 5.1 |
Release date | — | Jun 1st, 2012 |
---|---|---|
Generation | — | NVS Mobile (x400M) |
Production | — | End-of-life |
Interface | — | MXM |
Reviews | — | 26 in our database |