Introduction

There is a strong push within the display industry to take 4K Ultra HD to the masses, especially with 4K monitors being sold deep under the $500 mark. A pair of any of today's $300-ish graphics cards in a multi-GPU setup can set you up for gaming at this resolution with reasonably high eye-candy. Back in March, NVIDIA launched the first single-GPU graphics card that lets you play any of today's games at 4K with high eye-candy, freeing you from the quirks of multi-GPU setups; it, on the flip-side, cost $1000, and you could only buy and use its noisy reference design if you didn't have a liquid-cooling loop. Competition from AMD in the form of its upcoming "Fiji XT" graphics card and the rush for pre-summer builds and upgrades have now prompted NVIDIA to fill the vast gorge between the GeForce GTX 980 and the GTX Titan X with the cheapest 4K-worthy single-GPU graphics card before the season's hottest games come out. Enter the GeForce GTX 980 Ti.



The GeForce GTX 980 Ti is being launched at the $650 mark, the traditional price point at which NVIDIA sold its high-end single-GPU products before it started asking $1000 for its fastest single-GPU graphics cards. The GTX 980 Ti is also a true successor to the GTX 780 Ti based on NVIDIA's biggest silicon for the "Maxwell" GPU architecture, the GM200. Unlike its predecessor, it does not feature the full complement of CUDA cores on the silicon and is hence positioned a notch below the GTX Titan X. NVIDIA probably did so to avoid the repeat of the GTX 780 Ti cannibalizing the GTX Titan Black; buyers with deep pockets are lured with the prospect of buying a GM200 card with all its cylinders unlocked in the GTX Titan X.

The GeForce GTX 980 Ti, which we are reviewing today, still has a serious lot going for it. It features 2,816 of the 3,072 CUDA cores on this silicon, which NVIDIA achieved by enabling 22 of the 24 SMM units. The TMU count is 176 (compared to the 192 on the GTX Titan X), and the ROP count is confirmed to be 96. NVIDIA seems to have learned from the GTX 970 ROP-count and memory-configuration drama. The chip is wired to 6 GB of GDDR5 memory across its 384-bit interface and can address all of it at a consistent bandwidth. The clock speeds are similar to those of the GTX Titan X.

The best part about this SKU is that NVIDIA will allow its board partners to innovate custom-design boards with factory-overclocked speeds, so the inadequacy of NVIDIA's reference cooler and its PCB could be overcome. Along with launching the GTX 980 Ti at $650, NVIDIA repositioned the GM204-based GTX 980 at $500. In this review, we will deal with the reference-design GeForce GTX 980 Ti to give you have a crystal-clear idea of whether NVIDIA managed to fill the gap between the GTX 980 and the GTX Titan X.

Architecture

At the heart of the GeForce GTX 980 Ti is the 28 nm GM200 silicon. On paper, it is quite an engineering feat because of its gargantuan 8 billion transistor count and 601 mm² large die on the existing 28 nm process that appeared to have reached its thermal boundaries with the previous-generation NVIDIA GK110 and AMD "Hawaii".

The GM200 is based on the "Maxwell" architecture. It features the same component hierarchy as the GM204, but is a 50% upscale in every respect. It features six graphics processing clusters (GPCs) as opposed to the four on the GM204, which makes for 3,072 CUDA cores, a 50% wider 384-bit memory bus, and a 50% larger 3 MB L2 cache over the GM204. In the GeForce GTX 980 Ti, NVIDIA disabled 2 of the 24 streaming multiprocessors (SMMs) on the silicon, which results in 2,816 CUDA cores. At 176, the texture-memory unit (TMU) count is lower. The ROP count is 96. The card features 6 GB of memory, half that of the GTX Titan X, but at 288 GB/s, the memory bandwidth is the same. The GPU can address the entire 6 GB of memory at a consistent speed.



The GM200 features 900 million more transistors than its predecessor, the GK110, although in its GTX TITAN X avatar, it features the same 250W TDP rating. That's both impressive and unnerving. The GM204, despite its 5.2 billion transistors, was rated at 165W TDP on the GTX 980, indicating that with Maxwell, NVIDIA may have finally reached the thermal limits of the 28 nm process.

At the heart of the Maxwell architecture is a redesigned streaming multiprocessor (SMM), the tertiary subunit of the GPU. The chip begins with a PCI-Express 3.0 x16 bus interface, a 384-bit wide GDDR5 memory interface, and a display controller that supports as many as three Ultra HD displays, or five physical displays in total. This display controller introduces support for HDMI 2.0, which has enough bandwidth to drive Ultra HD displays at 60 Hz refresh rates. The controller is ready for 5K (5120x2880, four times the pixels as QuadHD), and the 384-bit wide memory interface holds 6 GB of memory.

The GigaThread Engine splits workloads between four graphics processing clusters (GPCs). The L2 cache cushion transfers between these GPCs. Each GPC holds four streaming multiprocessors (SMMs) and a common raster engine between them. Each SMX holds a third-generation PolyMorph Engine, a component that performs a host of rendering tasks, such as fetch, transform, setup, tessellation, and output. The SMX has 128 CUDA cores, the number-crunching components of NVIDIA GPUs, spread across four subdivisions with dedicated warp-schedulers, registers, and caches. NVIDIA claims the SMM to have two times the performance-per-watt figure of "Kepler" SMX units.

GeForce Features

With each new architecture, NVIDIA introduces innovations in the consumer graphics space that go beyond simple feature-level compatibility with new DirectX versions. NVIDIA says GeForce Titan X, GTX 980, and GTX 970 cards to be DirectX 12 cards, but exact feature levels and requirements have not been finalized by Microsoft, yet support for OpenGL 4.4 has also been added. OpenGL 4.4 adds a few new features through its GameWorks SDK that give game developers easy-to-implement visual features through existing APIs.



According to NVIDIA, the first and most important is VXGI, or real-time voxel global illumination. VGXI adds realism to the way light behaves with different surfaces in a 3D scene. VXGI introduces volume pixels, or voxels, a new 3D graphics component. These are pixels with built-in 3-dimensional data, so their interactions in 3D objects with light look more photo-realistic.



No new NVIDIA GPU architecture launch is complete without advancements in post-processing, particularly anti-aliasing. NVIDIA introduced an interesting feature called Dynamic Super Resolution (DSR), which it claims offers 4K-like clarity on a 1080p display. To us, it comes across as a really nice super-sampling AA algorithm with a filter.



Using GeForce Experience, you can enable DSR arbitrarily for 3D apps. The other new algorithm is MFAA (multi-frame sampled AA), which offers MSAA-like image quality at a deficit of 30 percent in performance. Using GeForce Experience, MFAA can hence be substituted for MSAA, perhaps even arbitrarily.



Moving on, NVIDIA introduced VR Direct, a technology designed for the re-emerging VR headset market due to the growing interest in Facebook's Occulus Rift VR headset. VR Direct is an API designed to reduce latency between the headset's input and the change on the display, governed by the principle that head movements are more rapid and unpredictable than pointing and clicking with a mouse.



To meet the need of a low-cost (performance cost), realistic hair- or grass-rendering technology, NVIDIA came up with Turf Effects. NVIDIA PhysX also got a much needed feature-set update that introduces new gas dynamics and fluid adhesion effects. Epic's Unreal Engine 4 will implement the technology.

GeForce Experience

With its GeForce 320.18 WHQL drivers, NVIDIA released the first stable version of GeForce Experience. The application simplifies the process of configuring a game and is meant for PC gamers who aren't well-versed in all the necessary technobabble required to get a game to run at the best-possible settings with the hardware available to them. GeForce Experience is aptly named as it completes the experience of owning a GeForce graphics card; PCs, being the best-possible way to play video games, should not be any harder to use than gaming consoles.

NVIDIA Shadow Play

GeForce Experience Shadow Play is another feature NVIDIA recently debuted. Shadow Play lets you record gaming footage or stream content in real time, with a minimal performance drop to the game you're playing. The feature is handled by GeForce Experience, which lets you set hot-keys to toggle recording on the fly, or set output, format, quality, etc.



Unlike other apps, which record videos in loss-less AVI formats by tapping into the DirectX pipeline and clogging the system bus, disk, and memory with high bit-rate video streams, Shadow Play taps into a proprietary path that lets it copy the display output to the GPU's hardware H.264 encoder. This encoder neither strains the CPU nor the GPU's own unified shaders. Since the video stream being saved to a file comes out encoded, its bit-rate is infinitesimally lower than uncompressed AVI.