GEFORCE GTX 670

A little earlier, two of the most powerful solutions from NVIDIA had already been released: the single-chip video card model GeForce GTX 680, based on the first graphics processor of the Kepler architecture, and its dual-chip analogue – the GeForce GTX 690 model, which became the fastest video card on the market.

The top single-chip model GeForce GTX 680 is based on the Kepler architecture, the operating frequency of the graphics processor using technology GPU Boost reaches 1058 MHz and higher. As a result, the GeForce GTX 680 has become the fastest single-chip model from NVIDIA. Recall that when designing solutions for the Kepler family, the main goal was maximum energy efficiency. The 28 nm process technology also played a major role in reducing power requirements, but the efficiency of the new GPU Even more impactful were the significant architectural changes in Kepler - many of the execution units of the new GPU were completely redesigned.

NVIDIA is introducing the third video card based on the first chip of the Kepler architecture - GeForce GTX 670. As the name suggests, this is a successor to the GeForce GTX 470 and GTX 570 video cards, but based on a graphics processor of a new architecture, more productive and energy efficient.

The GeForce GTX 670 is designed for those gamers who plan to run the most demanding 3D applications with maximum settings, at high separate screen resolutions and with full-screen anti-aliasing enabled. Those who want to get all the functionality of the older GTX 680 video card, but for a lower price. The GeForce GTX 670 is based on the same GK104 video chip as the older model, and has 2 gigabytes of GDDR5 memory operating at the same frequencies as the video memory on the GeForce GTX 680.

This is an absolutely correct decision, since memory capacity and bandwidth are the most important factors limiting the performance of a top-end model. The new GeForce GTX 670 graphics card provides excellent performance in a class below that of AMD's Radeon HD 7950. The presented model is intended for this price category.

Since the released GeForce GTX 670 video card is based on the Kepler architecture graphics processor, already known to us under the code name GK104, there is nothing special to describe in this section - everything has already been described in great detail earlier. In this material we will only dwell on the differences and repeat the basic information.

The foundations of the Kepler architecture were laid in the Fermi chips released a couple of years ago (GeForce GTX 480 and then GTX 580), but despite the similarities, Kepler is still an almost completely redesigned architecture, the main goal of which was to improve energy efficiency. The GK670 graphics processor installed on the GeForce GTX 104 consists of four Graphics Processing Clusters, and differs from GPU GTX 680 only by the number of active blocks.

To ensure high enough performance to successfully compete with AMD accelerators, the GeForce GTX 670 decided to use the GK104 graphics processor with one of the eight SMX multiprocessors disabled. That is, one of the SMX blocks in the chip is disabled by hardware, and the GTX 670 offers the power of 1344 CUDA computing cores, assembled into 7 multiprocessors.

The GeForce GTX 670 has a base clock speed of 915 MHz, which is 10% lower than the top GTX 680. But the average turbo frequency GPU Boost is 980 MHz, which is only 8% less. Let's remember that GPU Boost allows Kepler GPUs to automatically increase their frequency GPU to achieve the highest possible performance. You can read about this technology in detail in the basic review of the GeForce GTX 680. The actual turbo frequency of the GK104 in the case of the GTX 670 depends on the specific 3D application, and most often amounts to a value even higher than 1 GHz.