Modern NVidia processors allow you to create high-performance graphics cards. Such devices are capable of solving tasks of increased complexity and have a high speed of operation. As part of this material, the current model range of semiconductor chips, which underlies the accelerators of the 20XX line, will be considered.
Actual models
Modern NVidia GPUs are manufactured using 12-nanometer technology. Due to this, their energy efficiency improves and electric energy consumption is reduced. Currently, chips are developed only for accelerators of the middle and premium classes. The most budgetary microprocessors for low-performance discrete graphics cards have not yet been presented.
At the same time, the mid-level adapters are based on the TU-106-400 and TU-106-300 chips, which are respectively used in the RTX 2070 and RTX 2060 accelerator models. In turn, two microprocessor models are also provided for high-performance graphics accelerators. One of them is the TU-104. This chip is used only in the RTX 2080 series adapters. But the more efficient TU-102 microprocessor is used in two models of graphic accelerators: RTX 2080Ti and Titan RTX. In the foreseeable future, this lineup of four microcircuits will be complemented by the least productive solutions.
Mid-Range Graphics Accelerator Chip
The TU-106-300 is the NVidia's least performing processor. The GeForce RTX 2060 is based on it. The recommended cost of such accelerators is $ 350. This chip includes 1920 stream processors and 30 ray tracing units. The number of TMU and ROP is 120 and 48 pieces, respectively. The clock frequency of this chip can vary in the range from 1365 to 1680 MHz. All this ensures the computing performance of this device at 6.5 TFLOPS.
The TU-106-400 chip boasts a slightly higher level of performance. It is used in the RTX 2070 series of video cards. Such devices are priced at $ 500 or more. This microprocessor includes 2304 streaming processors and already 36 hardware ray tracing modules. There are 144 units of TMUs in this case, and ROP - 64. The clock frequency range of the device is limited to 1410 MHz from the bottom and 1620 MHz from the top. Its claimed performance is 7.5 TFLOPS.
Microprocessor for high-end graphics cards
The RTX 2080 graphic accelerator is based on the TU-104 chip. Estimated cost of such devices is $ 700. In this case, the number of CUDA cores has been increased to 2,944. In turn, the trace modules in this case are already 46. The number of TMUs is increased to 184, and the ROP is equal to the same 64 pieces. This chip model operates at clock frequencies from 1,515 to 710 MHz. Moreover, its speed is 10.1 TFLOPS.
The processor of the NVidia RTX 2080 Ti and Titan RTX video cards is the same. Its marking is TU-102. In its maximum configuration, it includes 4,608 CUDA modules, 72 ray tracing elements, 272 TMU elements, and 88 ROPs. In the younger model of the RTX 2080 Ti graphics adapter, some of these elements are simply disabled, and hardware. Recommended clock frequencies are 1,350–1,545 MHz. At the same time, the speed of such devices is 13.5 TFLOPS. The price of such accelerators starts at $ 1,000.
Conclusion
As previously noted, modern mid-range and premium-level NVidia processors for graphics accelerators provide a high level of speed and are able to solve any problems. They implement ray tracing technology at the hardware level. In some cases, it should further increase the performance of such adapters, but so far it has not yet become widespread. As experts and specialists say, the future lies with it, and it will gradually become more widespread.
The graphic devices of this series considered earlier were presented quite recently. Therefore, this line of video cards will be supplemented with new devices and will remain relevant for the next year. And after this time interval, such accelerators without any problems will cope with the most demanding tasks for another 2-3 years.
That is, this is a worthy investment that will increase the speed of any PC. But nevertheless, it is most justified to use such accelerators only in combination with the most productive computing processors, which include the latest i5 and i7 modifications from Intel or Ryzen 5 and Ryzen 7 from AMD. In all other cases, the hardware resources of the graphics accelerator will not be fully loaded.