Nvidia Keplar Architecture
Nvidia first announced the new architecture in September 2010.In early 2012, details of the first members of the 600 series parts emerged. These initial members were entry-level laptop GPUs sourced from the older Fermi architecture.
On March 22, 2012, the first Kepler products joined the 600 series: the GTX 680 for desktop PCs and the GeForce GT 640M, GT 650M, and GTX 660M for notebook/laptop PCs. The GK104 (which powers the GTX680) has 1536 CUDA cores, in eight groups of 192, and 3.5 billion transistors. The GK107 (GT 640M/GT 650M/GTX 660M) has 384 CUDA cores.
On April 29, 2012 , first dual GPU Kepler product GTX 690 joins 600 series. GTX 690 has two GTX 680 GPUs in it, so the total count of CUDA core in it is 3072 and a 512 bit memory and PCIe 3.0 interface.
Kepler based members of the 600 series add the following standard features to the GeForce family:
- Microsoft Direct3D 11.1
- PCI Express 3.0 interface
- DisplayPort 1.2
- HDMI 1.4a 4K x 2K video output
- Purevideo VP5 hardware video acceleration (up to 4K x 2K H.264 decode)
- Hardware H.264 encoding acceleration block (NVENC)
- Manufactured by TSMC on a 28 nm process
- Support for up to 4 independent 2D displays, or 3 stereoscopic/3D displays (NV Surround)
For laptop GPUs, the older Fermi architecture occupies both the entry-level and the top-end of the product lineup, while the newer Kepler architecture fills in the mid-range. Most of the desktop lineup is occupied by the Kepler architecture while the entry-level is occupied by the older Fermi architecture.