Nvidia unveils its all-new GeForce GTX 980 and GTX 970 graphics processors - nelsonspermild

Nvidia Chief operating officer Jen-Hsun Huang loves a spectacle. So while you're recitation this sentence, the GPU-manufacturer's founder is regaling thousands of gamers at a 24-60 minutes gaming event the company is sponsoring in Los Angeles with the announcement of Nvidia's latest graphics processor, code-named "Big J. C. Maxwell."

Despite Nvidia's draconian efforts to prevent a recurrence of the leaks that presaged the announcement of its Shield Tablet, details of the new GPUs have been dripping into the Interwebs for several weeks. Here's the official information: The new GPU will ab initio be available in two SKUs, the $329 GeForce GTX 970 and the $549 GeForce GTX 980. The GTX 970 has 1664 processor cores spurting at a theme frequence of 1050MHz (boost clock of 1178MHz), while the beefier GTX 980 has 2048 cores running at 1126MHz (boost clock of 1216MHz). The GTX 970 and the GTX 980 some have a 256-bit interface to 4GB of GDDR5 memory spouting at an effective speed of 7Gbps.

"Big Maxwell" is an apropos encode name for Nvidia's latest graphics processor.

The mounting brackets on card game following Nvidia's reference pattern testament have uncomparable dual-link DVI connector, troika DisplayPort 1.2 interfaces, and one HDMI 2.0 embrasure. HDMI 2.0 support is particularly great because it supports 4K resolution at a refresh rate of 60Hz (the experienced HDMI 1.4b standard is limited to a review order of just 30Hz, which is fine for movies, but terrible for games).

Four new features

To boot to making games run faster—the key promise behind every novel GPU—Nvidia proclaimed four new features that promise to make games flavor more realistic: Dynamic Super Resolve, Multi-Couc-Sampled Anti-aliasing (MFAA), Voxel Spherical Illumination, and VR Direct. Here's a brief overview of those technologies.

Finally, a video card with HDMI 2.0, soh it can drive a 4K display at a refresh rate of 60Hz.

Energising Super Resolution, according to Nvidia, enables the current GPUs to deliver 4K-quality graphics on a 1080p display. The processor effectively renders 4K resolution in the GPU's frame buffer, and then applies a Gaussian filter to downsample the image to 1080p when it's end product to the monitor. This promises to increase visual faithfulness without taking a hit in soma rate. The feature is enabled past nonremittal in Nvidia's GeForce Feel for utility, and the end user may increase the resolution as graduate as 5K if desired. Scott Herkelman, general manager of Nvidia's GeForce business unit of measurement, demoed the result for Maine at a briefing on Tuesday, and it is dazzling.

Nvidia provided this screenshot to show off the capabilities of its Dynamic First-rate Resolution. Observe the image prime of the grasses in this scene.

Aliasing describes the visual distortion that occurs when a GPU renders an image. In the most common examples, not-square images can have jagged edges, and moire can spoil the detail in intricate patterns. Opposed-aliasing, obviously, is a means of coping with this phenomenon, and multi-sample anti-aliasing (MSAA) is the most effective technique.

MSAA kit and caboodle by having the GPU sample ten-fold locations of each pixel in a picture, and then full rendering and combining those pixels in the image that's ultimately rendered along the display. In 4X MSAA, four samples of each pel are taken. For whol its strength, MSAA is very computationally expensive and keister significantly trim back shape rate when information technology's enabled in a game.

Nvidia's Multi-Framing Anti-aliasing (MFAA) functions in a twin forge, but information technology samples pixels over cardinal frames patc rotating the pixels. The technique, reported to Nvidia, delivers results that are precise corresponding to MSAA without the operation hit that MSAA exacts. Herkelman says MFAA is up to 30 per centum faster than MSAA.

Voxel Global Illuminance (VXGI) is the third Brobdingnagian advance to be found in the GeForce GTX 970 and -980. Briefly, IT's a brand-new lighting technique that promises to deliver much finer project quality without requiring a significant performance hit. A Herkelman explained it, a voxel (a portmanteau for meter pel) stores info about the light in a rendered environment.

Games premeditated to run connected previous-generation GPUs ride what Herkelman described as "hand-placed lights." A couple of light sources in a stake environment are placed in fixed locations, so the manner in which the low-cal behaves and its impact on the environment is predetermined in the game's programming code. That's depart of the rationality why only predestinate objects in a game can be destroyed, the programmer must hard code the manner in which the light and shadows will be rendered on those objects.

These images demonstrate the capabilities of Nvidia's new lighting technology. The image connected the right on is a NASA photograph of the first Apollo moon landing. The image on the left was rendered aside Nvidia's GeForce GTX graphics processor.

VXGI enables programmers to place dynamic light sources in a game's environment. Objects in the game behind be assigned properties that determine how they'll chew over or engage the light cast upon them. With this technology, the game coder can only place light sources, and those lights bequeath react dynamically to any changes in the environment. In the rendered image of the Apollo moon landing, above, Herkelman changed viewpoints aside touching the camera all around the scene, and the lighting changed consequently. The way objects reflected operating theater absorbed light changed dynamically, and cast shadows moved in relation to the point of view.

Oculus Breach keep

Nvidia's VR Patrilineal engineering science is intended to benefit upcoming virtual reality headsets so much as the Eye Rift. This parcel of features is designed to tighten reaction time, allow headsets to take full advantage of Nvidia's threefold-GPU SLI technology, and ameliorate stereo-vision sustain. Herkelman demoed a new place-combat game for ME Tuesday, and it looked leagues better than anything I saw over the line of Nvidia's 3D Vision initiative.

Like the underived Maxwell architecture Nvidia announced in February, these new GPUs adopt power-savings tricks originally developed by Nvidia's Tegra Mainframe team. Where a GeForce GTX 680 card with 2GB of memory has a thermal invention big businessman (TDP) paygrad of 195 watts, and a GeForce GTX 780 with 3GB of memory board has a TDP of 250 Watts, the TDP for the GeForce GTX 980 with 4GB is just 165 Watts.

Like its smaller cousin, "Whacking Maxwell" is incredibly power effective.

Despite the lower power usance, Nvidia says the GTX 980 will deliver 5 teraflops of single-precision compute carrying out, compared to 3- and 4TFLOPs for the GTX 680 and -780, severally (a teraflop is one trillion floating-repoint operations per second). The new GTX 970, meanwhile, has a TDP of 145 watts and delivers 4TFLOPs of calculate performance. Thanks to the take down TDPs, reference-design cards will have cardinal 6-tholepin index connectors to supplement the power the cards draw from the PCIe bus.

In the wake of this ware launch, Nvidia is discontinuing its GeForce GTX 780Ti, GTX 780, and GTX 770. The suggested retail price for basic boards supported its GeForce GTX 760 has been reduced to $219.

Update:This article was updated to correctly report the telecasting outputs on Nvidia reference-design cards. The source of the incorrect information came from a presentment provided away Nvidia, but I should have detected that it didn't tally the photograph of the card.

Source: https://www.pcworld.com/article/435373/nvidia-unveils-its-all-new-geforce-gtx-980-and-gtx-970-graphics-processors.html

Posted by: nelsonspermild.blogspot.com

Share this post