NVIDIA GeForce GTX 780 Ti - More Cores Unlocked!
With 25% more CUDA cores than the GTX 780, the NVIDIA GeForce GTX 780 Ti unleashes a total of 2880 cores. Coupled with 3GB of GDDR5 video memory rated at 7000MHz, this card is touted to be the fastest graphics card yet from the company. It is clearly positioned to be the very best consumer graphics card, but will it live up to its promise? We find out.
By Wong Chung Wee -
NVIDIA GeForce GTX 780 Ti - More Cores Unlocked!
The NVIDIA GeForce GTX 780 Ti card was announced in Montreal under a shroud of mystery last month. At NVIDIA’s Montreal event, the card made an appearance but it was whisked away before any of the card’s details, especially its specifications, were made known to public. In addition to its flash-in-the-pan appearance, the price of the card, at US$699, was announced subsequently. We understand this card is most likely seen as NVIDIA’s attempt to steal some thunder from AMD’s recent launch of their new Radeon R9 290 series Hawaii GPU-based cards. The NVIDIA GeForce GTX 780 Ti is clearly targeted at the top-end R9 290X edition.
The NVIDIA GeForce 780 Ti sports a fully unlocked GK110 core, with 2880 CUDA cores. It has a base clock of 876MHz, and a boost clock of 928MHz. Its 3GB of GDDR5 video memory is rated at 7000MHz, with a 384-bit memory interface. (Image Source: NVIDIA)
Based on its appearance, the GTX 780 Ti appears identical to the GTX Titan, GTX 780 and GTX 770 cards. In fact, many would have thought it's nothing more than an overclocked GeForce GTX 780. However, that's far from reality when looking underneath its massive cooler.
Under its hood, the GTX 780 Ti uses the same GK110 core that's used on the GTX 770, GTX 780 and the Titan. However, the GTX 780 Ti has 15 Streaming Multiprocessors (SMX), which is one more than GTX Titan's count of 14! On the GTX 780, its core only features 12 operational SMX units. Just when we thought the GeForce GTX Titan has unlocked all the potential of the GK110, NVIDIA surprised us once more.
As a result, the GTX 780 Ti has a total of 2880 CUDA cores for single precision processing, and a total of 960 CUDA cores for double precision operations. However, do note that the double precision cores on the GTX 780 Ti operate at 1/24 their full speed, to the tune of 210 GFLOPS or 0.21 TFLOPS. On the other hand, despite GTX Titan's lower number of 896 double precision CUDA cores, they operate at full speed to churn 1.3 TFLOPS. This is the major difference that separates the Titan apart from the GTX 780 Ti and a clear signal that the Titan has always been a solution for workstation and engineering tasks (but also doubled up nicely for gaming) as we've personally found from the GeForce GTX Titan PlayTest event we held with NVIDIA.
GeForce GTX 780 Ti | GeForce GTX Titan | GeForce GTX 780 | |
CUDA cores (single precision) | 2880 | 2688 | 2304 |
CUDA cores (double precision) | 960 | 896 | NIL |
Double precision processing speed | 1/24 | Full Speed | NIL |
Double precision processing throughput | 0.21 TFLOPS | 1.3 TFLOPS | NIL |
Back to the GTX 780 Ti, it has a total of 240 texture mapping units, and 48 raster operators. While the GTX 780 Ti has the same of of ROPs as the Titan and GTX 780, its increased number of TMUs will put the card in good stead during 3D scene rendering. As such, we are already expecting the card to perform better.
New Feature - A Balance of Power
The GTX 780 Ti has support for GPU Boost 2.0 that primarily makes use of the GPU core's temperature threshold to dynamically adjust core clock speeds for better performance. It also supports the new fan controller that was first featured in the GTX 780 card. However, the newer GTX 780 Ti has a nifty feature that balances power over its three power sources or rails. Like any modern graphics card, it draws power from the Molex power connectors as well as from the PCIe interface. During overclocking, the user runs the risk of maxing out power draw at any of the three rails. Once this occurs, the card will throttle itself, and will result in a lower overclocked state. However, with this new power balancing feature, the GTX 780 Ti is able draw upon power from the other rails to supplement its needs level up the lagging power sources, so that all of them would be drawing the same maximum power level. As such, the GTX 780 Ti is touted to have better overclocking capabilities than the other GeForce GTX cards.
In terms of video connectivity options, the GTX 780 Ti has two Dual-Link DVI ports, a HDMI port and a DisplayPort port. The card supports G-Sync, which is a new technology that synchronizes the monitor’s refresh rates to the GPU’s draw rates. The end result, really is that monitors will now have a variable refresh rate, ranging from as low as 30Hz to as high as 144Hz. However, the monitor needs to feature a G-Sync add-on board that will significantly increase its costs.
The card features two Dual-Link DVI ports, a HDMI port and a DisplayPort port for support of up to four displays. (Image Source: NVIDIA)
To recap, the launch price of the card is US$699. In the wake of its announcement, NVIDIA also announced price cuts to the incumbent cards, consisting of the GeForce GTX 780 and GTX 770. Their new prices are US$499 and US$329 respectively. However, there will be no price reduction for the GTX Titan as the company wants to preserve the supercomputing pedigree of the card. Although the Titan sports less CUDA cores than the GTX 780 Ti, it has a much more higher double precision compute capabilities than the former. It also sports twice as much video memory buffer at 6GB. At launch, the GTX 780 Ti is positioned as a "high-end enthusiast grade graphics card", and it is expected to take the spot as NVIDIA's top consumer graphics card. Let us put the card through its paces to see if the statement rings true!
Here's a look at how the NVIDIA GeForce GTX 780 Ti card compares against the competing cards:
[hwzcompare]
[products=427431,373666,393642,426095,298166]
[width=175]
[caption=NVIDIA GeForce GTX 780 Ti 3GB GDDR5 and competitive SKUs compared]
[showprices=0]
[/hwzcompare]
Test Setup
These are the specifications of our graphics testbed:
- Intel Core i7-3960X (3.3GHz)
- ASUS P9X79 Pro (Intel X79 chipset) Motherboard
- 4 x 2GB DDR3-1600 G.Skill Ripjaws Memory
- Seagate 7200.10 200GB SATA hard drive (OS)
- Western Digital Caviar Black 7200 RPM 1TB SATA hard drive (Benchmarks + Games)
- Windows 7 Ultimate 64-bit
Below is the list of cards we'll be testing. For the reference GTX 780 card, we had to clock down the ASUS GeForce GTX 780 DirectCU II 3GB GDDR5 to the default operating values of the intended reference card. For the AMD Radeon HD 7970, the downclocked Sapphire Radeon HD 7970 OC 3GB GDDR5 was used. We also took the chance to pit the top-end AMD R9 290X "Hawaii" card against the best ones from NVIDIA, in order to have a gauge of its performance standings.
- NVIDIA GeForce GTX 780 Ti 3GB GDDR5 (ForceWare 331.70)
- NVIDIA GeForce GTX Titan 6GB GDDR5 (ForceWare 331.65)
- NVIDIA GeForce GTX 780 3GB GDDR5 (ForceWare 331.65)
- AMD Radeon R9 290X 4GB GDDR5 (AMD Catalyst 13.11 Beta 7)
- AMD Radeon HD 7970 GHz Edition 3GB GDDR5 (AMD Catalyst 13.9)
Note 1: In temperature and power consumption comparisons, the results used were from the data gathered from the actual reference cards. Please refer to our reviews for the NVIDIA GeForce GTX 780 and AMD Radeon HD 7970 GHz Edition.
Note 2: In our overclocking testing, we overclocked the ASUS GeForce GTX 780 DirectCU II 3GB GDDR5 to simulate an overclocked reference GTX 780 card.
Benchmarks
Here's the full list of benchmarks that we'll be using for our assessment:-
- Futuremark 3DMark 2013
- Crysis 3
- Unigine 4.0 "Heaven"
- Hitman: Absolution
- Far Cry 3
For our temperature and power consumption tests, 3DMark 2011 was used.
3DMark 2013 Results
We kicked off with the 3DMark (2013) Fire Strike benchmark. Its two tests, Fire Strike and Fire Strike Extreme, will put these high-end cards through their paces with extreme levels of tessellation and volumetric illumination, as well as complex smoke simulation using compute shaders and dynamic particle illumination.
The NVIDIA GeForce GTX 780 Ti card took the top spot for both tests; however, the AMD R9 290X card was nipping at its heels. The NVIDIA card only managed to edge ahead by slightly less than 1% for Fire Strike, and for Fire Strike Extreme, the GTX 780 Ti was on par with the Radeon R9 290X. Against the GTX Titan and GTX 780 card, the new top dog showed the advantages of having more CUDA cores, as well as higher speed video memory modules that are rated at 7000GHz for increased memory bandwidth. Overall, the GTX 780 Ti pulled ahead of the once mighty GTX Titan by a margin that ranged from 3.4- to 4.8% and it was also approximately 13% ahead of the GTX 780.
Will these findings translate over to the real-world games? Read on to find out!
Crysis 3 Results
Moving on to our in-game environment test environment consisting of Crysis 3 and our Fraps utility, which is used to measure the average frame rates churned out by each card at a stipulated rendered cutscene of the game title. Crysis 3 is driven by the CryEngine 3, with extreme amounts of tessellation, per-pixel per-object motion blur, Bokeh Depth of Field, displacement mapping on small terrain, particle and volumetric lighting and fog shadows, improved dynamic cloth and vegetation, dynamic caustics and diffuse shadows.
Generally speaking, NVIDIA GeForce GTX series cards fare well on the Crysis 3 benchmark and the GTX 780 Ti is no exception as it took pole positions for all the test scenarios. Against the strongest competitor, the GTX Titan, the GTX 780 Ti was about 7% better on average. What about AMD's fresh new Radeon R9 290X? The GTX 780 Ti easily overtook it with a performance advantage ranging from 17 to 20%.
Unigine 4.0 "Heaven" Results
The Unigine 4.0 "Heaven" benchmark tests GPUs with extreme tessellation, dynamic sky with volumetric clouds, real-time global illumination, and screen-space ambient occlusion among others. The GTX 780 Ti continued to show its advantage in the superiority of its fully unlocked GK110 graphics core and its highly rated graphics memory. It handily took the top spot for all four test scenarios. At the highest setting, it was the only card to crack the 30fps level, with a score of 33.6fps. With this score, it pulled away from the GTX Titan and R9 290X cards, with a margin that ranged from 10- to almost 20%!
Far Cry 3 Results
The PC game title Far Cry 3 is powered by Dunia 2 Engine that is a modified version of Crytek's CryEngine. It features heavy tessellation, high amounts of volumetric lighting, and deferred radiance transfer volumes (global illumination). Hence, we expected the NVIDIA cards to perform well, based on our experience with Crysis 3.
Interestingly, the GTX 780 card showed a spark of brilliance, especially at the resolution of 1920 x 1200 pixels, with the anti-aliasing feature turned off, the GTX 780 actually registered a top score of 74.7fps. This phenomenon was also observed in our initial review of the NVIDIA GeForce GTX 780 card and was constantly repeatably. In all other settings, the GTX 780 Ti card showed its mettle; at the highest game settings used in our test environment, it churned out an average frame rate of 30fps, beating all the other cards. Notably, the newcomer had an easy win of over 20% when compared to the AMD Radeon R9 290X.
Hitman: Absolution Results
Hitman: Absolution is another challenging gaming benchmark. Running on IO Interactive's proprietary Glacier2 engine, this hardware-intensive engine is able to render up to 1200 NPCs simultaneously. Besides the massive crowd of NPCs, it also features Reflective Shadow Mapping (RSM), Direct Compute accelerated Bokeh Depth of Field, extreme tessellation and Ambient Occlusion.
With anti-aliasing turned off, the GTX 780 Ti failed to show the strength of its 2880 CUDA cores as it was edged out by Radeon R9 290X on both resolutions by a small margin. However, with the said feature turned on, the newest NVIDIA GeForce card pulled ahead convincingly!
Temperature
As we now know that the GTX 780 Ti features the fully unlocked GK110 core, we expected the card to run at a higher temperature than the GTX 780 and GTX Titan cards. However, during our tests, the GTX 780 Ti managed to operate at a lower temperature than the GTX Titan, even though the difference was marginal. All three cards have the same TDP of 250W. The other thing you should be aware is that all the new NVIDIA cards supporting GPU Boost 2.0 (which is all the compared cards) have a default GPU threshold of 80 degrees Celsius that they try to maximize to eek out as much performance as possible. This is the main reason all three NVIDIA cards registered similar GPU temperatures. Despite that, the performance results on the earlier pages show how they perform given a similar temperature threshold.
Over to the red camp, it's not looking too great. The Radoen R9 290X has a TDP of 290W with a default maximum temperature threshold set at 95 degrees Celsius! It's not wonder it registered the highest operating temperature of 87 degrees Celsius in our test. Even with greater leeway over the green camp, its actual game performance couldn't keep up with the new GeForce GTX 780 Ti.
Power Consumption
The three NVIDIA GeForce cards shared almost identical idle power draws at 148W or so. At load, they ranged between 430 to 440W bracket - the power draw of the GTX 780 Ti was just 5W higher than the GTX 780, and 10W lower than the Titan. The Radeon R9 290X card had a power draw at load that was similar to the GTX 780 card. This is partly due to each cards' performance-enhancing feature of PowerTune 2.0 and GeForce Boost 2.0 respectively, as both attempt to maximize the available power budget.
Overclocking
For our overclocking efforts, we had high expectations for the new GTX 780 Ti card. To reiterate, the new card features a power balancing feature. This will attempt to prevent maximum power draw on any one of the three power rails that power the card during overclocking. This new power balancing feature is touted to automatically increase power draw on the lesser used power rails so that all three rails end up drawing similar power levels - thus preventing a scenario when the card throttles down when only one of the rails has maxed out. As such, the GTX 780 Ti will be able to achieve higher overclock speeds than the older GTX 780 and 770 GPUs.
In our tests, we managed to overclock the GTX 780 Ti to the highest clock speed of 1176MHz, an increment of 34% over its base clock of 876MHz! For its video memory, we reached an overclock speed of 7500MHz that is an increase of 7% over the default value of 7000MHz. In terms of resultant performance, this overclock had an average gain of approximately 20%!
The AMD R9 290X also showed promising overclocking capabilities as it managed to outclass the overclocked reference GTX 780 card. During our overclocking exercise, we ran the fans at 100%; the AMD R9 290X cooling system registered a 69dB (decibel) noise level; while the GTX 780 Ti's cooling system was much quieter, at just 60dB. As a note to our readers, during normal operations, the AMD system had a noise level of 60dB; while the GTX 780's noise level measured 55dB. So we could see, or hear, how noisy the cooling system of the AMD R9 290X was, in comparison to the GTX 780 Ti.
Conclusion - A Truly High-End Card for Enthusiasts Gamers
True to the words of NVIDIA, the GeForce GTX 780 Ti graphics card is designed for serious PC gamers and overclockers. Its performance on both artificial and in-game benchmarks are very impressive, as it ranked first in most situations. In fact, it was the only card to churn out average frame rates that numbered 30fps and above for some benchmarks. Its overclocking performance resulted in an increment of over 34% over its base clock; this was truly beyond expectations as we normally experience gains between 15- to 20%. This meant that its new power balancing feature worked just as intended, allowing the GeForce GTX 780 Ti to plough through and climb the overclocking ranks higher than any other card in recent history. Before we break out the champagne, note that the performance gain due to overclocking was about 20%, which is in line with the overclocking performance of other high-end cards.
Priced at US$699, this top-notch gaming card truly commands its premium price.
Its truly impressive performance was its ability to keep total system power draw to a 'low' of 432W, despite the increase in CUDA cores, as well as its massively faster video memory that is rated to perform at 7000MHz. At the same time, its highest temperature was just two degrees higher than the GTX 780, at 79 degrees Celsius. Although the temperature outcomes is kind of controlled by GPU Boost 2.0's default settings, what's impressive is the kind of performance delivered at the same temperature threshold as the other top NVIDIA cards.
In a nutshell, it performed about 10% better than the Titan on our benchmarks. Against the GTX 780 and R9 290X cards, it was about 10- to 17% better than them. For a premium price of US$699, this card is meant for enthusiast gamers who need to play games at the absolute highest settings at a resolution of 1920 x 1200 or even 2560 x 1600 pixels. In its overclocked state, the user is able to milk quite a bit of extra performance from the card. In fact, for gamers with deeper pockets, they can even consider purchasing a pair of GTX 780 Ti cards for a 2-way SLI configuration. According to NVIDIA, this setup is perfect for Ultra HD or 4K gaming and we're not surprised considering the performance churned out by a single card. However, this will entail additional costs as the user will need a 4K monitor like the 31.5-inch ASUS PQ321Q UHD monitor.
The GTX 780 Ti is without a doubt a gaming card built for the enthusiast gamer, with its quiet but top-notch performance and an efficient cooling system to boot. But as with all things extreme, they come at a premium.
Our articles may contain affiliate links. If you buy through these links, we may earn a small commission.