GeForce GTX 750 Ti
The GTX 750 Ti is powered by the GM107 GPU. The number of computational units of GM107 is significantly greater than that of GK107: 640 CUDA cores and 40 texture units instead of 384 and 32, respectively. However, the GM107 still has 16 ROPs and a 128-bit memory bus. These numbers in themselves are not surprising, if not for the fact that the GM107 remained within the same power consumption range as the GK107 (the stated TDP is even slightly lower - 60 versus 64 W). In essence, this is the purpose of the Maxwell architecture - to increase performance per watt.
Judging by the diagrams presented, the main innovation of Maxwell is a seemingly minor, but potentially very effective reorganization of blocks GPU. At the global level, GM107 follows the principles laid down in Kepler. All the computational logic is concentrated in a structure called the Graphics Processing Cluster (GPC), of which there is only one in GM107, although there will be more in larger chips.
Outside the GPC is the entire back-end of the processor in the form of ROP blocks and two 64-bit memory controllers, as well as the Giga Thread Engine, which performs the functions of changing context, simultaneous execution of kernels and distributing load threads between GPCs (the latter is not our case yet) . The quantitative difference from Kepler here is the L2 cache, increased from 256 to 2048 KB, which should compensate for the narrow 128-bit bus, as well as reduce energy consumption for transactions with very voracious memory, which is GDDR5 SDRAM.
GeForce GTX 750 Ti specifications
|
|
||||||
|
Chip
|
||||||
|
Frequencies
|
||||||
|
Memory
|
||||||
|
Interface and TDP
|
The base frequency is 1020 MHz. Since it uses the technology GPU Boost 2.0, i.e. Boost Clock, equal to 1085 MHz. Video memory operates at an effective frequency of 5400 MHz. Thus, in terms of overall characteristics, the GTX 750 Ti is close to the GTX 650 Ti on the GK106 chip, even without taking into account the more efficient Maxwell architecture.
