Introduction

In early 2008, NVIDIA's GeForce 9600 GT, armed with a mere 64 shader units, 16 ROPs, 512 MB of memory, and an inviting price-tag, rattled competitor AMD's Radeon HD 3800 lineup. It allowed gamers to achieve playable framerates with cranked up visual details that were, until then, not possible with graphics cards in its price-segments. From that point on, NVIDIA realized it could gain a substantial market share in the sub-$250 price-segment, hovering around the $200 price-point, if it creates a GPU that can handle high-resolution gaming with a fair amount of eye-candy enabled. Continuing its legacy, NVIDIA's GeForce GTS 250, GeForce GTX 460, and GeForce GTX 660 are each successful products. In August, NVIDIA launched the GeForce GTX 660 Ti, a GPU that achieved a nice price-performance index in the $250-300 price-range. NVIDIA's next logical step would be to create a GPU that does the same with the $200-250 price-range. Enter the GeForce GTX 660.



Unlike its "Ti" cousin, the GeForce GTX 660 is not based on the GK104 silicon from which several other GPUs, such as the GTX 670, GTX 680, and the dual-GPU GTX 690, are derived. The GTX 660 is, instead, based on the new GK106 silicon that makes its desktop debut today. The GK106 is a physical downscale of the GK104 which retains its features, including component hierarchy, but has fewer numbers of them. The GK106 silicon is smaller with a die-area of 221 mm² and a transistor count of 2.54 billion (compared to 294 mm² and 3.54 billion with the GK104). The GK106 is built on the same 28 nanometer silicon fabrication process. A smaller chip results in reduced power draw. A case in point is that the GeForce GTX 660 needs power from just one 6-pin PCIe power connector, while the GTX 660 Ti needs two of them.

As mentioned before, components on the GK106 maintain the same hierarchy as on the GK104, and the two provide the same exact feature-set. The chip is based on NVIDIA's successful GeForce Kepler architecture. While GK104 packs eight graphics processing clusters (GPCs) with a total of sixteen streaming multiprocessor (SMX) units holding 192 CUDA cores, each, for to a total of 1,536 CUDA cores, the GK106 packs three GPCs and five SMX units, totaling 960 CUDA cores. It's interesting to note that, if the block diagram is anything to go by, NVIDIA created a GPC with just one SMX unit. The chip may really have six SMX units, but it's kept out of the block diagram to, perhaps, help harvest the chip better.



The GK106 silicon packs a total of 960 CUDA cores, with 80 texture memory units (TMUs), 24 raster operations processors (ROPs), and a 192-bit wide GDDR5 memory interface. As with the GeForce GTX 660 Ti, NVIDIA set 2 GB as the standard memory amount for the GeForce GTX 660. A 192-bit wide memory interface, populated with six memory chips of the same 2 Gbit density, should, typically, result in a memory amount of 1.5 GB. NVIDIA populated two of the six 32-bit wide paths with two piggy-backed 2-Gbit chips each, for a total of eight 2 Gbit memory chips and 2 GB of memory. The 25% narrower memory bus width shouldn't worry you because NVIDIA uses 6.00 GHz memory clock speed, resulting in a memory bandwidth of 144 GB/s. The GPU core is clocked at 980 MHz with a GPU Boost frequency of 1033 MHz.



Although NVIDIA has a reference design board for the GeForce GTX 660 in place, its add-in card partners are free to launch graphics cards of their own designs. This review covers the ASUS GeForce GTX 660 DirectCU II TOP, a factory-overclocked graphics card that uses ASUS' popular DirectCU II dual-slot cooling solution, which ASUS has used extensively on GeForce and Radeon based performance-segment graphics cards. The card ships with a core clock speed of 1072 MHz, and 1137 MHz GPU Boost.