The GF110 chip shares a lot of its roots with the GF100 core. The GPU still packs an impressive 3.2 billion transistors in a die seize 520mm squared. Its default internal configuration has been ported from GF100 in that the GPU features 512 CUDA cores or shader processors as we are more accustomed to. There are organised in a 4x16x32 block where 16 denotes the number of stream multi-processors (SM) and 32 being the number of cores on each SM. Each SM has its own L1 Cache and a common L2 Cache is shared by all 16. The GPU is still manufactured on the 40nm process.


The GTX560Ti-448 we have for review today has 14 out of the total 16 SM enabled for a final 448 CUDA core count. Comparing it to a GTX570 means it has one less SM (480 CUDA cores) and two less than a GTX580, itself having the maximum having 512 CUDA cores enabled. So in effect it is a trimmed down GTX570 rather than an enhanced GTX560 which is based on the GF114 silicon containing a maximum 384 CUDA cores.

The memory subsystem on the GTX560Ti is more akin to the GTX570 as well with its 5 memory controllers each sporting a 256MB GDDR5 framebuffer to give 1280MB of available memory. The memory interface is composed of ten 32-bit channels for a 320-bit interface.

GTX570: 15 SMs x 32 = 480 Core, 15 SMs x 4 = 60 texture units
32-bit channel x 10 = 320-bit interface, 256MB x 5 memory controllers = 1280MB memory

GTX560: 14 SMs x 32 = 448 Core, 14 SMs x 4 = 56 texture units
32-bit channel x 10 = 320-bit interface, 256MB x 5 memory controllers = 1280MB memory



The GTX560Ti 448 then looks to be very competitive against the GTX570 in that it is clocked higher, although the missing core might affect its ability to compete. We will be testing the new GTX560Ti-448 against both its smaller sibling, the 384 core GTX560Ti based on the GF114 core along with a stocked clocked GTX570 to see which card comes out on top.



Let's take a look at the cards feature set...