780 vs 980: Nvidia GTX 780 vs 980

GeForce GTX 780 vs GeForce GTX 980


GeForce GTX 780 vs GeForce GTX 980


  1. Home
  2. VGA Benchmarks
  3. GeForce GTX 780 vs GeForce GTX 980
  • GeForce GTX 780

    100%

  • GeForce GTX 980

    135%

Relative performance

  • GeForce GTX 780

    100%

  • GeForce GTX 980

    133%

Relative performance

Reasons to consider GeForce GTX 780
Supports PhysX
Supports G-Sync
Supports ShadowPlay (allows game streaming/recording with minimum performance penalty)
Based on an outdated architecture (Nvidia Kepler), there are less performance optimizations for current games and applications
Reasons to consider GeForce GTX 980
33% higher gaming performance.
85 watts lower power draw. This might be a strong point if your current power supply is not enough to handle the GeForce GTX 780 .
This is a much newer product, it might have better long term support.
Supports PhysX
Supports G-Sync
Supports ShadowPlay (allows game streaming/recording with minimum performance penalty)
Based on an outdated architecture (Nvidia Maxwell), there may be no performance optimizations for current games and applications

HWBench recommends GeForce GTX 980

The GeForce GTX 980 is the better performing card based on the game benchmark suite used (13 combinations of games and resolutions).

Core Configuration
GeForce GTX 780 GeForce GTX 980
GPU Name GK110 (GK110-300-A1) vs GM204 (GM204-400-A1)
Fab Process 28 nm vs 28 nm
Die Size 561 mm² vs 398 mm²
Transistors 7,080 million vs 5,200 million
Shaders 2304 vs 2048
Compute Units 12 vs 16
Core clock 863 MHz vs 1127 MHz
ROPs 48 vs 64
TMUs 192 vs 128

Memory Configuration
GeForce GTX 780 GeForce GTX 980
Memory Type GDDR5 vs GDDR5
Bus Width 384 bit vs 256 bit
Memory Speed 1502 MHz


6008 MHz effective
vs 1753 MHz

7012 MHz effective
Memory Size 3072 Mb vs 4096 Mb
Additional details
GeForce GTX 780 GeForce GTX 980
TDP 250 watts vs 165 watts
Release Date 23 May 2013 vs 19 Sep 2014
  • GeForce GTX 780

    41. 40 GP/s

  • GeForce GTX 980

    72.10 GP/s

GigaPixels — higher is better

  • GeForce GTX 780

    166.00 GT/s

  • GeForce GTX 980

    144.30 GT/s

GigaTexels — higher is better

  • GeForce GTX 780

    288.00 GB/s

  • GeForce GTX 980

    224.40 GB/s

GB/s — higher is better

  • GeForce GTX 780

    3977.00 GFLOPs

  • GeForce GTX 980

    4616.00 GFLOPs

GFLOPs — higher is better

  • GeForce GTX 780

    13770

  • GeForce GTX 980

    18720

Points (higher is better)

DX11, Ultra Quality, 4xMSAA,EP3 Gator Bait

  • GeForce GTX 780

    52

  • GeForce GTX 980

    71

FPS (higher is better)

DX11, Max Details, 16:1 AF, 2xMSAA

  • GeForce GTX 780

    68

  • GeForce GTX 980

    88

FPS (higher is better)

DX11,Max Details, 16:1 HQ-AF, +AA

  • GeForce GTX 780

    39

  • GeForce GTX 980

    60

FPS (higher is better)

DX11, Very High Details

  • GeForce GTX 780

    57

  • GeForce GTX 980

    71

FPS (higher is better)

DX11, Ultra Quality, 4xMSAA,EP3 Gator Bait

  • GeForce GTX 780

    36

  • GeForce GTX 980

    49

FPS (higher is better)

DX11, Ultra, DDOD, FXAA

  • GeForce GTX 780

    73

  • GeForce GTX 980

    86

FPS (higher is better)

DX11, Max Details, 16:1 AF, 2xMSAA

  • GeForce GTX 780

    47

  • GeForce GTX 980

    61

FPS (higher is better)

DX11, High Quality, 2x MSAA, 16x AF

  • GeForce GTX 780

    54

  • GeForce GTX 980

    67

FPS (higher is better)

DX11,Max Details, 16:1 HQ-AF, +AA

  • GeForce GTX 780

    29

  • GeForce GTX 980

    48

FPS (higher is better)

DX11, Very High Details

  • GeForce GTX 780

    43

  • GeForce GTX 980

    52

FPS (higher is better)

DX11, Max Details, 16:1 AF, 2xMSAA

  • GeForce GTX 780

    24

  • GeForce GTX 980

    31

FPS (higher is better)

DX11,Max Details, 16:1 HQ-AF, +AA

  • GeForce GTX 780

    19

  • GeForce GTX 980

    28

FPS (higher is better)

DX11, Very High Details

  • GeForce GTX 780

    23

  • GeForce GTX 980

    29

FPS (higher is better)

VS
GeForce GTX 780 GeForce GTX TITAN
VS
GeForce GTX 780 Radeon R9 380X
VS
GeForce GTX 980 GeForce GTX 1650 SUPER
VS
GeForce GTX 980 Radeon RX 580
VS
Radeon RX 5500 GeForce GTX 1660
VS
GeForce GTX 1660 Radeon R9 Nano

Please enable JavaScript to view the comments powered by Disqus.

Gigabyte GeForce GTX 780 vs Nvidia GeForce GTX 980: What is the difference?

45points

Gigabyte GeForce GTX 780

47points

Nvidia GeForce GTX 980

Comparison winner

vs

54 facts in comparison

Gigabyte GeForce GTX 780

Nvidia GeForce GTX 980

Why is Gigabyte GeForce GTX 780 better than Nvidia GeForce GTX 980?

  • 22 GTexels/s higher texture rate?
    166 GTexels/svs144 GTexels/s
  • 64GB/s more memory bandwidth?
    288GB/svs224GB/s
  • 128bit wider memory bus width?
    384bitvs256bit
  • 256 more shading units?
    2304vs2048
  • 1880million more transistors?
    7080 millionvs5200 million
  • 64 more texture mapping units (TMUs)?
    192vs128
  • Has Double Precision Floating Point (DPFP)?
  • 2°C lower idle GPU temperature?
    30°Cvs32°C

Why is Nvidia GeForce GTX 980 better than Gigabyte GeForce GTX 780?

  • 263MHz faster GPU clock speed?
    1126MHzvs863MHz
  • 0. 62 TFLOPS higher floating-point performance?
    4.6 TFLOPSvs3.98 TFLOPS
  • 30.7 GPixel/s higher pixel rate?
    72.1 GPixel/svs41.4 GPixel/s
  • 85W lower TDP?
    165Wvs250W
  • 251MHz faster memory clock speed?
    1753MHzvs1502MHz
  • 1004MHz higher effective memory clock speed?
    7012MHzvs6008MHz
  • 33.33% more VRAM?
    4GBvs3GB
  • 1 newer version of DirectX?
    12vs11

Which are the most popular comparisons?

Gigabyte GeForce GTX 780

vs

Nvidia GeForce GTX 1650

Nvidia GeForce GTX 980

vs

XFX HD 6950 XXX 1GB

Gigabyte GeForce GTX 780

vs

Nvidia GeForce GTX 1660 Ti

Nvidia GeForce GTX 980

vs

Nvidia GeForce GTX 1050

Gigabyte GeForce GTX 780

vs

Nvidia GeForce GTX 750 Ti

Nvidia GeForce GTX 980

vs

Nvidia GeForce RTX 2060

Gigabyte GeForce GTX 780

vs

Nvidia GeForce RTX 2060

Nvidia GeForce GTX 980

vs

Nvidia GeForce RTX 3050 Laptop

Gigabyte GeForce GTX 780

vs

AMD Radeon RX 580

Nvidia GeForce GTX 980

vs

XFX HD 6950 XXX 2GB

Gigabyte GeForce GTX 780

vs

Asus ROG Strix RX 470

Nvidia GeForce GTX 980

vs

AMD Radeon RX 580

Gigabyte GeForce GTX 780

vs

Nvidia GeForce GTX 960

Nvidia GeForce GTX 980

vs

Nvidia GeForce RTX 3050 Ti Laptop

Gigabyte GeForce GTX 780

vs

AMD Radeon RX 560X

Nvidia GeForce GTX 980

vs

Nvidia GeForce GTX 1070

Gigabyte GeForce GTX 780

vs

Nvidia GeForce GTX 1050

Nvidia GeForce GTX 980

vs

Nvidia Tesla C2050

Nvidia GeForce GTX 980

vs

Nvidia GeForce GTX 970

Price comparison

User reviews

Performance

1. GPU clock speed

863MHz

1126MHz

The graphics processing unit (GPU) has a higher clock speed.

2.GPU turbo

902MHz

1216MHz

When the GPU is running below its limitations, it can boost to a higher clock speed in order to give increased performance.

3.pixel rate

41.4 GPixel/s

72.1 GPixel/s

The number of pixels that can be rendered to the screen every second.

4.floating-point performance

3.98 TFLOPS

4.6 TFLOPS

Floating-point performance is a measurement of the raw processing power of the GPU.

5.texture rate

166 GTexels/s

144 GTexels/s

The number of textured pixels that can be rendered to the screen every second.

6.GPU memory speed

1502MHz

1753MHz

The memory clock speed is one aspect that determines the memory bandwidth.

7.shading units

Shading units (or stream processors) are small processors within the graphics card that are responsible for processing different aspects of the image.

8.texture mapping units (TMUs)

TMUs take textures and map them to the geometry of a 3D scene. More TMUs will typically mean that texture information is processed faster.

9.render output units (ROPs)

The ROPs are responsible for some of the final steps of the rendering process, writing the final pixel data to memory and carrying out other tasks such as anti-aliasing to improve the look of graphics.

Memory

1.effective memory speed

6008MHz

7012MHz

The effective memory clock speed is calculated from the size and data rate of the memory. Higher clock speeds can give increased performance in games and other apps.

2. maximum memory bandwidth

288GB/s

224GB/s

This is the maximum rate that data can be read from or stored into memory.

3.VRAM

VRAM (video RAM) is the dedicated memory of a graphics card. More VRAM generally allows you to run games at higher settings, especially for things like texture resolution.

4.memory bus width

384bit

256bit

A wider bus width means that it can carry more data per cycle. It is an important factor of memory performance, and therefore the general performance of the graphics card.

5.version of GDDR memory

Newer versions of GDDR memory offer improvements such as higher transfer rates that give increased performance.

6.Supports ECC memory

✖Gigabyte GeForce GTX 780

✖Nvidia GeForce GTX 980

Error-correcting code memory can detect and correct data corruption. It is used when is it essential to avoid corruption, such as scientific computing or when running a server.

Features

1.DirectX version

DirectX is used in games, with newer versions supporting better graphics.

2.OpenGL version

OpenGL is used in games, with newer versions supporting better graphics.

3.OpenCL version

Some apps use OpenCL to apply the power of the graphics processing unit (GPU) for non-graphical computing. Newer versions introduce more functionality and better performance.

4.Supports multi-display technology

✔Gigabyte GeForce GTX 780

✔Nvidia GeForce GTX 980

The graphics card supports multi-display technology. This allows you to configure multiple monitors in order to create a more immersive gaming experience, such as having a wider field of view.

5.load GPU temperature

A lower load temperature means that the card produces less heat and its cooling system performs better.

6.supports ray tracing

✖Gigabyte GeForce GTX 780

✖Nvidia GeForce GTX 980

Ray tracing is an advanced light rendering technique that provides more realistic lighting, shadows, and reflections in games.

7.Supports 3D

✔Gigabyte GeForce GTX 780

✔Nvidia GeForce GTX 980

Allows you to view in 3D (if you have a 3D display and glasses).

8.supports DLSS

✖Gigabyte GeForce GTX 780

✖Nvidia GeForce GTX 980

DLSS (Deep Learning Super Sampling) is an upscaling technology powered by AI. It allows the graphics card to render games at a lower resolution and upscale them to a higher resolution with near-native visual quality and increased performance. DLSS is only available on select games.

9.PassMark (G3D) result

Unknown. Help us by suggesting a value. (Nvidia GeForce GTX 980)

This benchmark measures the graphics performance of a video card. Source: PassMark.

Ports

1.has an HDMI output

✔Gigabyte GeForce GTX 780

✔Nvidia GeForce GTX 980

Devices with a HDMI or mini HDMI port can transfer high definition video and audio to a display.

2.HDMI ports

Unknown. Help us by suggesting a value. (Gigabyte GeForce GTX 780)

Unknown. Help us by suggesting a value. (Nvidia GeForce GTX 980)

More HDMI ports mean that you can simultaneously connect numerous devices, such as video game consoles and set-top boxes.

3.HDMI version

Unknown. Help us by suggesting a value. (Gigabyte GeForce GTX 780)

Unknown. Help us by suggesting a value. (Nvidia GeForce GTX 980)

Newer versions of HDMI support higher bandwidth, which allows for higher resolutions and frame rates.

4.DisplayPort outputs

Allows you to connect to a display using DisplayPort.

5.DVI outputs

Allows you to connect to a display using DVI.

6.mini DisplayPort outputs

Allows you to connect to a display using mini-DisplayPort.

Price comparison

Cancel

Which are the best graphics cards?

Kwikset 780 vs. 980-Say goodbye to your worries by securing your home with a quality lock

This site contains affiliate links to products. We may receive a commission for purchases made through these links.

You can get the most expensive items for your home, but without a secure lock, you risk losing it all. Kwikset ha you back since it offers safe and strong locks. Let us compare Kwikset 780 vs. 980.

My parents nurtured the habit of saving in me from a young age. As an adult, I now understand the importance of saving. I maintain a savings account to buy the most precious items for my home. I have managed to fill my house with elegant items from my small salary. The thought of someone invading my home scares me. When I heard about a break-in in my neighborhood, I had to sneak from work to go and confirm that my house was secure. I wanted to have peace of mind, and so I thought of replacing the locks. I was torn between choosing Kwikset 780 and 980, so I came up with this comparison.

What are the differences between Kwikset 780 and 980? How do they compare

Name Kwikset 980 780
Security standards Grade 1 Grade 2
Finish Black iron Venetian bronze
Weight 12 ounces 1 pound
Call to action Check here Check here

Kwikset 780 vs. 980- What are the main differences

Quality

According to the standards of locks set by reputable organizations such as BHMA, Kwikset 980 is a grade 1 single cylinder deadbolt. It has passed through numerous tests and is accredited to be a high-quality lock that is long lasting. Kwikset 780 falls under the grade 2 category making it low in quality.

Purpose

Kwikset 980 is a high-quality lock that can be used for both residential and commercial purposes. It is strong enough to withstand daily abuse and attacks. 780, on the other hand, is only suitable for residential applications since it lacks some of the features that make a lock resistant to physical attacks.

Rekeying mechanism

The users of Kwikset 980 find the rekeying tool efficient and reliable. It does not disappoint you when you need to make a new key. Most people who have used 780 are not happy about the rekey mechanism of this lock. Sometimes, it does not work as expected and can cause inconveniences as you try to control who gets access to your home.

Finishing

Different materials are used in the finishing of these two locks. Kwikset 980 has a black iron finishing while 780 comes with some bronze highlights that make it look flashy. The type of finish used in the lock is important since some users look for colors and materials that can easily complement their hardware. You can also shop around for the same models in different finishes if you are not content with the regular type.

Kwikset 780

Not all the doors in your home require locks, but the exterior one needs a secure lock to protect your home from invaders. One of the locks in the market is Kwikset 780. It is a single cylinder deadbolt that is attractive and tough. You can unlock the door with a key on the exterior or use the thumb turn level mechanism on the interior. This feature comes in handy during emergencies when you need to evacuate people out of the house fast. The presence of an adjustable latch makes this lock fit on any standard door.

Thedeadbolt also incorporates the use of SmartKey technology which comes with numerous benefits. It allows you to rekey your lock if someone loses a key or if you want to deny some people access to your home. By rekeying your lock, old keys become obsolete. The lock also contains a BumpGuard that prevents your door from bumping techniques. It includes a 5-pin cylinder that has two steel balls to deliver effective drill resistance. Its finishing reveals some bronze highlights which add style to the lock.

Pros

  • It is easy to install using a screwdriver
  • Comes with the SmartKey security system

Cons

  • Some parts may feel loose

Kwikset 980

980 is a grade 1 single cylinder deadbolt that uses different technological systems to boost its performance. For instance, it makes use of side locking bar mechanism which enhances security by protecting your lock from bumping. The lock also uses Smartkey security system that gives you total control of who can access your home. Thanks to this mechanism, you can rekey your lock within minutes. The installation process of this lock is a breeze since most people install it in less than 15 minutes.

It is also equipped with a BumpGuard which enhances its security and an adjustable latch that makes it ideal for all standard doors. The pins and racks in the SmartKey cylinder make the lock strong and resistant to attacks through drilling and use of saws and hammers. It is a tough deadbolt that allows you to unlock the exterior using a key and the interior via the thumb turn lever. The manufacturers use materials such as iron and stainless steel in the construction of this model increasing its durability. It comes in a black finish that can match your hardware. Your purchase gives you a lifetime warranty to fix defective parts.

Pros

  • High quality and durable deadbolt
  • It is not prone to lock bumping and is resistant to drilling

Cons

  • Comes with confusing installation instructions

Conclusion

Over the years, Kwikset has managed to remain on top of the competition in the lock industry. The company continues to produce high-quality locks equipped with advanced features for maximum security. You can always find a lock that has specific features to meet your needs. Though the company provides different models, we have compared Kwikset 780 vs. 980.

After reviewing both of them, we chose Kwikset 980 to be the winner with compelling reasons. First, it is a grade 1 single cylinder deadbolt that excels in quality and durability. The manufacturers equip it with SmartKey security system to increase convenience and boost security. I chose it since I don’t have to hire a locksmith to install my lock on the door; thus it saves me some additional expenses. The inclusion of an adjustable latch, BumpGuard and thumb turn lever also increases its flexibility.

Can someone open Kwikset 780 after I have rekeyed it using an old key?

No. Once you rekey your lock, you change its s configuration. This makes old keys obsolete. Rekeying is a useful mechanism when you don’t want a person to access your home anymore.

Which materials are the best for secure locks?

A good lock should be made of materials such as iron and steel. Reputable companies such as Kwikset make use of such materials to create sturdy locks that can withstand some form of abuse.

What if I cannot understand the instructions on my lock manual?

If you are new to kwikset deadbolts, you may find some of the instructions hard to follow during installation. The retailer or a certified locksmith can help you install the lock.

Why does Kwikset 980 have an adjustable latch?

This feature comes in handy during installation. It makes the lock suitable for standard doors with different thicknesses.

Nvidia’s GeForce GTX 980 and 970 graphics cards reviewed

2014 has been a strange year for graphics chips. Many of the GeForce and Radeon graphics cards currently on the market are based on GPUs over two years old. Rather than freshening up their entire silicon lineups top-to-bottom like in the past, AMD and Nvidia have chosen to take smaller, incremental steps forward.

Both firms introduced larger chips based on existing GPU architectures last year. Then, two weeks ago, the Tonga GPU in the Radeon R9 285 surprised us with formidable new technology that’s still somewhat mysterious. Before that, this past spring, Nvidia unveiled its next-gen “Maxwell” graphics architecture on a single, small chip aboard the GeForce GTX 750 Ti. We could tell by testing that card’s GM107 GPU that Maxwell was substantially more power-efficient than the prior-gen Kepler architecture. However, no larger Maxwell-based chips were forthcoming.

Until today, that is.

At long last, a larger Maxwell derivative is here, powering a pair of new graphics cards: the flagship GeForce GTX 980 and its more affordable sibling, the GTX 970. These cards move the needle on price, performance, and power efficiency like only a new generation of technology can do.

The middle Maxwell: GM204

The chip that powers these new GeForce cards is known as the GM204. Although the Maxwell architecture is bursting with intriguing little innovations, the GM204 is really about two big things: way more pixel throughput and vastly improved energy efficiency. Most of what you need to know about this chip boils down to those two things—and how they translate into real-world performance.

Here’s a look at the basic specs of the GM204 versus some notable contemporaries:

ROP

pixels/

clock

Texels

filtered/

clock

(int/fp16)

Shader

processors

Rasterized

triangles/

clock

Memory

interface

width (bits)

Estimated

transistor

count

(Millions)

Die
size

(mm²)

Fab

process

GK104 32 128/128 1536 4 256 3500 294 28 nm
GK110 48 240/240 2880 5 384 7100 551 28 nm
GM204 64 128/128 2048 4 256 5200 416 (398) 28 nm
Tahiti 32 128/64 2048 2 384 4310 365 28 nm
Tonga 32 (48) 128/64 2048 4 256 (384) 5000 359 28 nm
Hawaii 64 176/88 2816 4 512 6200 438 28 nm

Nvidia did well to focus on energy efficiency with Maxwell, because foundries like TSMC, which makes Nvidia’s GPUs, have struggled to move to smaller process geometries. Like the entire prior generation of GPUs, GM204 is built on a 28-nm process. (Although TSMC is apparently now shipping some 20-nm silicon, Nvidia tell us the 28-nm process is more cost-effective for this chip, and that assessment is consistent with what we’ve heard elsewhere.) Thus, the GM204 can’t rely on the goodness that comes from a process shrink; it has to improve performance and power efficiency by other means.

Notice that the GM204 is more of a middleweight fighter, not a heavyweight like the GK110 GPU in the GeForce GTX 780- and Titan-series cards. Nvidia considers the GM204 the successor to the GK104 chip that powers the GeForce GTX 680 and 770, and I think that’s appropriate. The GM204 and the GK104 both have a 256-bit memory interface and the same number of texture filtering units, for instance.

Size-wise, the GM204 falls somewhere in between the GK104 and the larger GK110. Where exactly is an interesting question. When I first asked, Nvidia told me it wouldn’t divulge the new chip’s die area, so I took the heatsink off of a GTX 980 card, pulled out a pair of calipers, and measured it myself. The result: almost a perfect square of 20.4 mm by 20.4 mm. That works out to 416 mm². Shortly after I had my numbers, Nvidia changed its tune and supplied its own die-size figure: 398 mm². I suppose they’re measuring differently. Make of that what you will.

The GM204’s closest competition from AMD is the new Tonga GPU that powers the Radeon R9 285. We know for a fact that not all of Tonga’s capabilities are enabled on the 285, though, and I have my own crackpot theories about how the full Tonga looks. I said in my review that I think it has a 384-bit memory interface, and after more noodling on the subject, I strongly suspect it has 48 pixels per clock of ROP throughput waiting to be enabled. Mark my words so you can mock me later if I’m wrong!


Functional block diagram of the GM204 GPU. Source: Nvidia.

One reason I suspect Tonga has more ROPs is that it just makes sense to increase a GPU’s pixel throughput in the era of 4K and high-PPI displays. I believe the GM204’s ROPs are meant to be represented by the deep blue Chiclets™ surrounding the L2 cache in the fakey diagram above. At 64 pixels per clock, the GM204 has 50% more per-clock ROP throughput than the big Kepler GK110 chip—and double that of the GK104. That’s a sizeable commitment, an enormous increase over the previous generation, and it means the GM204 is ready to paint lots of pixels.

At 2048KB, the GM204’s L2 cache is relatively large, too. The GK104 has only a quarter of the cache, at 512KB, and even the GK110’s 1536KB L2 cache is smaller. Caches are growing by leaps and bounds in recent graphics architectures, as a means of both amplifying bandwidth and improving power efficiency (since memory access burns a lot of power.)


Functional block diagram of the Maxwell SM. Source: Nvidia.

The larger cache is just one way Nvidia has pursued increased efficiency in the Maxwell architecture. Many of the other gains come from the new Maxwell core structure, known as the shader multiprocessor or SMM. The GM204 has a total of 16 SMMs. Each of them is broken into four “quads,” and each of those has a single 32-wide vector execution unit with its own associated control logic. Threads are still scheduled in “warps,” or groups of 32 threads, with one thread per “lane” executing sequentially on each vec32 execution unit. Nvidia says the SMM’s new structure makes scheduling tasks on Maxwell simpler and more efficient, which is one reason this architecture uses less energy per instruction than Kepler. Maxwell’s efficiency improvements come from several sources, though, and I hope to have time to explore them in more depth in a future article.

For now, let’s look at the new GeForce cards.

The GeForce GTX 970 and 980

Nvidia’s new silicon has spawned a pair of video cards, the GeForce GTX 970 and 980. Pictured above is the 980, the new high end of Nvidia’s consumer graphics card lineup (excepting the ultra-expensive Titan series.) Here’s the lowdown on the two new GeForce models:

GPU

base

clock

(MHz)

GPU

boost

clock

(MHz)

ROP

pixels/

clock

Texels

filtered/

clock

Shader

pro-

cessors

Memory

path

(bits)

GDDR5
transfer

rate

Peak

power

draw

Intro

price

GTX
970
1050 1178 64 104 1664 256 7 GT/s 145W $329
GTX
980
1126 1216 64 128 2048 256 7 GT/s 165W $549

At $549, the GeForce GTX 980 ain’t cheap. What you’ll want to notice, though, is its lethal combination of clock speeds and power rating. The GTX 980’s full-fledged GM204 runs at a “boost” speed of over 1.2GHz—and that’s a typical, not peak, operating frequency in games. The card’s 4GB of GDDR5 memory runs at a nosebleed-inducing 7 GT/s, too. That’s one way to squeeze the most out of a 256-bit memory interface. Meanwhile, the GTX 980’s TDP is just 165W—well below the 250W rating of the GeForce GTX 780 Ti or the 195W rating of the previous-gen GTX 680. That’s quite a testament to the efficiency of the Maxwell architecture, especially since all of these chips are fabbed with 28-nm process tech.

Thanks to its frugal power needs, the GTX 980 requires only a pair of 6-pin aux power inputs—and it could darn near get by with just one of them. Although this card has the same familiar, aluminum-clad reference cooler as the last crop of GeForces, its port configuration is something new: a trio of DisplayPort outputs, an HDMI port, and a dual-link DVI connector. Given the ascendancy of DisplayPort for use with 4K and G-Sync monitors, this is a welcome change.

GeForce GTX 980 cards in the form you see above should be available from online retailers almost immediately, as I understand it. Nvidia had the first batch of cards produced with its reference cooler, and I expect custom designs from board makers to follow pretty quickly. Many of those are likely to be clocked higher than the reference board we have for testing.

I’ve gotta admit, though, that I’m more excited about the prospects for the GeForce GTX 970. This card has a much lower suggested starting price of $329, and rather than produce a reference design, Nvidia has left it up to board makers to create their own GTX 970 cards. Have a look at what Asus has come up with:

This is the Strix GTX 970 OC Edition, and it’s pretty swanky. The headline news here is this card’s 1114MHz base and 1253MHz boost clocks, which are quite a bit higher than what Nvidia’s reference specs call for. Heck, the boost clock is even higher than the GTX 980’s and could go a long way in making up for the loss of three SMMs in the GTX 970. Since the GTX 970 has the same 4GB of GDDR5 memory at 7 GT/s, this card’s delivered performance should be within shouting distance of the GTX 980’s. The price? Just $339.99.

Asus has tricked out the Strix with a bunch of special features, which I’d be happy to talk about if I hadn’t just received this thing literally yesterday. I have noted that the cooler’s twin fans only spin when needed; they go completely still until the GPU temperature rises above a certain level. For some classes of games—things like DOTA 2—Asus claims this card can operate completely fanlessly.

On the downside, I’m a little disappointed with the move back to dual DVI outputs and a single DisplayPort connector. I suppose the more conventional port setup will appeal to those with existing multi-monitor setups, but it may prove to be a frustrating limitation in the future.

On the, er, weird side, Asus has elected to give the Strix 970 a single aux power input of the 8-pin variety. That’s unusual, and Asus touts this config as an advantage, since it simplifies cable management. I suppose that’s true, and perhaps 8-pin power connectors are now common enough that it makes sense to use them by default. Still, I was surprised not to see a dongle in the box to convert two 6-pin connectors into an 8-pin one.

Here’s another version of the GTX 970 that just made its way into Damage Labs. The MSI GTX 970 Gaming 4G has the same clock speeds as the Strix, but its cooler is even flashier. MSI says this card will sell for $359.99. I haven’t yet managed to test this puppy completely, but we’ll follow up on it in a future article.

Nvidia is trimming its lineup to make room for these new GeForces. The firm is so confident in the Maxwell cards that it’s ending shipments of GeForce GTX 770, 780, and 780 Ti cards, effective now. Meanwhile, the GeForce GTX 760’s price is dropping to $219. That should be a pretty good clue about how the newest GeForces alter the landscape.

Sizing ’em up

Do the math involving the clock speeds and per-clock potency of the GM204 cards, and you’ll end up with a comparative table that looks something like this:

Peak pixel

fill rate

(Gpixels/s)

Peak

bilinear

filtering

int8/fp16

(Gtexels/s)

Peak

shader

arithmetic

rate

(tflops)

Peak

rasterization

rate

(Gtris/s)

Memory
bandwidth
(GB/s)
Radeon
R9 285
29 103/51 3. 3 3.7 176
Radeon
R9 280X
32 128/64 4.1 2.0 288
Radeon
R9 290
61 152/76 4.8 3.8 320
Radeon
R9 290X
64 176/88 5.6 4.0 320
GeForce GTX 770 35 139/139 3.3 4.3 224
GeForce GTX
780
43 173/173 4.2 4.5 288
GeForce GTX
780 Ti
45 223/223 5.3 4.6 336
GeForce GTX
970
75 123/123 3. 9 4.7 224
Asus Strix GTX
970
80 130/130 4.2 5.0 224
GeForce GTX
980
78 156/156 5.0 4.9 224

The rates above aren’t destiny, but they do tend to be a pretty good indicator of how a given GPU will perform. Since the GM204 can run at higher clock speeds than the GK110, the GeForce GTX 980 is able to give even the mighty GTX 780 Ti a run for its money in terms of shader arithmetic—with a peak rate of five teraflops—and rasterization. The 980 trails a bit in the texture filtering department, but look at that pixel fill rate. Nothing we’ve seen before comes all that close.

Contrast that prowess to the GTX 980’s relatively modest memory bandwidth, which is no higher than the prior-gen GTX 770’s, and you might ask some questions about how this new balance of resources is supposed to work. The answer, it turns out, is similar to what we saw with AMD’s Tonga GPU a couple of weeks back.

Nvidia Senior VP of Hardware Engineering Jonah Alben revealed in a press briefing that Maxwell makes more effective use of its memory bandwidth by compressing rendered frames with a form of delta-based compression. (That is, checking to see whether a pixel’s color has changed from a neighboring pixel and perhaps only storing information about the amount of change.) In fact, Alben told us Nvidia GPUs have used delta-based compression since the Fermi generation. Maxwell’s compression is the third iteration. The combination of better compression and more effective caching allows Maxwell to reduce memory bandwidth use substantially compared to Kepler—from 17% to 29% in workloads based on popular games, according to Alben.

So what happens when we try 3DMark Vantage’s color fill test, which is limited by pixel fill rate and memory bandwidth, on the GTX 980?

Yeah, that works pretty darned well. The GTX 980 paints over twice as many pixels in this test as the GK104-based GTX 770, even though the two cards have the same 224 GB/s of memory bandwidth.

On paper, the GTX 980’s other big weakness looks to be texturing capacity, and in practice, the 980 samples textures at a lower rate than its competition. The GTX 970 even falls slightly behind the GTX 770 in this synthetic test, just as it does on paper. We’ll have to see how much of a limitation this weakness turns out to be in real games.

The GM204 cards have some of the highest rasterization rates in the table above, and they make good on that promise in these tests of tessellation and particle manipulation. The GTX 980 sets new highs in both cases.

In theory, the GeForce GTX 780 Ti has more flops on tap and higher memory bandwidth than the GTX 980, so it should perform best in these synthetic tests of shader performance. In reality, though, Maxwell delivers on more of its potential. Even with a big memory bandwidth handicap, the GTX 980 outperforms the GTX 780 Ti in both benchmarks. Only AMD’s big Hawaii in the Radeon R9 290X is more potent—and not by a huge margin.

Maxwell’s other innovations

In addition to the performance and efficiency gains we’ve discussed, Nvidia has built some nifty new features into Maxwell-based products. I’ve been awake for five days straight on a cocktail of pure Arabica coffee, Five Hour Energy shots, methadone, ginkgo biloba, and anti-freeze. The hallucinations are starting to get distracting, but I’ll attempt to convey some sense of the new features if I can. To make that happen, I’m resorting to an old-school TR crutch, the vaunted bulleted list of features. Here’s what else is new in Maxwell:

  • Something called Dynamic Super Resolution — Some of us graphics nerds have been bugging Nvidia for years about exposing supersampled antialiasing as an easy-to-access control panel option or something along those lines. They’ve finally found a way to make it happen, and they’ve taken the concept one step further. Supersampling generally involves rendering two or more samples per pixel and then combining the results in order to get a higher-quality result, and it was in use in real-time graphics as far back as the 3dfx days. Multisampled AA, which more efficiently targets only object edges, has largely supplanted it.

    DSR brings supersampling back by letting users select higher resolutions, via in-game menus, than their monitors can natively support. For instance, a gamer with a 1080p display could choose the most popular 4K resolution of 3840×2160, which is exactly four times the size of his display. The graphics card will then render the game at a full 3840×2160 internally and scale the output down to 1920×1080 in order to match the display. In doing so, every single pixel on the screen will have been sampled four times, producing a smoother, higher-quality result than what’s possible with any form of multisampling.

    DSR goes beyond traditional supersampling, though. Rather than just sample multiple times from within a pixel, it uses a 13-tap gaussian downsizing filter to produce a nice, soft result. The images it produces are likely to be a little softer and more cinematic-feeling. This filter has the advantage of being able to resize from intermediate resolutions. For instance, the user could select 2560×1440, and DSR would downsize to 1080p even though it’s not a perfect 2:1 or 4:1 fit.

    Sounds good in theory, but I’ve not had the time to attach a lower-res monitor to my Maxwell cards to try it yet. (The images above come from Nvidia.) I’m sure we’ll revisit this feature in more detail later. Nvidia says DSR will begin its life as a Maxwell exclusive, but the company expects this feature to make its way to some older GeForce cards via driver updates eventually.

  • MFAA — M-F’in’ AA? No, tragically, the name is not that epic. It’s just “multi-frame sampled antialiasing,” apparently. I think every new GPU launch requires a novel AA method, and we keep getting some interesting new attempts, so why not? MFAA seeks to achieve the quality of 4X multisampling at the performance cost of 2X multisampling. To do so, it combines several elements. The subpixel sample points vary from one pixel to the next in interleaved, screen-door fashion, and they swap every other frame. The algorithm then “borrows” samples from past frames and combines them with current samples to produce higher-quality results—that is, smoother edges.

    Nvidia showed a demo of this feature in action, and it does seem to work. I have questions about exactly how well it works when the camera and on-screen objects are moving rapidly, since borrowing temporally from past frames probably falls apart with too much motion. Unfortunately, Nvidia wasn’t willing to say exactly how the MFAA routine decides what samples to borrow from past frames, so it’s something of a mystery. One wonders whether it will really be any better than pretty decent methods like SMAA, which are already widely deployed in games and offer similar promises of 4X MSAA quality at 2X performance.

    MFAA isn’t yet enabled in Nvidia’s drivers, so we can’t test it. One plus of MFAA, once it arrives, is that it can be enabled via a simple on-off switch; it doesn’t require integration into the game engine like Nvidia’s TXAA does.

    More interesting than MFAA itself is the fact that Maxwell has much more flexibility with regard to AA sampling points than Kepler. On Maxwell, each pixel in a 4×4 quad can have its own unique set of subpixel sample points, and the GPU can vary those points from one frame to the next. That means Maxwell could allow for much more sophisticated pseudo-stochastic sampling methods once it’s been in the hands of Nvidia’s software engineers for more than a few weeks.

  • Substantial new rendering capabilities for DX12 — Yes, DirectX 12 isn’t just about reducing overhead. It will have some features that require new GPU hardware, and Maxwell includes several of them. In fact, Direct3D Lead Developer Max McMullen from Microsoft delivered the news at the Maxwell press event. What’s more, a new revision of Direct3D 11, version 11.3, will also expose these same hardware features. The highlights included ROVs, typed UAV loads, volume tiled resources, and conservative rasterization.

    I’d like to explain more about what precisely these features are and what they do, but that will have to wait for a future article. Interestingly enough, many of these features are not present in the GM107 chip that debuted earlier this year. GM204 contains some significant new technology.

  • Accelerated voxel-based global illumination — There’s some overlap with the prior point and this one, but it’s worth calling out the fact that Nvidia has built hardware into Maxwell—some of which won’t be exposed via DX12—to accelerate a specific method of global illumination the company has been developing for some time. Maxwell can “multicast” incoming geometry to multiple viewports in order to facilitate the conversion of objects into a low-res series of blocks or 3D pixels known as voxels. Once the voxel grid is created, it can be used to simulate light bounces in order to create high-quality, physically correct indirect lighting. That could prove to be a huge advance for real-time graphics and gaming, and it deserves more attention than I can give it right now.
  • VR Direct — This is essentially a suite of features Nvidia has been implementing in its drivers to better support virtual reality headsets like the Oculus Rift. Most of those features have to do with reducing the latency between user input (head movements, usually) and visual output (when images reflecting the input reach the screen). Nvidia has even implemented in its drivers an improved version of Carmack’s “time warp” method of repositioning a frame post-rendering. At least, that is the claim. We’ve not yet been able to try a Rift with this feature enabled.

Our testing methods

We’ve tested as many different competing video cards against the new GeForces as was practical. However, there’s no way we can test everything our readers might be using. A lot of the cards we used are renamed versions of older products with very similar or even identical specifications. Here’s a quick table that will decode some of these names for you.

Original Closest

current

equivalent

GeForce GTX 670 GeForce GTX 760
GeForce GTX 680 GeForce GTX 770
Radeon HD 7950 Boost Radeon R9 280
Radeon HD 7970 GHz Radeon R9 280X

If you’re a GeForce GTX 680 owner, Nvidia thinks you may want to upgrade to the GTX 980 once you’ve seen what it can do. Just keep in mind that our results for the GTX 770 should almost exactly match a GTX 680’s.

Most of the numbers you’ll see on the following pages were captured with Fraps, a software tool that can record the rendering time for each frame of animation. We sometimes use a tool called FCAT to capture exactly when each frame was delivered to the display, but that’s usually not necessary in order to get good data with single-GPU setups. We have, however, filtered our Fraps results using a three-frame moving average. This filter should account for the effect of the three-frame submission queue in Direct3D. If you see a frame time spike in our results, it’s likely a delay that would affect when the frame reaches the display.

We didn’t use Fraps with BF4. Instead, we captured frame times directly from the game engine itself using BF4‘s built-in tools. We didn’t use our low-pass filter on those results.

As ever, we did our best to deliver clean benchmark numbers. Our test systems were configured like so:

Processor Core i7-3820
Motherboard Gigabyte
X79-UD3
Chipset Intel X79
Express
Memory size 16GB (4 DIMMs)
Memory type Corsair
Vengeance CMZ16GX3M4X1600C9
DDR3 SDRAM at 1600MHz
Memory timings 9-9-9-24
1T
Chipset drivers INF update
9. 2.3.1023

Rapid Storage Technology Enterprise 3.6.0.1093

Audio Integrated
X79/ALC898

with Realtek 6.0.1.7071 drivers

Hard drive Kingston
HyperX 480GB SATA
Power supply Corsair
AX850
OS Windows
8.1 Pro
Driver
revision
GPU
base

core clock

(MHz)

GPU
boost

clock

(MHz)

Memory

clock

(MHz)

Memory

size

(GB)

Radeon
HD 7950 Boost
Catalyst 14. 7 beta
2
925 1250 3072
Radeon
R9 285
Catalyst 14.7 beta
2
973 1375 2048
XFX Radeon
R9 280X
Catalyst 14.7 beta
2
1000 1500 3072
Radeon
R9 290
Catalyst 14. 7 beta
2
947 1250 4096
XFX Radeon
R9 290X
Catalyst 14.7 beta
2
1000 1250 4096
GeForce
GTX 760
GeForce
340.52
980 1033 1502 2048
GeForce
GTX 770
GeForce
340. 52
1046 1085 1753 2048
GeForce
GTX 780
GeForce
340.52
863 902 1502 3072
GeForce
GTX 780 Ti
GeForce
340.52
876 928 1750 3072
Asus Strix
GTX 970
GeForce
344. 07
1114 1253 1753 4096
GeForce
GTX 980
GeForce
344.07
1127 1216 1753 4096

Thanks to Intel, Corsair, Kingston, and Gigabyte for helping to outfit our test rigs with some of the finest hardware available. AMD, Nvidia, and the makers of the various products supplied the graphics cards for testing, as well.

Also, our FCAT video capture and analysis rig has some pretty demanding storage requirements. For it, Corsair has provided four 256GB Neutron SSDs, which we’ve assembled into a RAID 0 array for our primary capture storage device. When that array fills up, we copy the captured videos to our RAID 1 array, comprised of a pair of 4TB Black hard drives provided by WD.

Unless otherwise specified, image quality settings for the graphics cards were left at the control panel defaults. Vertical refresh sync (vsync) was disabled for all tests.

The tests and methods we employ are generally publicly available and reproducible. If you have questions about our methods, hit our forums to talk with us about them.

Thief

For this first test, I decided to use Thief‘s built-in automated benchmark, since we can’t measure performance with AMD’s Mantle API using Fraps. Unfortunately, this benchmark is pretty simplistic, with only FPS average(as well as a maximum and minimum numbers, for all that’s worth.)

Welp, this is a pretty nice start for the GTX 980. Nvidia’s newest is faster than anything else we tested at both resolutions, and the GTX 970 isn’t far behind. The fastest single-GPU Radeon, the R9 290X, can’t quite keep up, even when using AMD’s proprietary Mantle API.

The generational increase from the GK104-based GTX 770 to the GM204-based GTX 980 is enormous.

Watch Dogs

Click the buttons above to cycle through the plots. Each card’s frame times are from one of the three test runs we conducted for that card. Most of these cards run Watch_Dogs pretty well at these settings, with no major spikes in frame times.

The GTX 980 is the overall champ in the FPS average sweeps, and it backs that victory up by taking the top spot in our 99th percentile frame time metric. That means in-game animations should be generally smooth, not just a collection of high frame rates punctuated by slowdowns. Amazingly, even the Asus GTX 970 outperforms the GTX 780 Ti.

We can better understand in-game animation fluidity by looking at the “tail” of the frame time distribution for each card, which shows us what happens in the most difficult frames. As you can see, the GTX 970 and 980 perform well right up to the last few percentage points worth of frames.

These “time spent beyond X” graphs are meant to show “badness,” those instances where animation my be less than fluid—or at least less than perfect. The 50-ms threshold is the most notable one, since it corresponds to a 20-FPS average. We figure if you’re not rendering any faster than 20 FPS, even for a moment, then the user is likely to perceive a slowdown. 33 ms correlates to 30 FPS or a 30Hz refresh rate. Go beyond that with vsync on, and you’re into the bad voodoo of quantization slowdowns. And 16.7 ms correlates to 60 FPS, that golden mark that we’d like to achieve (or surpass) for each and every frame.

The GTX 980 almost stays entirely below the 16.7-ms threshold here, which means it’s not far from perfectly matching a 60Hz monitor’s desire for a new frame every refresh interval. When you slice it this way, the GTX 980’s lead over the competition looks even larger.

Overall, this is a nice set of results in that the frame-time-based metrics all seem to correspond with the FPS average. None of the cards are exhibiting the sort of bad behavior that our time-sensitive metrics would highlight. That said, the new GeForces perform very well, and the $339 Asus Strix GTX 970 very nearly matches the performance of AMD’s fastest single-GPU product, the Radeon R9 290X.

Crysis 3

A look at the frame time plots will show you that the Radeons encounter a couple of slowdowns during our test session. By the seat of my pants, I know that’s the spot where I’m shooting exploding arrows at the bad guys like one of the Duke boys. Nvidia cards used to slow down similarly at this same spot, but a driver update earlier this year eliminated that problem. As a result, GeForce cards take the top three places in our 99th percentile frame time metric, despite the R9 290X having the second-fastest FPS average.

Those slowdowns on the Radeons are evident in the last two to three percentage points worth of frames.

Our “badess” metric captures the difference most dramatically. The GeForces spend no time beyond our 50-ms cutoff and very little above the 33-ms mark, while the Radeons spend many tens of milliseconds waiting for those long-latency frames.

Battlefield 4

We tested those last few games at 2560×1440. Let’s switch to 4K and see how the new GeForces handle that.

Although the GTX 980 has a slight edge in terms of average FPS, the Radeon R9 290X performs a bit better overall when running Tomb Raider at 4K according to our time-sensitive metrics. This isn’t the sort of difference one would tend to perceive, though—and even the fastest cards would be struggling to provide a frame to a 60Hz display on every other refresh cycle. In order words, this ain’t the smoothest animation.

Borderlands 2

Borderlands 2 isn’t an especially challenging game for GPUs of this class to handle at 2560×1440, but I’d hoped we could learn something interesting here—and I think we have. Nearly every card has a 99th percentile frame time below 16.7 ms, which means all but the last 1% of frames is produced at a silky-smooth 60 cycles per second. The GeForces struggle just a little more than the Radeons in that last 1% of frames, though, as indicated by our “badness” metric.

Also, notice that I’ve added a new wrinkle to our “badness” results for this review: time spent beyond the 8.3-ms threshold. If you can stay below that threshold, you can pump out frames at 120Hz—perfect for a fast gaming display. Going with a fast graphics card does help considerably on this front, and the GTX 780 Ti gets the closest to achieving that goal.

A caveat: when you’re looking at frame times in such tiny intervals, things like CPU bottlenecks and run-to-run variations tend to play a larger role than they otherwise would. I think we may need to conduct more than three runs per card in order to get really reliable results on this front.

Power consumption

Please note that our “under load” tests aren’t conducted in an absolute peak scenario. Instead, we have the cards running a real game, Crysis 3, in order to show us power draw with a more typical workload.

We already know the GeForce GTX 980 generally outperforms the GTX 780 Ti and the Radeon R9 290X. Now we know that it does so while consuming substantially less power—virtually no more than the prior-gen GK104 GPU does aboard the GeForce GTX 770. That’s a remarkable achievement.

Noise levels and GPU temperatures

Don’t get too hung up on the noise levels at idle (and with the display off) here. The noise floor in my basement lab tends to vary a bit depending on factors I can’t quite pinpoint. I think the speed of the CPU fan may be the biggest culprit, but I’m not sure why it tends to vary.

Anyhow, the bottom line is that all of these cards are pretty quiet at idle. The only one that seems really different to my ears is the GTX 760, whose cooler is cheap and kind of whiny. The fact that the Asus Strix card completely stops its cooler at idle is most excellent and would count for more in an utterly silent environment.

The Nvidia reference cooler on the GTX 980 performs well here, almost exactly like it does on the GTX 770. Meanwhile, the dual-fan cooler on the Asus Strix GTX 970 has just as much heat to remove as Nvidia’s stock cooler—our power results tell us that—but it does so while making less noise and keeping its GPU at a much cooler temperature.

Conclusions

As usual, we’ll sum up our test results with a couple of value scatter plots. The best values tend toward the upper left corner of each plot, where performance is higher and prices are lower.

By either measure, the GeForce GTX 980 is the fastest single-GPU graphics card we tested. With the possible exception of the pricey Titan Black, it’s also the fastest single-GPU graphics card on the planet. Although $549 is a lot to pay, the GTX 980 manages to deliver appreciably better value than the GeForce GTX 780 Ti, which it replaces. The new GeForce flagship outperforms AMD’s Radeon R9 290X, as well. If you want the best, the GTX 980 is the card to get.

That’s an assessment based on price and performance, but we know from the preceding pages that the GTX 980’s other attributes are positive, too. The GM204 GPU’s power efficiency is unmatched among high-end GPUs. With Nvidia’s stock cooler, that translates into lower noise levels under load than any older GeForce or current Radeon in this class. I’m also quite happy with the suite of extras Nvidia has built into the Maxwell GPU, such as DSR for improved image quality and a big ROP count for high performance at 4K resolutions. This graphics architecture takes us a full generation beyond Kepler—and thus beyond what’s in current game consoles like the PlayStation 4 and Xbone.

All of that’s quite nice, if you insist on having the best and fastest. However, the GeForce GTX 970 is what really excites the value nexus in my frugal Midwestern noggin. For $339, the Asus Strix GTX 970 card we tested is astonishing, with overall performance not far from the GeForce GTX 780 Ti at a fraction of the price. This thing checks all of the boxes, with good looks, incredibly quiet operation, and relatively cool operating temperatures that suggest substantial overclocking headroom. As long as you can live with the fact that it has only one DisplayPort output, the Strix 970 looks like a mighty tempting upgrade option for anyone who has that itch.

Then again, MSI’s GTX 970 Gaming seems pretty nice, too. I’m not sure there are any bad choices here.

The folks who have tough choices to make are Nvidia’s competitors in the Radeon camp. What do you do when your single-GPU flagship has been bested by a smaller chip on a cheaper card? Cut prices, of course, and a well-placed industry source has informed us that a price reduction on the R9 290X is indeed imminent, likely early next week. We expect the R9 290X to drop to $399 and to receive a freshened-up Never Settle game bundle, too.

The revised price would certainly improve the 290X’s place on our value scatter plot. AMD would then be in the position of offering slightly better performance than the GeForce GTX 970 for a little more money—and with 100W of additional power consumption and associated fan noise. Does a game bundle make up for the extra power draw? I’m not sure what to make of that question. I’m also not sure whether a fully enabled Tonga variant could do much to alter the math.

I am happy to see vigorous competition and innovation giving PC gamers a better set of choices, though. Feels like it’s been a long time coming, and I’m still wondering at the fact that Nvidia was able to pull off this sort of advance without the benefit of a process shrink. We’ll have to dig deeper into some of Maxwell’s features, including multi-GPU operation, in the coming weeks.

Enjoy our work? Pay what you want to subscribe and support us.

Snapdragon 855 vs Kirin 980: tests and benchmarks

VS

Snapdragon 855

Kirin 980

We compared two 8-core processors: Qualcomm Snapdragon 855 (with Adreno 640 graphics) and HiSilicon Kirin 980 (Mali G76 MP10). Here you will find the pros and cons of each chip, technical specs, and comprehensive tests in benchmarks, like AnTuTu and Geekbench.

  1. Review
  2. Differences
  3. Benchmarks
  4. AnTuTu v9
  5. GeekBench 5
  6. Gaming
  7. Specs
  8. Comments (2)

Review

General comparison of performance, power consumption, and other indicators

CPU Performance

Single and multi-core processor tests

Snapdragon 855

60

Kirin 980

55

Gaming Performance

GPU performance in games and OpenCL/Vulcan

Snapdragon 855

57

Kirin 980

46

Battery life

Efficiency of battery consumption

Snapdragon 855

76

Kirin 980

71

NanoReview Score

Overall chip score

Snapdragon 855

63

Kirin 980

56

Key Differences

Main differences and advantages of each chip

Pros of Qualcomm Snapdragon 855

  • Developers optimize games for Snapdragon processors more often than for Kirin
  • Performs 30% better in floating-point computations
  • 9% higher CPU clock speed (2840 vs 2600 MHz)
  • Supports 7% higher memory bandwidth (34. 1 against 31.78 GB/s)
  • Shows better (up to 7%) AnTuTu 9 score – 512K vs 479K
  • Better instruction set architecture

Pros of HiSilicon Kirin 980

  • Has 2 MB larger L3 cache size than the Snapdragon 855
  • Higher GPU frequency (~23%)

Benchmarks

Performance tests in popular benchmarks

SoC:

Snapdragon 855

vs

Kirin 980

AnTuTu 9

The AnTuTu Benchmark measures CPU, GPU, RAM, and I/O performance in different scenarios

Snapdragon 855
+7%

512447

Kirin 980

479948

CPU 140558 140916
GPU 183147 143456
Memory 87772 83772
UX 105950 115457
Total score 512447 479948

▶️ Submit your AnTuTu result

GeekBench 5

The GeekBench test shows raw single-threaded and multithreaded CPU performance

Single-Core Score

Snapdragon 855
+6%

737

Kirin 980

693

Multi-Core Score

Snapdragon 855
+5%

2595

Kirin 980

2474

Image compression 143. 55 Mpixels/s 123.8 Mpixels/s
Face detection 23.7 images/s 20.4 images/s
Speech recognition 44.8 words/s 47.2 words/s
Machine learning 45.65 images/s 47.4 images/s
Camera shooting 24.2 images/s 23.2 images/s
HTML 5 2.93 Mnodes/s 2.39 Mnodes/s
SQLite 783.05 Krows/s 655 Krows/s

3DMark

A cross-platform benchmark that assesses graphics performance in Vulkan (Metal)

3DMark Wild Life Performance

Snapdragon 855
+23%

3054

Kirin 980

2489

Stability 93% 48%
Graphics test 18 FPS 14 FPS
Score 3054 2489

Gaming

Table of average FPS and graphics settings in mobile games

PUBG Mobile 58 FPS
[Ultra]
56 FPS
[Ultra]
Call of Duty: Mobile 56 FPS
[Ultra]
39 FPS
[Ultra]
Fortnite 28 FPS
[Ultra]
28 FPS
[High]
Shadowgun Legends 51 FPS
[Ultra]
51 FPS
[Ultra]
World of Tanks Blitz 59 FPS
[Ultra]
60 FPS
[Ultra]
Mobile Legends: Bang Bang 57 FPS
[Ultra]
60 FPS
[Ultra]
Device Xiaomi Mi 9T Pro
1080 x 2340
Huawei Nova 5T
1080 x 2340

We provide average results. FPS may differ, depending on game version, OS and other factors.

Specifications

Full list of technical specifications of Snapdragon 855 and Kirin 980

Architecture 1x 2.84 GHz – Cortex-A76 (Kryo 485 Gold)
3x 2.42 GHz – Cortex-A76 (Kryo 485 Gold)
4x 1.8 GHz – Cortex-A55 (Kryo 485 Silver)
2x 2.6 GHz – Cortex-A76
2x 1.92 GHz – Cortex-A76
4x 1.8 GHz – Cortex-A55
Cores 8 8
Frequency 2840 MHz 2600 MHz
Instruction set ARMv8.1-A ARMv8-A
L1 cache 384 KB 512 KB
L2 cache 768 KB 512 KB
L3 cache 2 MB 4 MB
Process 7 nanometers 7 nanometers
Transistor count 6. 7 billion 6.9 billion
TDP 10 W 6 W

Graphics

GPU name Adreno 640 Mali G76 MP10
Architecture Adreno 600 Bifrost
GPU frequency 585 MHz 720 MHz
Execution units 2 10
Shading units 384 160
FLOPS 899 Gigaflops 691 Gigaflops
Vulkan version 1.1 1.0
OpenCL version 2.0 1.2
DirectX version 12 12

Memory

Memory type LPDDR4X LPDDR4X
Memory frequency 2133 MHz 2133 MHz
Bus 4x 16 Bit 4x 16 Bit
Max bandwidth 34. 1 Gbit/s 31.78 Gbit/s
Max size 16 GB 8 GB

Multimedia (ISP)

Neural processor (NPU) Hexagon 690 Yes
Storage type UFS 3.0 UFS 3.0
Max display resolution 3840 x 2160 3120 x 1440
Max camera resolution 1x 192MP, 2x 22MP 1x 48MP, 2x 20MP
Video capture 4K at 120FPS 4K at 30FPS
Video playback 8K at 30FPS, 4K at 120FPS 4K at 60FPS
Video codecs H.264, H.265, VP8, VP9 H.264, H.265, VP9
Audio codecs AAC, AIFF, CAF, MP3, MP4, WAV AIFF, CAF, MP3, MP4, WAV

Connectivity

Modem X24 LTE, X50 5G
4G support LTE Cat. 20 LTE Cat. 21
5G support Yes No
Download speed Up to 2000 Mbps Up to 1400 Mbps
Upload speed Up to 316 Mbps Up to 200 Mbps
Wi-Fi 6 6
Bluetooth 5.0 5.0
Navigation GPS, GLONASS, Beidou, Galileo, QZSS, SBAS GPS, GLONASS
Announced December 2018 August 2018
Class Flagship Flagship
Model number SM8150
Official page Qualcomm Snapdragon 855 official site HiSilicon Kirin 980 official site

Cast your vote

So, which SoC would you choose?

Snapdragon 855

1010 (45. 4%)

Kirin 980

1214 (54.6%)

Total votes: 2224

Related Comparisons

1.
Snapdragon 855 vs Snapdragon 870

2.
Snapdragon 855 vs Snapdragon 765G

3.
Snapdragon 855 vs Snapdragon 860

4.
Snapdragon 855 vs Snapdragon 778G Plus

5.
Kirin 980 vs Snapdragon 870

6.
Kirin 980 vs Snapdragon 778G

7.
Kirin 980 vs Helio G96

▶️ Compare other chipsets

Unboxing: Strix GeForce GTX 980 And Compared To GTX 780 Ti, Matrix R9 290X | ROG

With four new world records already under Strix GTX 980’s belt, the coming few weeks should get interesting as we keep an eye on all the new benchmark results recorded with this card.  Built on Nvidia’s acclaimed 2nd-gen Maxwell architecture with customized ASUS components and DirectCU II cooling system, this video card is a GeForce to be reckoned with.  

Let’s pop the bonnet to see what’s roaring inside, and then compare the differences between the Strix GTX 980 and its predecessor — the ASUS GTX 780 Ti DirectCU II — and the widely-popular Matrix R9 290X Platinum.

The anticipation of opening a brand-new high-end video card is never without a bit of suspense and a whole lot of OOOOHs and AAAAHHHs.   Strix GTX 980 is indeed no different.   

When opening it up, keep the box and its contents in pristine condition, because it’s simply too beautiful to be ravaged. 

Inside the box you will find a well-protected Strix GTX 980 graphics card, user’s guide, software CD, metal customization stickers, and a power cable.

ASUS’ high-end graphics cards are perennially the popular choice among PC enthusiasts, when you take out the card out of the box you can already get a sense of why that is. This beast isn’t just filled with quality components, the whole package certainly feels premium.  It is immediately obvious that the gargantuan DirectCU II heatsink is 220% larger than reference, with ultra-phat 10mm copper heatpipes all encased in a metal shroud (not plastic).

One of the key features of the Strix GTX 980 is the 0dB Fan Technology, which keeps the fans off unless the GPU temperature reaches ~65ºC.  Paired with the huge heatsink and the amazingly efficient new Maxwell chip GM204, that threshold won’t be reached easily.  When you run a benchmark (as you normally would do every time you get new hardware) then the twin fans will kick in whenever needed, even then, you can hardly hear them!  DirectCU II technology makes the card 30% cooler and three times quieter, unless you’re playing a game involving turbines, get the fan noise out of the game.  At the rear of the PCB is the gorgeous brushed-metal ASUS back-plate, featured there intentionally since that is usually the side showing.  There are five choices of outputs: DVI, HDMI 2.0 and three DisplayPort 1.2 (four of which can be used concurrently).

This card comes factory-overclocked to make you go faster than blazingly-fast. It is clocked at 1,279MHz (4.5% boost from 1,178MHz), with 4GB of GDDR5 RAM operating at 7,012MHz (effective) on the 256bit memory bus.  The 2048-core GPU is fed by the DIGI+ VRM with a 10-phase power design, high-quality super-alloy capacitors and chokes.  ASUS has not factory-overclocked aggressively, much thought has been put into a balanced design, focusing on minimizing under-load noise and heat, while also improving power efficiency, although if you choose to overclock some more (of course you do, and not just some), there is still plenty of headroom; enough to please the most extreme enthusiast — as proven by those 3DMark records.  In other words, ASUS didn’t just slap on a chunky heatsink then push the clock speed up as high as possible.  The PCB is very similar to the Strix 970.

This dual-slot card is 288.6mm x 134.4mm x 40.9mm in size. There is plenty of power overhead from the 6-pin and an 8-pin power connectors. 

If you compare the Strix GTX980 (bottom) and the GTX 780 Ti (top), you can see they are almost identical in size. Both have brushed-metal backplates and metal shrouds, the heatsinks and heatpipes are kept in the same format since it works so well.  While the GTX 780 Ti used two 8-pin connectors, the Strix GTX 980 only requires a 6-pin and an 8-pin due to the efficiency of new technology. 

The GTX 780 Ti has 2 DVI ports, 1 HDMI port and 1 DisplayPort, this time the GTX 980 has opted to go with 1 DVI port, 1 HDMI port and a trio of DisplayPorts, making it suitable for G-Sync surround if you wanted to use three PG278Q’s together!

Physically the ASUS ROG Matrix Platinum R9 290X measures 290. 718 X 152.4 X 40.6 mm, the GTX 980 is 288.6mm x 134.4mm x 40.9mm in size, so the ROG R9 290X is slightly longer and taller.

 

  •  

 

The ROG theme sets the Matrix Platinum apart visually from the Strix, along with its ROG colour-coded load indicator, actively displaying how much load the GPU has.  This is unique to the ROG hardware.

All three cards are similar in size; they all utilize the DirectCU II cooling system for superior cooling, and they are all quality high-end cards with killer-looks.

 

  •  

 

Here’s ASUS GTX 780 Ti DirectCU II, Strix GTX 980 DirectCU II and ROG Matrix R9 290X Platinum side by side so you can see how they compare.

ASUS GTX 980 DIGI+ DirectCU II dismantle GM207 GTX 780 Ti R9 290X ROG Matrix Platinum R9 290X Strix GTX 980 Unboxing Articles Product

0024 166 GTexels/s vs 144 GTexels/s

  • 64GB/s more memory bandwidth?
    288GB/s vs 224GB/s
  • 128bit wider memory bus?
    384bit vs 256bit
  • 256 more stream processors?
    2304 vs 2048
  • 1880million more transistors?
    7080 million vs 5200 million
  • 64 more texture units (TMUs)?
    192 vs 128
  • Has DPFP?
  • 2°C lower GPU idle temperature?
    30°C vs 32°C
  • Why is Nvidia GeForce GTX 980 better than Gigabyte GeForce GTX 780?

    • GPU frequency 263MHz higher?
      1126MHz vs 863MHz
    • 0. 62 TFLOPS higher than FLOPS?
      4.6 TFLOPS vs 3.98 TFLOPS
    • 30.7 GPixel/s higher pixel rate?
      72.1 GPixel/s vs 41.4 GPixel/s
    • 85W below TDP?
      165W vs 250W
    • 251MHz faster memory speed?
      1753MHz vs 1502MHz
    • 1004MHz higher effective clock speed?
      7012MHz vs 6008MHz
    • 33.33% more VRAM?
      4GB vs 3GB
    • 1 newer version of DirectX?
      12 vs 11

    What are the most popular comparisons?

    Gigabyte GeForce GTX 780

    vs

    Nvidia GeForce GTX 1650

    Nvidia GeForce GTX 980

    vs

    XFX HD 6950 XXX 1GB

    Gigabyte GeForce GTX 780

    vs

    Nvidia GeForce GTX 1660 Ti

    Nvidia Nvidia GeForce GTX 1050

    Gigabyte GeForce GTX 780

    vs

    Nvidia GeForce GTX 750 Ti

    Nvidia GeForce GTX 980

    vs

    Nvidia GeForce RTX 2060

    Gigabyte GeForce GTX 780

    vs

    Nvidia GeForce RTX 2060

    Nvidia GeForce GTX 980

    vs

    Nvidia GeForce RTX 3050 Laptop

    Gigabyte GeForce AMD Radeon RX 580

    Nvidia GeForce GTX 980

    vs

    XFX HD 6950 XXX 2GB

    Gigabyte GeForce GTX 703

    vs

    0004 Asus ROG Strix RX 470

    Nvidia GeForce GTX 980

    vs

    AMD Radeon RX 580

    Gigabyte GeForce GTX 780

    vs

    Nvidia GeForce GTX 960

    Nvidia GeForce GTX 980

    vs

    Nvidia GeForce RTX 3050 Ti Laptop

    Gigabyte GeForce GTX 780

    vs

    AMD Radeon RX 560X

    Nvidia GeForce GTX 980

    vs

    Nvidia GeForce GTX 1070 80 Gigabyte

    0003

    902MHz

    1216MHz

    When the GPU is running below its limits, it can jump to a higher clock speed to increase performance.

    3.pixel rate

    41.4 GPixel/s

    72.1 GPixel/s

    The number of pixels that can be displayed on the screen every second.

    4.flops

    3.98 TFLOPS

    4.6 TFLOPS

    FLOPS is a measure of GPU processing power.

    5.texture size

    166 GTexels/s

    144 GTexels/s

    The number of textured pixels that can be displayed on the screen every second.

    6.GPU memory speed

    1502MHz

    1753MHz

    Memory speed is one aspect that determines memory bandwidth.

    7.shading patterns

    Shading units (or stream processors) are small processors in a video card that are responsible for processing various aspects of an image.

    8.textured units (TMUs)

    TMUs accept textured units and bind them to the geometric layout of the 3D scene. More TMUs generally means texture information is processed faster.

    9 ROPs

    ROPs are responsible for some of the final steps of the rendering process, such as writing the final pixel data to memory and for performing other tasks such as anti-aliasing to improve the appearance of graphics.

    Memory

    1.memory effective speed

    6008MHz

    7012MHz

    The effective memory clock frequency is calculated from the memory size and data transfer rate. A higher clock speed can give better performance in games and other applications.

    2.max memory bandwidth

    288GB/s

    224GB/s

    This is the maximum rate at which data can be read from or stored in memory.

    3.VRAM

    VRAM (video RAM) is the dedicated memory of the graphics card. More VRAM usually allows you to run games at higher settings, especially for things like texture resolution.

    4.memory bus width

    384bit

    256bit

    Wider memory bus means it can carry more data per cycle. This is an important factor in memory performance, and therefore the overall performance of the graphics card.

    5.versions of GDDR memory

    Later versions of GDDR memory offer improvements such as higher data transfer rates, which improve performance.

    6. Supports memory debug code

    ✖Gigabyte GeForce GTX 780

    ✖Nvidia GeForce GTX 980

    Memory debug code can detect and fix data corruption. It is used when necessary to avoid distortion, such as in scientific computing or when starting a server.

    Functions

    1.DirectX version

    DirectX is used in games with a new version that supports better graphics.

    2nd version of OpenGL

    The newer version of OpenGL, the better graphics quality in games.

    OpenCL version 3.

    Some applications use OpenCL to use the power of the graphics processing unit (GPU) for non-graphical computing. Newer versions are more functional and better quality.

    4. Supports multi-monitor technology

    ✔Gigabyte GeForce GTX 780

    ✔Nvidia GeForce GTX 980

    The video card has the ability to connect multiple screens. This allows you to set up multiple monitors at the same time to create a more immersive gaming experience, such as a wider field of view.

    5.GPU Temperature at Boot

    Lower boot temperature means that the card generates less heat and the cooling system works better.

    6.supports ray tracing

    ✖Gigabyte GeForce GTX 780

    ✖Nvidia GeForce GTX 980

    Ray tracing is an advanced light rendering technique that provides more realistic lighting, shadows and reflections in games.

    7.Supports 3D

    ✔Gigabyte GeForce GTX 780

    ✔Nvidia GeForce GTX 980

    Allows you to view in 3D (if you have a 3D screen and glasses).

    8.supports DLSS

    ✖Gigabyte GeForce GTX 780

    ✖Nvidia GeForce GTX 980

    DLSS (Deep Learning Super Sampling) is an AI based scaling technology. This allows the graphics card to render games at lower resolutions and upscale them to higher resolutions with near-native visual quality and improved performance. DLSS is only available in some games.

    9. PassMark result (G3D)

    Unknown. Help us offer a price. (Nvidia GeForce GTX 980)

    This test measures the graphics performance of a graphics card. Source: Pass Mark.

    Ports

    1.has HDMI output

    ✔Gigabyte GeForce GTX 780

    ✔Nvidia GeForce GTX 980

    Devices with HDMI or mini HDMI ports can stream HD video and audio to the connected display.

    2.HDMI connectors

    Unknown. Help us offer a price. (Gigabyte GeForce GTX 780)

    Unknown. Help us offer a price. (Nvidia GeForce GTX 980)

    More HDMI connections allow you to connect multiple devices at the same time, such as game consoles and TVs.

    3rd HDMI version

    Unknown. Help us offer a price. (Gigabyte GeForce GTX 780)

    Unknown. Help us offer a price. (Nvidia GeForce GTX 980)

    Newer versions of HDMI support higher bandwidth, resulting in higher resolutions and frame rates.

    4. DisplayPort outputs

    Allows connection to a display using DisplayPort.

    5.DVI outputs

    Allows connection to a display using DVI.

    Mini DisplayPort 6.outs

    Allows connection to a display using Mini DisplayPort.

    Price match

    Cancel

    Which graphics cards are better?

    Test: comparison between GeForce GTX 980 and GeForce GTX 780 Ti at equal clock speeds

    Last week NVIDIA introduced the new GeForce GTX 980 and GTX 970 graphics cards, we published a detailed test and review comparing them with the previous generation. But in the article, we used the reference version of the GeForce GTX 980, which was compared with previous reference cards. This comparison is not entirely complete, since the market today is dominated by alternatively designed GeForce GTX 780 Ti graphics cards, which usually run at higher clock speeds than the reference model.

    To be honest, we don’t see GeForce GTX 980 successor to GeForce GTX 780 Ti in GeForce GTX 980, if you have already purchased a high-end video card of the previous generation, then it hardly makes sense to change it to a new one. You’ll get a small performance boost, albeit with better power efficiency. And the price difference between the current GeForce GTX 780 Ti and the new GeForce GTX 980 nullifies any talk of lower power consumption benefits. The GeForce GTX 980 graphics card, we think, will be more interesting for those users who have purchased the first models of the Kepler generation, such as the GeForce GTX 680, or are still using Fermi generation graphics cards.

    We also wanted to compare a GeForce GTX 980 with a GPU at 1.200 MHz with a GeForce GTX 780 Ti at the same GPU frequency of 1.200 MHz. In order for both video cards to stay at the set frequencies, we had to go for some tricks.

    GeForce GTX 780 Ti can bind Pstate2 to a fixed clock speed. Unfortunately, this method does not work with new «Maxwell» graphics cards. We had to choose such frequencies of the video card, so that under the load of GPU Boost, the frequency would always steadily increase to 1.200 MHz. It’s also important to remember that our reference GeForce GTX 980 has already run most loads at 1.151 MHz, so the difference isn’t that big. Sometimes the graphics card would hit higher Boost frequencies, so our 1.200 MHz GPU frequency would be even slower.

    So we had to slightly overclock the GeForce GTX 980 to 1200 MHz, and we had to overclock the GeForce GTX 780 Ti significantly over 200 MHz.

    Futuremark 3DMark

    Ice Storm

    NVIDIA GeForce GTX 980 @ 1. 200 MHz

    157616
    XX

    NVIDIA GeForce GTX 780 Ti @ 1200 MHz

    155211
    XX

    Futuremark points

    More is better

    Futuremark 3DMark

    Cloud Gate

    NVIDIA GeForce GTX 980 @ 1.200 MHz

    28464
    XX

    NVIDIA GeForce GTX 780 Ti @ 1200 MHz

    28297
    XX

    Futuremark points

    More is better

    Futuremark 3DMark

    Fire Strike

    NVIDIA GeForce GTX 780 Ti @ 1200 MHz

    11220
    XX

    NVIDIA GeForce GTX 980 @ 1.200 MHz

    10913
    XX

    Futuremark points

    More is better

    Futuremark 3DMark

    Fire Strike Extreme

    NVIDIA GeForce GTX 780 Ti @ 1200 MHz

    5583
    XX

    NVIDIA GeForce GTX 980 @ 1.200 MHz

    5491
    XX

    Futuremark points

    More is better

    Luxmark 2.0

    Sala

    NVIDIA GeForce GTX 980 @ 1.200 MHz

    2944
    XX

    NVIDIA GeForce GTX 780 Ti @ 1200 MHz

    2596
    XX

    Points

    More is better

    Compute Mark

    Fluid 2D

    NVIDIA GeForce GTX 780 Ti @ 1200 MHz

    702
    XX

    NVIDIA GeForce GTX 980 @ 1. 200 MHz

    530
    XX

    Points

    Bigger is better

    Compute Mark

    Fluid 3D

    NVIDIA GeForce GTX 780 Ti @ 1200 MHz

    796
    XX

    NVIDIA GeForce GTX 980 @ 1.200 MHz

    549
    XX

    Points

    More is better

    Compute Mark

    Mandel Skalar

    NVIDIA GeForce GTX 780 Ti @ 1200 MHz

    563
    XX

    NVIDIA GeForce GTX 980 @ 1.200 MHz

    460
    XX

    Points

    More is better

    Compute Mark

    Mandel Vector

    NVIDIA GeForce GTX 780 Ti @ 1200 MHz

    332
    XX

    NVIDIA GeForce GTX 980 @ 1.200 MHz

    302
    XX

    Points

    More is better

    Compute Mark

    Ray Tracing

    NVIDIA GeForce GTX 780 Ti @ 1200 MHz

    691
    XX

    NVIDIA GeForce GTX 980 @ 1.200 MHz

    573
    XX

    Points

    More is better

    In synthetic tests, the reference GeForce GTX 980 was often even faster than our model set to 1. 200 MHz. This is due to the higher Boost frequency of the reference card. Unlike the 3D tests, where we could use an extra run to warm up the graphics card, in 3DMark the start time of the test is too long, the graphics card has time to cool down, after which it starts at high Boost clock speeds.

    On the next page, we will present some gaming tests and other measurements.

    <>Test: Comparing GeForce GTX 980 and GeForce GTX 780 Ti at equal clock speeds
    Gaming tests, additional measurements

    from GTX 780 Ti to RTX 3090 (tests in new games) 9002 9002

    • Pro GeForce GTX 780 Ti
    • Pro GeForce GTX 980 Ti
    • Pro GeForce GTX 1080 Ti
    • Pro GeForce RTX 2080 Ti
    • Pro GeForce RTX 3090
    • Test configuration
    • Tests in games

    Hello, dear readers of Uspei.com. Do you remember Fall 2020? The Nvidia and AMD announcements then seemed like a bright spot in this terrible 2020. Humane price tags, a new level of performance. Dealers and shortages quickly dashed these hopes, taking with them new consoles. Who then would have thought that in 2021 it would get even worse?

    Another boom in mining and people, having smeared themselves with loans and sold kidneys with apartments, run to buy RTX 3090 for more than 4 thousand dollars, hoping to recoup the money invested in six months or a year. Everyone goes to the slaughter: from gaming laptops to old ladies RX 480, updated versions of which have risen in price by 5 times.

    All the madness that is happening now is a topic for a separate post. And today I would like to remember what we love video cards for — for beautiful frames in large quantities, and not for ether mega hashes. At the same time, let’s see what the top segment of past generations is capable of in modern games.

    To index ↑

    GeForce GTX 780 Ti pro

    The GeForce GTX 700 series was just a ten-year-old Kepler update, and the oldest video card in our comparison came out at the end of 2013, a year after the release of the first Titan. Nvidia decided that this was enough time to milk the enthusiasts dry and finally release a flagship for the people for $ 700.

    Only the released Playstation 4 and Xbox One made up the company then, and the game industry tried to sit on the old and new console chair. Therefore, from technological games, one can only recall Battlefield 4, the reboot of Tomb Raider and Metro Last Light.

    To contents ↑

    Pro GeForce GTX 980 Ti

    The next generation of Maxwell had to wait until the next Titan was cut in the spring of 2015: a slightly cut version could not boast of new nanometers, but the performance gap was up to 40% compared to the previous one Ti and twice the video buffer suited everyone.

    Zotac, like the rest of Nvidia’s partners, played to the fullest on this chip, turning a 250-watt card into a 350-watt one and breaking away from the reference frequencies by almost a third. Maxwell overclocked perfectly, and this card still serves me faithfully, if only it made less noise.

    In The Witcher 3, Batman Arkham Knight and Dying Light, the sliders could be turned all the way, and the Tomb Raider sequel willingly consumed the entire 6GB video buffer.

    To index ↑

    Pro GeForce GTX 1080 Ti

    review

    The 1080 Ti turned out to be so good, as well as the Pascal architecture in general, that nVidia decided to hold it until 2017, allowing smaller caliber cards to rule the roost in 2016. The 1080 Ti is perhaps the best thing that Nvidia has given mere mortals in recent years: this card is respected by everyone, even the most devoted AMD fans.

    Updated 16nm process technology, many architectural improvements, plenty of video memory and performance almost twice as high as the 980 Ti — this card needs no introduction and is still relevant today.

    Table of contents ↑

    Pro GeForce RTX 2080 Ti

    review

    Pascal’s success seems to have turned the green giant’s head, and the release of the next Turing architecture caused completely opposite emotions. The price tag has gone up to $1,200, which is way more than the performance boost we got. The main focus of the announcement was on support for ray tracing, but beautiful reflections and a handful of games with their support left a bad aftertaste in August 2018.

    The update of DLSS technology from soapy to normal version 2 helped to catch up, but the release of Super-variants and the 16th pastegen line once again reminded us that we had to wait for the next generation. The card itself has become a kind of status device for the rich: they did not take it in the hope of a huge breakthrough in performance, but in order to pull RT-beauty with a normal frame rate.

    Table of contents ↑

    Pro GeForce RTX 3090

    review

    The announcement of the new Ampere generation in September again fueled public interest in video cards: the promised increase compared to the previous generation was impressive, and the prices seemed quite reasonable.

    And all this caused a perfect storm: the demand for new pieces of hardware during the pandemic was so huge that it was almost impossible to get a new video card at the recommended price. Speculators, on the other hand, finished off a barely noticeable start of sales, and another mining boom went through Ampere like a skating rink.

    My opinion of the flagship 3090 hasn’t changed since last review: Nvidia has found a new way to milk the enthusiast stratum by just changing the name slightly and steadily jacking up the price for a still-cut GPU. All this did not at all scare away the fans who spent the night at the store at the start of sales, and even more so now, when buying a card for the price of a car in the hope of recouping it for

  • SSD Kingston KC600 512 GB
  • Power Seasonic Prime Ultra Platinum 1300W
  • be quiet! Pure Base 500DX
  • Tests in games

    Assassin’s Creed Valhalla

    And the first game on our list is Assassin’s Creed Valhalla. Wait, where’s the 780 Ti? Despite the fact that Kepler supports DirectX 12, Valhalla flatly refuses to run on the ’13 flagship. Support is different: Valhalla, judging by the published system requirements, provide at least a set of features of level 12_0, that is, starting with the 2nd generation of GCN from AMD and Maxwell from Nvidia.

    Full HD is not a hindrance for flagships, however, for the 980 Ti, you will need to twist the graphics settings sliders for a comfortable frame rate.

    Quad HD is already too much for the 980 Ti: regular jerks in this resolution are observed only in it, 1080 Ti is still doing its best.

    4K is the verdict of 980 Ti, and even 3090 cannot afford 60 FPS, but this is not surprising: the game loves video cards from red ones.

    Watch Dogs Legion

    Watch Dogs Legion minimum requirements start with GTX 970, but as it turned out, the 780 Ti works and manages to give out 15-20 frames. And this is at maximum settings, which require 8 gigabytes of video memory.

    1440p without rays, only the top three are tough, while outsiders give out slideshows. You can’t compete with such a video buffer. The

    4K knocked out the old 780 Ti from the legion, and the 3090, even without beams, can’t keep up with 60 fps.

    Far Cry New Dawn

    Far Cry New Dawn is based on Dunia Engine 2 from 2012, so it works without problems at maximum settings and on 780 Ti, but powerful Full HD graphics cards do not straighten their shoulders, so the difference between the leaders is so small .

    2K widens the gap between cards, but hits hard on the weak point of the 780 Ti — the amount of video memory.

    4K finishes it off completely, the friezes won’t let you play, unlike the same 980 Ti, which pulls out more than 30 frames without problems.

    Mafia Definitive Edition

    Little is known about the Mafia remaster engine, but it runs on DirectX 11 and works well: the 780 Ti feels fine, but for the 3090 Full HD again nothing.

    2K showcases the power of the 3090, but the underdogs are still holding their own, delivering a playable framerate.

    But 4K took the 780 Ti off the baton, because with FPS below 20 the speed of the game world becomes noticeably slower than normal, it’s impossible to play like that.

    Metro Exodus

    Metro Exodus on Ultra settings with tessellation, and even in DX12 mode, it’s hard for 780 Ti, but the game runs smoothly, other cards also have no problems in Full HD.

    1440p can handle even 980 Ti, not 60 FPS of course, but it’s quite possible to play at not the lowest settings.

    4K normally draws only a couple of fresh tops, and by the way, “Ultra” is not the maximum graphics preset yet.

    Red Dead Redemption 2

    I did not test in Red Dead Redemption 2 780 Ti, because 3 GB of video memory will not allow setting the maximum settings with which other cards are tested, and in Full HD they look cheerful, especially 980 Ti.

    Once again, Maxwell is impressive: console FPS at completely non-console settings and at 1440p — the old lady can still surprise.

    4K and stable 60 FPS can be afforded by happy owners of the RTX 3090. The rest will have to sacrifice graphics settings.

    Dirt 5

    The next game that Kepler doesn’t like is Dirt 5, it just won’t run on the 780 Ti. The 980 Ti, by the way, also shows a weak result compared to the 1080 Ti, which is exactly twice as fast.

    In 2K the results are similar, the 1080 Ti still holds the bar at 60 fps.

    There are no surprises in 4K. Please note that 3090 is exactly twice as fast as the 1080 Ti — this used to be the norm between generations, but now we have to wait for two.

    Horizon Zero Dawn

    Horizon Zero Dawn is VRAM hungry, but the 780 Ti holds its own and hits over 30 FPS in a not-so-graphically light game.

    It’s amazing how the 780 Ti manages to work at all in conditions of such a severe lack of memory, where even the successor cannot boast of a good frame rate.

    4K still finished it off: with the naked eye, you can see that a lot of textures are not displayed. 9The 80 Ti is holding on with all its might, despite the huge shortage of video memory.

    Godfall

    With Godfall, the situation is atypical: not only did the 780 Ti somehow start this game, but the 980 Ti suddenly performed unexpectedly well, or the 1080 Ti unexpectedly weaker than expected.

    In 2K, the 780 Ti puts on a slideshow, and the 980 Ti miraculously goes over 30 fps.

    4K was only managed by the RTX 3090. The fact that the 780 Ti made it past the splash screen is already a feat.

    Cyberpunk 2077

    Well, where without Cyberpunk 2077? The most demanding game in the test runs on the 780 Ti at ultra settings, but you can see the FPS for yourself. With these settings, you need at least a 1080 Ti.

    But for 1440p it won’t be enough either — only a couple of tops of the current and previous generation will fit here.

    4K puts the verdict on even the golden RTX 3090. And that’s even without turning on Ray Tracing.

    Rainbow 6 Siege

    And finally, something simpler. It came as no surprise to anyone that Rainbow 6 can handle all flagships, even the 780 Ti with the Vulkan API. For RTX 3090 need more load.

    In 2K everything is smooth even on Kepler, to say nothing of the rest.

    Well, in 4K, the 780 Ti is certainly capable of more, if not for the small amount of video memory of 3 gigabytes by modern standards.

    What can the GTX 780 Ti do at low and medium settings

    But what if we don’t torture it with max settings and see what it can do at low or medium settings? Let’s see.

    Well, it’s quite playable for those who don’t go crazy with graphics settings sliders and who can’t compete with miners’ wallets now.

    How long the old tops will last is unknown, but we can say that in the light of recent events and the situation on the market, we all had to moderate our appetites, reconsider our attitude to video cards, the gaming industry and not only.

    It can take a long time to expect a collapse of cryptocurrencies, and will they collapse enough to make mining unprofitable? Wait and see. And we are not in a hurry to throw the pastegen in the trash. He will still serve us. Take care of yourself and everyone!

    source

    The video memory array is equipped with chips from ELPIDA, which have rarely come across over the past year. Marking W2032BBBG-60-F indicates a nominal effective frequency of 6 GHz.

    ASUS ROG Poseidon GTX 780 Platinum Front View

    ASUS ROG Poseidon GTX 780 Platinum Rear View

    NVIDIA GeForce GTX 780 Front View

    NVIDIA GeForce GTX 780 Rear View

    The board has pads for monitoring and modifying voltages on the GPU, video memory and PLL, accessible through a cutout in the plate that covers the back surface. But for some reason, the purpose of the contacts is not signed, and the areas that should be closed with solder for the volt modes to start working are hidden under the plate.

    How useful are water-cooled graphics cards?

    The question is: does water cooling for the GPU improve the performance of the CPU itself? The cooling system for the video card has proven its effectiveness, as it significantly affects the performance of the PC. We have put together a list of benefits that a water-cooled graphics card offers:

    • Reduced power consumption
    • Creates less noise
    • Withstands more heat
    • Allows overclocking to much higher frequencies

    Thus, we decided to create a list of the best liquid-cooled video cards. Fortunately, there are many models available on the market.

    Radeon RX Vega 64 Liquid Cooled

    Frequency: 1406 MHz | Memory capacity: 8 GB | Memory frequency: 945 MHz | Bus interface: PCI Express 3.0 | DirectX: DirectX 12 | OpenGL: 4.5 | Outputs: 3 x DisplayPort, HDMI

    Looking for a graphics card that’s not just for gaming? The liquid-cooled Radeon RX Vega 64 is one of the best on the market. This is a Radeon RX Vega series GPU built on AMD’s Vega GPU architecture.

    The model is an excellent choice for everyone, whether it’s high-end gaming or video or photo editing. This video card is powered by 4096 CUDA processors, which are built on the basis of the 14nm FinFET process technology.

    The processor features 8 GB of HBM2 video memory, low power consumption and is even faster than the GDDR5X memory used in Pascal-based graphics cards. This feature is very useful for VR.

    In terms of water cooling functions, the video card has a closed liquid system. Its feature is a highly reliable compact pump, which is used to circulate water in a closed circuit. This is a circuit that offers excellent solutions to the challenges of high GPU thermal loads, low thermal resistance, and maintaining low noise while managing high heat fluxes.

    The frequency here is 1408 MHz and can be overclocked up to 1668 MHz. In addition, the processor supports DirectX 12.0, and playing the latest AAA game in 4K resolution is not a problem.

    Note: The RX Veg 64 requires a high capacity power supply as the graphics card consumes up to 1000W of power.

    ⇡#Design

    The video card is made in the catchy style of the ROG series and is most similar to another ASUS video card with the same GPU, but purely air-cooled — the GeForce GTX 780 DirectCU II. Only tubes for installing fittings, closed with stoppers, give out the presence of an integrated water block.

    ASUS ROG Poseidon GTX 780 Platinum

    NVIDIA GeForce GTX 780

    Without a CBO connection, a pair of 90 mm fans performs the cooling function. The back surface of the printed circuit board is covered with a decorative metal plate. The presence of current in the auxiliary power connectors is signaled by the LEDs located next to them. The ROG logo on the end also glows.

    ASUS ROG Poseidon GTX 780 Platinum

    NVIDIA GeForce GTX 780

    The fan frame is not needed when using water cooling. It is a pity that it is not so easy to remove it without removing the heatsink from the board, although it is still possible if you pry off the fixing teeth with a thin screwdriver.

    ASUS ROG Poseidon GTX 780 Platinum

    NVIDIA GeForce GTX 780

    The radiator does not look like a water block at all. As it turned out, the internal structure is also different. Perhaps, the video card would take up three slots if ASUS simply hoisted an air radiator on top of a standard thickness water block. Instead, a more complex solution is used. At the heart of the cooler there is an evaporation chamber, which compensates for the short length of the simple U-shaped channel.

    ASUS ROG Poseidon GTX 780 Platinum

    NVIDIA GeForce GTX 780

    In addition to the vapor chamber, there are also heat pipes connecting the base to the fin assembly. It is noteworthy that the aluminum base of the heatsink covers the MOSFETs of the power system, as well as GDDR5 chips, which will not hurt when overclocking video memory.

    For connection to the water block, the tubing of the water block has a standard ¼ inch thread, and the fittings can be any. They are not supplied as a set.

    Keep in mind that dropsy hoses add a lot to the width of the video card, even if L fittings are used.

    Gigabyte GeForce GTX 1080 8GB Xtreme Gaming WATERFORCE

    CUDA cores: 2560 | Frequency: 1784 MHz | Memory capacity: 8 GB | Memory frequency: 10.4 GHz | Bus interface: PCI Express 3.0 x16 | DirectX: DirectX 12 | OpenGL: 4.5 | Outputs: 3 x DisplayPort, 3 x HDMI, DVI The fluid flow in this graphics card quickly removes heat from the large copper plate that is in direct contact with the GPU, VRAM and VRM chips and effectively reduces the heat generated.

    This graphics card from Gigabyte provides the highest performance, most advanced gaming technology, and provides users with the best gaming ecosystem. In addition, the device is highly energy efficient.

    There’s also the opportunity to have an incredible next-generation VR experience with Xtreme VR Link, as the graphics card offers revolutionary 360-degree imaging even in VR environments.

    In terms of chassis features, the graphics card has several lighting effects that can be selected using the XTREME Engine utility.

    The rear panel features a black metal plate to reinforce the structure, and for compact protection, the card is covered with Aerospace-Grade PCB, which makes it dust-proof, moisture-proof and corrosion-resistant.

    EVGA GeForce GTX 1080 FTW HYBRID

    CUDA Cores: 2560 | Clock frequency: 1721 MHz | Memory capacity: 8 GB | Memory frequency: 10 GHz | Bus interface: PCI Express 3.0 x16 | DirectX: DirectX 12 | OpenGL: 4.5 | Outputs: 3 x DisplayPort, DVI, HDMI

    If you’re looking for a very advanced graphics card for gaming, the EVGA GeForce GTX 1080 FTW HYBRID is the way to go. This innovative GPU is based on Nvidia’s Pascal architecture. The device is made using the latest and ultra-fast FinFET and is very energy efficient.

    Speaking of performance, 8GB GDDR5X video memory delivers the latest in gaming technology, next-generation virtual reality, and industry-leading performance. The video card supports resolutions up to 7680 × 4320 and demonstrates simultaneous output to 4 monitors. The base frequency here is 1721 MHz with the possibility of overclocking to 1860 MHz.

    Thanks to the liquid cooling function, this incredible graphics card has a great ability to withstand heat and greatly reduces the operating temperature of the GPU. The temperature here is about 40°C cooler than in the standard GeForce GTX 1080. The processor is equipped with a 120mm radiator and fan, which significantly reduces heat. The graphics card has a dedicated 10 cm cooling fan board to cool the VRAM and VRM.

    But that’s not all! The GTX 1080 FTW supports the latest Microsoft DirectX 12 API for fantastic performance in the latest games. You will get smooth gameplay when playing in 4K resolution! The graphics card offers a customizable RGB LED that can be customized using the EVGA Precision XOC overclocking software.

    The maximum power consumption of the card is 215W. An 8-pin power connector is required.

    Testing

    Test bench:
    — Intel Core i5-8600K processor
    — Corsair Vengeance LPX DDR4-2800 RAM
    — ASUS ROG Maximus X Apex motherboard
    — Corsair AX1200i power supply.

    Testing of the video card is divided into two parts, first the video card was tested at nominal frequencies, then the same tests were run at higher frequencies. The GPU was overclocked from 1595 MHz (1709 MHz Boost) to 1645 MHz (1759 MHz Boost), GDDR5X memory overclocked from 1376 MHz to 1445 MHz. When there is no load, the graphics card drops the GPU frequency to 139 MHz, and the memory slows down to 101 MHz.

    The test results are shown in the graphs below. The games were set to maximum settings and a resolution of 1920×1080 pixels.
    Testing in benchmarks.

    Testing ASUS ROG Poseidon GeForce GTX 1080 Ti Platinum in games.

    Testing the ASUS ROG Poseidon GeForce GTX 1080 Ti Platinum cooling system.

    Rated frequencies, fan operation mode — Auto.

    Rated frequencies, fan operation mode — 85% of maximum speed.

    ⇡#Board

    The Poseidon is based on almost the same PCB as in the Strix GTX 1080 Ti. However, a set of image output interfaces (two DisplayPort and HDMI each plus a single Dual-Link DVI-D) and a power system that includes ten phases for the GPU and two for memory chips (as well as a PLL phase) under the control of the uPI Semiconductor uP9 PWM controller511P. A protection board slot on the back of the board gives access to Hotwire pads, which can be used to measure and adjust GPU, RAM and PLL supply voltages (using a multimeter and trimmers or the UEFI menu on top ASUS motherboards). However, without modifying the board, only measurement is possible. For volt modding and removing the power limit, you need to remove several resistors and close the desired contact.

    Micron memory chips marked 7CA77 D9VRL are rated at an effective frequency of 11 GHz. One of the sites is empty (because part of the memory controllers is deactivated in the GP102 chip for gaming video cards), as is the place for an additional microcircuit and a BIOS switch.

    ARCTIC Accelero Xtreme IV High-End Graphics Card Cooler

    This is a high-end graphics card cooler that is even larger than the Accelero Twin Turbo III. Comes with an extra long radiator and three 92mm fans for excellent cooling performance.

    ARCTIC Accelero Xtreme IV has a cooling capacity of 300W, making it a great choice for high-end and advanced graphics cards. For example, such as Nvidia Titan X or GTX 1080. The design of the radiator consists of aluminum fins and several copper tubes. And a direct copper contact with the GPU.

    Installation is quite simple and does not require any adhesive. It also provides a backplate cooler or heatsink to cool the VRAM and VRM. The performance of this graphics card cooler is top notch. And you can expect temperatures to drop to 25 to 30 degrees Celsius compared to stock cooling.

    It comes with MX-4 thermal compound which is perfect for you and you need to buy more thermal paste. This cooler is designed for top graphics cards and is compatible with the latest high performance graphics cards. Including Nvidia GeForce GTX 1060/1070/1080 and AMD Radeon RX 480.

    Note: The Accelero Xtreme IV is only compatible with graphics cards using a standard size 98mm PCB.

    Compatible ARCTIC Accelero Xtreme IV

    Nvidia GeForce:

    Titan X (Pascal) GTX 1080, 1070, 1060, Titan X, 980 (Ti), 970, Titan (black), 780 (Ti), 770, 760, 750 (Ti), 680, 670, 660 (Ti), 650 Ti (upgrade), 580, 570, 560 (Ti, SE), 550 Ti, 480, 460 (SE), GTS 450, 250, 240 (OEM ), GT 740, 9800 (GTX+, GTX, GT), 9600 (GT, GSO 512, GSO), 9500 GT (non-LP), 8800 Ultra (G80), 8800 GTX (G80), 8800 GTS (G80), 8800 GTS 512 (G92), 8800 GTS (G92), 8800 GT , 8800 GS (9600GSO), 7900 GTX, 7800 (GTX 512, GTX, GT).

    AMD Radeon:

    RX 480, RX 470, R9 390(X), 380(X), 370X, 290(X), 285, 280(X), 270(X), R7 370, 265, HD 8870 , 7970 (GHz), 7950 (boost), 7870 (XT, GHz), 7850, 6970, 6950, 6870, 6850, 6790, 5870, 5850, 5830 , 4890, 4870, 4850, 4830, 3870, 3850. 9004 Specifications ARCTIC Accelero Xtreme IV

    • Cooling capacity 300 W
    • Number of fans 3 x 92 mm
    • Cooling efficiency — Very good
    • Features — Reasonably quiet fans, memory cooling and VRM

    Cooling system

    Despite the apparent differences, the installed CO is essentially the same DirectCU II with a modified casing. Here it is much more massive and decorated more stylishly.

    The radiator is held on by 4 spring-loaded screws and is easy to remove. Of the minuses, one can note the lack of cooling on the memory chips, a massive heatsink does not contact them in any way.

    Two 5-pin plugs are used to power the fans and illuminated panel. The top panel is made of durable plastic.

    To remove the cover, unscrew 2 screws and slide it forward, despite its massiveness it is very light. The aluminum heatsink along with the heat pipes is painted black.

    In this case, 96 mm fans are installed and, despite the external difference, both are marked as First FD9015U12S. CoolTech Fan Technology, mentioned at the very beginning, is based on a modified impeller of one of the fans and allows you to get rid of dust more efficiently.

    Heat pipe direct contact technology is used to dissipate heat from the graphics chip. The thicker tube has a diameter of 10 mm, the two closest to the center are 8 mm each and two more thinner ones are 6 mm each. Considering the initial impression, we can conclude that the two outermost tubes are practically not in contact with the chip, which negatively affects the overall efficiency of the CO.

    In addition, a separate heatsink for the power subsystem is installed through the heat-conducting rubber.

    Another element of the cooling system is a perforated metal plate for heat dissipation. Together with an auxiliary bar, this plate sets a stiffening rib and the board does not bend when installed in the case.

    ⇡#Board

    The PCB of the original design most closely resembles the PCB of the aforementioned ASUS GeForce GTX 780 DirectCU II, although there are some differences. In general, the board looks impressive. The power system includes 11 phases in an 8 + 2 + 1 scheme (GPU, RAM and PLL, respectively). The voltage on the GPU is controlled by the Digi+ ASP1212 VRM controller.

    The video memory array is equipped with chips from ELPIDA, which have rarely come across over the past year. Marking W2032BBBG-60-F indicates a nominal effective frequency of 6 GHz.

    ASUS ROG Poseidon GTX 780 Platinum Front View

    ASUS ROG Poseidon GTX 780 Platinum Rear View

    NVIDIA GeForce GTX 780 Front View

    NVIDIA GeForce GTX 780 Rear View

    The board has pads for monitoring and modifying voltages on the GPU, video memory and PLL, accessible through a cutout in the plate that covers the back surface. But for some reason, the purpose of the contacts is not signed, and the areas that should be closed with solder for the volt modes to start working are hidden under the plate.

    ⇡#Design

    Although Poseidon differs from the ASUS ROG Strix GeForce GTX 1080 Ti that we tested last time, it is the possibility of water cooling, which is fundamentally more efficient than air, this did not help to make the video card smaller. Like Strix, Poseidon has 298mm long and the cooling system case protrudes beyond the two expansion slots.

    With the Strix series, the device combines a set of auxiliary functions. There is a backlight (the color of the user’s choice), which in this case is located in the protective plate hole on the back of the board and a large transparent window with an optical effect of an infinite mirror. If you have a motherboard with an Aura Sync connector, you can connect it to your graphics card with an additional cable for backlight synchronization. The other two headers on the Poseidon board are for case fan control.

    The heatsink is the same massive design as the ROG Strix GTX 1080 Ti, but completely different design. The heat from the GPU die to the heat sink fins in Poseidon is transferred by the evaporation chamber, and there are only two heat pipes. The radiator fins are blown by two 95mm fans, the mechanism of which is protected from dust according to the IP-5X standard.

    Poseidon’s water cooling circuit is very simple — a U-shaped channel molded to the surface of the evaporator chamber. The fittings are mounted on a standard ¼ inch thread. The holes are located perpendicular to the plane of the board, in contrast to the previous «Poseidons», in which they were parallel to the PCB. The protrusion of the water block allows you to bring the tubes in the case both from the top and bottom of the video card or from both sides to separate the fluid flow to the GPU and the CPU.

    The Poseidon GTX 1080 Ti is easier to disassemble than the Strix because there is no separate frame for cooling the memory chips and VRM transistors. All metal elements of the cooling system are assembled into a single unit.

    Game Testing

    The FPS of the GTX 780 in modern games remains quite decent even at maximum settings. The reason for this is the use in its manufacture of top-end components for 2013 that meet the requirements of 2016-2018.

    The manufacturer offers to use the video card together with the appropriate software for it — first of all, drivers, as well as the GeForce Experience service. The program allows you to make the most of the resources available to the user, as can be seen in the example of the game Tomb Raider.

    At the maximum resolution of the GTX 780 model, it is enough to render a picture with an FPS of 76 frames per second, at medium and minimum settings, the figure rises to 150-200. An overclocked card allows you to get even more impressive performance.

    Checking the video card in other games with an Intel Core i7 processor and 8 GB of RAM (Windows 7, NVIDIA GeForce 320.18 driver) showed the following results: FPS when set to maximum resolution and more than 100 for medium.

  • In the newer stealth action game Hitman: Absolution, at the best settings, the video card allows you to get more than a decent value of 42-48.5 FPS.
  • For the third part of the BioShock Infinite shooter released in 2013, 84-93 FPS is provided.
  • In the graphics-demanding game project Crysis 3, you can get about 40-42 FPS. This is less than the latest generation video adapters provide, but about the same as when choosing a TITAN model.
  • The maximum settings of the role-playing shooter Metro: Last Light provide 39-43 FPS.
  • When running The Witcher 3: Wild Hunt, you can get at least 30 frames per second. But already when using more powerful processors and 16 GB of RAM, the parameter rises to 40-46.
  • In Alan Wake’s 2012 psychological thriller, the GTX 780 delivers up to 30fps when you select a 2K picture, more than enough for a normal game.
  • Assasin Creed III, a multi-platform action adventure, starts at 44 FPS at 2K and goes over 100 at lower resolutions. In an even more modern game from the same series, Assasin Origins, 27 frames / s are issued — however, only on FullHD.
  • The card provides a fairly comfortable gameplay in both role-playing games like Fallout 4 and adventure games like Sherlock Holmes: The Devil’s Daughter. Here the user can set almost any settings.

    Another modern game, Kingdom Come: Deliverance, which was released in 2018 and forced many users to upgrade or upgrade their computers, runs normally with the GTX 780 at medium and minimum settings.

    Comparison of the performance of the video adapter in various games shows that even without overclocking, its capabilities are enough for the purposes of most gamers. Therefore, it is not worth making a decision about buying a new model with the already existing GTX 780. To improve performance by at least 1.5 times, a PC user will have to spend at least $400-$450 to buy an Nvidia GTX 1070 Ti.

    Gamers building a relatively inexpensive gaming system should pay attention to used GTX 780 variants (new ones disappeared from sale back in 2016), which cost only $150

    ⇡#Conclusions

    Poseidon makes an ambiguous impression. From an engineering point of view, this is certainly an unusual device. The combination of air and liquid cooling did not affect the efficiency of the cooler in both dry and wet modes. If we forget about the water block built into the radiator, then Poseidon differs little from the ASUS GeForce GTX 780 DirectCU II or another similar video card with a GK110 processor: efficient cooling, high-quality PCB, good overclocking potential. In addition, in the Platinum modification, this is the video card with the highest GPU frequencies in the ASUS line based on the GTX 780. But buying Poseidon without a water cooling system is absolutely pointless — it is too expensive.

    In the presence of good dropsy, the temperature on the GPU is kept within 40°C. The evaporation chamber at the base of the radiator really successfully replaces the traditional all-metal water block with a winding channel (which, by the way, is also expensive). The video card has all the data for a truly serious overclocking. There is one “but”: the available power limit of 110% limits attempts to achieve higher frequencies by raising the voltage on the GPU. You can try your luck with a non-standard BIOS, but since the video card has a regular water block, the BIOS should also provide a larger range for modifications. And yet, ASUS Poseidon deserved the Overclocker’s Choice medal. Flashing the BIOS will not scare a real overclocker. 9Fury XRadeon R9 FuryRadeon R9 NanoRadeon R9 390XRadeon R9 390Radeon R9 380XRadeon R9 380Radeon R7 370Radeon R7 360Radeon R9 295X2Radeon R9 290XRadeon R9 290Radeon R9 280XRadeon R9 285Radeon R9 280Radeon R9 270XRadeon R9 270Radeon R7 265Radeon R7 260XRadeon R7 260Radeon R7 250Radeon R7 240Radeon HD 7970Radeon HD 7950Radeon HD 7870 XTRadeon HD 7870Radeon HD 7850Radeon HD 7790Radeon HD 7770Radeon HD 7750Radeon HD 6990Radeon HD 6970Radeon HD 6950Radeon HD 6930Radeon HD 6870Radeon HD 6850Radeon HD 6790Radeon HD 6770Radeon HD 6750Radeon HD 6670 GDDR5Radeon HD 6670 GDDR3Radeon HD 6570 GDDR5Radeon HD 6570 GDDR3Radeon HD 6450 GDDR5Radeon HD 6450 GDDR3Radeon HD 5570 GDDR5Radeon HD 3750Radeon HD 3730Radeon HD 5970Radeon HD 5870Radeon HD 5850Radeon HD 5830Radeon HD 5770Radeon HD 5750Radeon HD 5670Radeon HD 5570Radeon HD 5550Radeon HD 5450Radeon HD 4890Radeon HD 4870 X2Radeon HD 4870Radeon HD 4860Radeon HD 4850 X2Radeon HD 4850Radeon HD 4830Radeon HD 4790Radeon HD 4770Radeon HD 4730Radeon HD 4670Radeon HD 4650Radeon HD 4550Radeon HD 4350Radeon HD 4350Radeon HD 43500 (IGP 890GX) Radeon HD 4200 (IGP)Radeon HD 3870 X2Radeon HD 3870Radeon HD 3850Radeon HD 3690Radeon HD 3650Radeon HD 3470Radeon HD 3450Radeon HD 3300 (IGP)Radeon HD 3200 (IGP)Radeon HD 3100 (IGP)Radeon HD 2900 XT 1Gb GDDR4Radeon HD 2900 XTRadeon HD 2900 PRORadeon HD 2900 GTRadeon HD 2600 XT DUALRadeon HD 2600 XT GDDR4Radeon HD 2600 XTRadeon HD 2600 PRORadeon HD 2400 XTRadeon HD 2400 PRORadeon HD 2350Radeon X1950 CrossFire EditionRadeon X1950 XTXRadeon X1950 XTRadeon X1950 PRO DUALRadeon X1950 PRORadeon X1950 GTRadeon X1900 CrossFire EditionRadeon X1900 XTXRadeon X1900 XTRadeon X1900 GT Rev2Radeon X1900 GTRadeon X1800 CrossFire EditionRadeon X1800 XT PE 512MBRadeon X1800 XTRadeon X1800 XLRadeon X1800 GTORadeon X1650 XTRadeon X1650 GTRadeon X1650 XL DDR3Radeon X1650 XL DDR2Radeon X1650 PRO on RV530XTRadeon X1650 PRO on RV535XTRadeon X1650Radeon X1600 XTRadeon X1600 PRORadeon X1550 PRORadeon X1550Radeon X1550 LERadeon X1300 XT on RV530ProRadeon X1300 XT on RV535ProRadeon X1300 CERadeon X1300 ProRadeon X1300Radeon X1300 LERadeon X1300 HMRadeon X1050Radeon X850 XT Platinum EditionRadeon X850 XT CrossFire EditionRadeon X850 XT Radeon X850 Pro Radeon X800 XT Platinum EditionRadeon X800 XTRadeon X800 CrossFire EditionRadeon X800 XLRadeon X800 GTO 256MBRadeon X800 GTO 128MBRadeon X800 GTO2 256MBRadeon X800Radeon X800 ProRadeon X800 GT 256MBRadeon X800 GT 128MBRadeon X800 SERadeon X700 XTRadeon X700 ProRadeon X700Radeon X600 XTRadeon X600 ProRadeon X550 XTRadeon X550Radeon X300 SE 128MB HM-256MBR adeon X300 SE 32MB HM-128MBRadeon X300Radeon X300 SERadeon 9800 XTRadeon 9800 PRO /DDR IIRadeon 9800 PRO /DDRRadeon 9800Radeon 9800 SE-256 bitRadeon 9800 SE-128 bitRadeon 9700 PRORadeon 9700Radeon 9600 XTRadeon 9600 PRORadeon 9600Radeon 9600 SERadeon 9600 TXRadeon 9550 XTRadeon 9550Radeon 9550 SERadeon 9500 PRORadeon 9500 /128 MBRadeon 9500 /64 MBRadeon 9250Radeon 9200 PRORadeon 9200Radeon 9200 SERadeon 9000 PRORadeon 9000Radeon 9000 XTRadeon 8500 LE / 9100Radeon 8500Radeon 7500Radeon 7200 Radeon LE Radeon DDR OEM Radeon DDR Radeon SDR Radeon VE / 7000Rage 128 GL Rage 128 VR Rage 128 PRO AFRRage 128 PRORage 1283D Rage ProNVIDIAGeForce RTX 4090GeForce RTX 4080 16GBGeForce RTX 4080 12GBGeForce RTX 3090 TiGeForce RTX 3090GeForce RTX 3080 TiGeForce RTX 3080 12GBGeForce RTX 3080GeForce RTX 3070 TiGeForce RTX 3070GeForce RTX 3060 TiGeForce RTX 3060 rev. 2GeForce RTX 3060GeForce RTX 3050GeForce RTX 2080 TiGeForce RTX 2080 SuperGeForce RTX 2080GeForce RTX 2070 SuperGeForce RTX 2070GeForce RTX 2060 SuperGeForce RTX 2060GeForce GTX 1660 TiGeForce GTX 1660 SuperGeForce GTX 1660GeForce GTX 1650 SuperGeForce GTX 1650 GDDR6GeForce GTX 1650 rev.3GeForce GTX 1650 rev.2GeForce GTX 1650GeForce GTX 1630GeForce GTX 1080 TiGeForce GTX 1080GeForce GTX 1070 TiGeForce GTX 1070GeForce GTX 1060GeForce GTX 1060 3GBGeForce GTX 1050 TiGeForce GTX 1050 3GBGeForce GTX 1050GeForce GT 1030GeForce GTX Titan XGeForce GTX 980 TiGeForce GTX 980GeForce GTX 970GeForce GTX 960GeForce GTX 950GeForce GTX TitanGeForce GTX 780 TiGeForce GTX 780GeForce GTX 770GeForce GTX 760GeForce GTX 750 TiGeForce GTX 750GeForce GT 740GeForce GT 730GeForce GTX 690GeForce GTX 680GeForce GTX 670GeForce GTX 660 TiGeForce GTX 660GeForce GTX 650 Ti BoostGeForce GTX 650 TiGeForce GTX 650GeForce GT 640 rev.2GeForce GT 640GeForce GT 630 rev.2GeForce GT 630GeForce GTX 590GeForce GTX 580GeForce GTX 570GeForce GTX 560 TiGeForce GTX 560GeForce GTX 550 TiGeForce GT 520GeForce GTX 480GeForce GTX 470GeForce GTX 465GeForce GTX 460 SEGeForce GTX 460 1024MBGeForce GTX 460 768MBGeForce GTS 450GeForce GT 440 GDDR5GeForce GT 440 GDDR3GeForce GT 430GeForce GT 420GeForce GTX 295GeForce GTX 285GeForce GTX 280GeForce GTX 275GeForce GTX 260 rev. 2GeForce GTX 260GeForce GTS 250GeForce GTS 240GeForce GT 240GeForce GT 230GeForce GT 220GeForce 210Geforce 205GeForce GTS 150GeForce GT 130GeForce GT 120GeForce G100GeForce 9800 GTX+GeForce 9800 GTXGeForce 9800 GTSGeForce 9800 GTGeForce 9800 GX2GeForce 9600 GTGeForce 9600 GSO (G94)GeForce 9600 GSOGeForce 9500 GTGeForce 9500 GSGeForce 9400 GTGeForce 9400GeForce 9300GeForce 8800 ULTRAGeForce 8800 GTXGeForce 8800 GTS Rev2GeForce 8800 GTSGeForce 8800 GTGeForce 8800 GS 768MBGeForce 8800 GS 384MBGeForce 8600 GTSGeForce 8600 GTGeForce 8600 GSGeForce 8500 GT DDR3GeForce 8500 GT DDR2GeForce 8400 GSGeForce 8300GeForce 8200GeForce 8100GeForce 7950 GX2GeForce 7950 GTGeForce 7900 GTXGeForce 7900 GTOGeForce 7900 GTGeForce 7900 GSGeForce 7800 GTX 512MBGeForce 7800 GTXGeForce 7800 GTGeForce 7800 GS AGPGeForce 7800 GSGeForce 7600 GT Rev.2GeForce 7600 GTGeForce 7600 GS 256MBGeForce 7600 GS 512MBGeForce 7300 GT Ver2GeForce 7300 GTGeForce 7300 GSGeForce 7300 LEGeForce 7300 SEGeForce 7200 GSGeForce 7100 GS TC 128 (512)GeForce 6800 Ultra 512MBGeForce 6800 UltraGeForce 6800 GT 256MBGeForce 6800 GT 128MBGeForce 6800 GTOGeForce 6800 256MB PCI-EGeForce 6800 128MB PCI-EGeForce 6800 LE PCI-EGeForce 6800 256MB AGPGeForce 6800 128MB AGPGeForce 6800 LE AGPGeForce 6800 GS AGPGeForce 6800 GS PCI-EGeForce 6800 XTGeForce 6600 GT PCI-EGeForce 6600 GT AGPGeForce 6600 DDR2GeForce 6600 PCI-EGeForce 6600 AGPGeForce 6600 LEGeForce 6200 NV43VGeForce 6200GeForce 6200 NV43AGeForce 6500GeForce 6200 TC 64(256)GeForce 6200 TC 32(128)GeForce 6200 TC 16(128)GeForce PCX5950GeForce PCX 5900GeForce PCX 5750GeForce PCX 5550GeForce PCX 5300GeForce PCX 4300GeForce FX 5950 UltraGeForce FX 5900 UltraGeForce FX 5900GeForce FX 5900 ZTGeForce FX 5900 XTGeForce FX 5800 UltraGeForce FX 5800GeForce FX 5700 Ultra /DDR-3GeForce FX 5700 Ultra /DDR-2GeForce FX 5700GeForce FX 5700 LEGeForce FX 5600 Ultra (rev. 2)GeForce FX 5600 Ultra (rev.1)GeForce FX 5600 XTGeForce FX 5600GeForce FX 5500GeForce FX 5200 UltraGeForce FX 5200GeForce FX 5200 SEGeForce 4 Ti 4800GeForce 4 Ti 4800-SEGeForce 4 Ti 4200-8xGeForce 4 Ti 4600GeForce 4 Ti 4400GeForce 4 Ti 4200GeForce 4 MX 4000GeForce 4 MX 440-8x / 480GeForce 4 MX 460GeForce 4 MX 440GeForce 4 MX 440-SEGeForce 4 MX 420GeForce 3 Ti500GeForce 3 Ti200GeForce 3GeForce 2 Ti VXGeForce 2 TitaniumGeForce 2 UltraGeForce 2 PROGeForce 2 GTSGeForce 2 MX 400GeForce 2 MX 200GeForce 2 MXGeForce 256 DDRGeForce 256Riva TNT 2 UltraRiva TNT 2 PRORiva TNT 2Riva TNT 2 M64Riva TNT 2 Vanta LTRiva TNT 2 VantaRiva TNTRiva 128 ZXRiva 128 9Fury XRadeon R9 FuryRadeon R9 NanoRadeon R9 390XRadeon R9 390Radeon R9 380XRadeon R9 380Radeon R7 370Radeon R7 360Radeon R9 295X2Radeon R9 290XRadeon R9 290Radeon R9 280XRadeon R9 285Radeon R9 280Radeon R9 270XRadeon R9 270Radeon R7 265Radeon R7 260XRadeon R7 260Radeon R7 250Radeon R7 240Radeon HD 7970Radeon HD 7950Radeon HD 7870 XTRadeon HD 7870Radeon HD 7850Radeon HD 7790Radeon HD 7770Radeon HD 7750Radeon HD 6990Radeon HD 6970Radeon HD 6950Radeon HD 6930Radeon HD 6870Radeon HD 6850Radeon HD 6790Radeon HD 6770Radeon HD 6750Radeon HD 6670 GDDR5Radeon HD 6670 GDDR3Radeon HD 6570 GDDR5Radeon HD 6570 GDDR3Radeon HD 6450 GDDR5Radeon HD 6450 GDDR3Radeon HD 5570 GDDR5Radeon HD 3750Radeon HD 3730Radeon HD 5970Radeon HD 5870Radeon HD 5850Radeon HD 5830Radeon HD 5770Radeon HD 5750Radeon HD 5670Radeon HD 5570Radeon HD 5550Radeon HD 5450Radeon HD 4890Radeon HD 4870 X2Radeon HD 4870Radeon HD 4860Radeon HD 4850 X2Radeon HD 4850Radeon HD 4830Radeon HD 4790Radeon HD 4770Radeon HD 4730Radeon HD 4670Radeon HD 4650Radeon HD 4550Radeon HD 4350Radeon HD 4350Radeon HD 43500 (IGP 890GX) Radeon HD 4200 (IGP)Radeon HD 3870 X2Radeon HD 3870Radeon HD 3850Radeon HD 3690Radeon HD 3650Radeon HD 3470Radeon HD 3450Radeon HD 3300 (IGP)Radeon HD 3200 (IGP)Radeon HD 3100 (IGP)Radeon HD 2900 XT 1Gb GDDR4Radeon HD 2900 XTRadeon HD 2900 PRORadeon HD 2900 GTRadeon HD 2600 XT DUALRadeon HD 2600 XT GDDR4Radeon HD 2600 XTRadeon HD 2600 PRORadeon HD 2400 XTRadeon HD 2400 PRORadeon HD 2350Radeon X1950 CrossFire EditionRadeon X1950 XTXRadeon X1950 XTRadeon X1950 PRO DUALRadeon X1950 PRORadeon X1950 GTRadeon X1900 CrossFire EditionRadeon X1900 XTXRadeon X1900 XTRadeon X1900 GT Rev2Radeon X1900 GTRadeon X1800 CrossFire EditionRadeon X1800 XT PE 512MBRadeon X1800 XTRadeon X1800 XLRadeon X1800 GTORadeon X1650 XTRadeon X1650 GTRadeon X1650 XL DDR3Radeon X1650 XL DDR2Radeon X1650 PRO on RV530XTRadeon X1650 PRO on RV535XTRadeon X1650Radeon X1600 XTRadeon X1600 PRORadeon X1550 PRORadeon X1550Radeon X1550 LERadeon X1300 XT on RV530ProRadeon X1300 XT on RV535ProRadeon X1300 CERadeon X1300 ProRadeon X1300Radeon X1300 LERadeon X1300 HMRadeon X1050Radeon X850 XT Platinum EditionRadeon X850 XT CrossFire EditionRadeon X850 XT Radeon X850 Pro Radeon X800 XT Platinum EditionRadeon X800 XTRadeon X800 CrossFire EditionRadeon X800 XLRadeon X800 GTO 256MBRadeon X800 GTO 128MBRadeon X800 GTO2 256MBRadeon X800Radeon X800 ProRadeon X800 GT 256MBRadeon X800 GT 128MBRadeon X800 SERadeon X700 XTRadeon X700 ProRadeon X700Radeon X600 XTRadeon X600 ProRadeon X550 XTRadeon X550Radeon X300 SE 128MB HM-256MBR adeon X300 SE 32MB HM-128MBRadeon X300Radeon X300 SERadeon 9800 XTRadeon 9800 PRO /DDR IIRadeon 9800 PRO /DDRRadeon 9800Radeon 9800 SE-256 bitRadeon 9800 SE-128 bitRadeon 9700 PRORadeon 9700Radeon 9600 XTRadeon 9600 PRORadeon 9600Radeon 9600 SERadeon 9600 TXRadeon 9550 XTRadeon 9550Radeon 9550 SERadeon 9500 PRORadeon 9500 /128 MBRadeon 9500 /64 MBRadeon 9250Radeon 9200 PRORadeon 9200Radeon 9200 SERadeon 9000 PRORadeon 9000Radeon 9000 XTRadeon 8500 LE / 9100Radeon 8500Radeon 7500Radeon 7200 Radeon LE Radeon DDR OEM Radeon DDR Radeon SDR Radeon VE / 7000Rage 128 GL Rage 128 VR Rage 128 PRO AFRRage 128 PRORage 1283D Rage ProNVIDIAGeForce RTX 4090GeForce RTX 4080 16GBGeForce RTX 4080 12GBGeForce RTX 3090 TiGeForce RTX 3090GeForce RTX 3080 TiGeForce RTX 3080 12GBGeForce RTX 3080GeForce RTX 3070 TiGeForce RTX 3070GeForce RTX 3060 TiGeForce RTX 3060 rev. 2GeForce RTX 3060GeForce RTX 3050GeForce RTX 2080 TiGeForce RTX 2080 SuperGeForce RTX 2080GeForce RTX 2070 SuperGeForce RTX 2070GeForce RTX 2060 SuperGeForce RTX 2060GeForce GTX 1660 TiGeForce GTX 1660 SuperGeForce GTX 1660GeForce GTX 1650 SuperGeForce GTX 1650 GDDR6GeForce GTX 1650 rev.3GeForce GTX 1650 rev.2GeForce GTX 1650GeForce GTX 1630GeForce GTX 1080 TiGeForce GTX 1080GeForce GTX 1070 TiGeForce GTX 1070GeForce GTX 1060GeForce GTX 1060 3GBGeForce GTX 1050 TiGeForce GTX 1050 3GBGeForce GTX 1050GeForce GT 1030GeForce GTX Titan XGeForce GTX 980 TiGeForce GTX 980GeForce GTX 970GeForce GTX 960GeForce GTX 950GeForce GTX TitanGeForce GTX 780 TiGeForce GTX 780GeForce GTX 770GeForce GTX 760GeForce GTX 750 TiGeForce GTX 750GeForce GT 740GeForce GT 730GeForce GTX 690GeForce GTX 680GeForce GTX 670GeForce GTX 660 TiGeForce GTX 660GeForce GTX 650 Ti BoostGeForce GTX 650 TiGeForce GTX 650GeForce GT 640 rev.2GeForce GT 640GeForce GT 630 rev.2GeForce GT 630GeForce GTX 590GeForce GTX 580GeForce GTX 570GeForce GTX 560 TiGeForce GTX 560GeForce GTX 550 TiGeForce GT 520GeForce GTX 480GeForce GTX 470GeForce GTX 465GeForce GTX 460 SEGeForce GTX 460 1024MBGeForce GTX 460 768MBGeForce GTS 450GeForce GT 440 GDDR5GeForce GT 440 GDDR3GeForce GT 430GeForce GT 420GeForce GTX 295GeForce GTX 285GeForce GTX 280GeForce GTX 275GeForce GTX 260 rev. 2GeForce GTX 260GeForce GTS 250GeForce GTS 240GeForce GT 240GeForce GT 230GeForce GT 220GeForce 210Geforce 205GeForce GTS 150GeForce GT 130GeForce GT 120GeForce G100GeForce 9800 GTX+GeForce 9800 GTXGeForce 9800 GTSGeForce 9800 GTGeForce 9800 GX2GeForce 9600 GTGeForce 9600 GSO (G94)GeForce 9600 GSOGeForce 9500 GTGeForce 9500 GSGeForce 9400 GTGeForce 9400GeForce 9300GeForce 8800 ULTRAGeForce 8800 GTXGeForce 8800 GTS Rev2GeForce 8800 GTSGeForce 8800 GTGeForce 8800 GS 768MBGeForce 8800 GS 384MBGeForce 8600 GTSGeForce 8600 GTGeForce 8600 GSGeForce 8500 GT DDR3GeForce 8500 GT DDR2GeForce 8400 GSGeForce 8300GeForce 8200GeForce 8100GeForce 7950 GX2GeForce 7950 GTGeForce 7900 GTXGeForce 7900 GTOGeForce 7900 GTGeForce 7900 GSGeForce 7800 GTX 512MBGeForce 7800 GTXGeForce 7800 GTGeForce 7800 GS AGPGeForce 7800 GSGeForce 7600 GT Rev.2GeForce 7600 GTGeForce 7600 GS 256MBGeForce 7600 GS 512MBGeForce 7300 GT Ver2GeForce 7300 GTGeForce 7300 GSGeForce 7300 LEGeForce 7300 SEGeForce 7200 GSGeForce 7100 GS TC 128 (512)GeForce 6800 Ultra 512MBGeForce 6800 UltraGeForce 6800 GT 256MBGeForce 6800 GT 128MBGeForce 6800 GTOGeForce 6800 256MB PCI-EGeForce 6800 128MB PCI-EGeForce 6800 LE PCI-EGeForce 6800 256MB AGPGeForce 6800 128MB AGPGeForce 6800 LE AGPGeForce 6800 GS AGPGeForce 6800 GS PCI-EGeForce 6800 XTGeForce 6600 GT PCI-EGeForce 6600 GT AGPGeForce 6600 DDR2GeForce 6600 PCI-EGeForce 6600 AGPGeForce 6600 LEGeForce 6200 NV43VGeForce 6200GeForce 6200 NV43AGeForce 6500GeForce 6200 TC 64(256)GeForce 6200 TC 32(128)GeForce 6200 TC 16(128)GeForce PCX5950GeForce PCX 5900GeForce PCX 5750GeForce PCX 5550GeForce PCX 5300GeForce PCX 4300GeForce FX 5950 UltraGeForce FX 5900 UltraGeForce FX 5900GeForce FX 5900 ZTGeForce FX 5900 XTGeForce FX 5800 UltraGeForce FX 5800GeForce FX 5700 Ultra /DDR-3GeForce FX 5700 Ultra /DDR-2GeForce FX 5700GeForce FX 5700 LEGeForce FX 5600 Ultra (rev. 2)GeForce FX 5600 Ultra (rev.1)GeForce FX 5600 XTGeForce FX 5600GeForce FX 5500GeForce FX 5200 UltraGeForce FX 5200GeForce FX 5200 SEGeForce 4 Ti 4800GeForce 4 Ti 4800-SEGeForce 4 Ti 4200-8xGeForce 4 Ti 4600GeForce 4 Ti 4400GeForce 4 Ti 4200GeForce 4 MX 4000GeForce 4 MX 440-8x / 480GeForce 4 MX 460GeForce 4 MX 440GeForce 4 MX 440-SEGeForce 4 MX 420GeForce 3 Ti500GeForce 3 Ti200GeForce 3GeForce 2 Ti VXGeForce 2 TitaniumGeForce 2 UltraGeForce 2 PROGeForce 2 GTSGeForce 2 MX 400GeForce 2 MX 200GeForce 2 MXGeForce 256 DDRGeForce 256Riva TNT 2 UltraRiva TNT 2 PRORiva TNT 2Riva TNT 2 M64Riva TNT 2 Vanta LTRiva TNT 2 VantaRiva TNTRiva 128 ZXRiva 128

    You can simultaneously select
    up to 10 video cards by holding Ctrl

    Reviews of video cards NVIDIA GeForce GTX 780 Ti:

    • MSI GTX 780Ti Gaming 3G video card review and testing

      MSI GTX 780Ti Gaming 3G

    • Review and testing of the ASUS ROG Matrix GTX 780 Ti Platinum graphics card

      ASUS MATRIX-GTX780TI-P-3GD5

    • Review and testing of the video card ASUS GTX780TI-DC2OC-3GD5

      ASUS GTX780TI-DC2OC-3GD5

    • Ice power. Review and testing of Inno3D iChill GeForce GTX 780 Ti HerculeZ X3 Ultra

      Inno3D iChill GeForce GTX 780 Ti HerculeZ X3 Ultra

    • Heavyweights. Performance comparison of Radeon R9 290X and GeForce GTX 780 Ti in 23 benchmark applications

      NVIDIA GeForce GTX 780 Ti

    GeForce GTX 980 vs Quadro RTX 4000 Max-Q

    GeForce GTX 980 vs Quadro RTX 4000 Max-Q — Th200

    Contents

    1. Introduction
    2. Features
    3. Tests
    4. Key differences
    5. Conclusion
    6. Comments

    Video card

    Video card

    Introduction

    We compared two graphics cards: NVIDIA GeForce GTX 980 vs NVIDIA Quadro RTX 4000 Max-Q. On this page, you will learn about the key differences between them, as well as which one is the best in terms of features and performance.

    The NVIDIA GeForce GTX 980 is a Maxwell 2.0 based GeForce 900 generation graphics card released Sep 19th, 2014. It comes with 4GB GDDR5 memory running at 1753MHz, has a 2x 6-pin power connector and consumes up to 165W.

    NVIDIA Quadro RTX 4000 Max-Q is a Quadro Mobile Generation (Tx000) integrated graphics card based on Turing architecture released May 27th, 2019.

    NVIDIA Quadro RTX 4000 Max-Q

    Release Date

    Sep 19th, 2014

    May 27th, 2019

    Bus Interface

    PCIe 3.0 x16

    PCIe 3 004 2048

    2560

    Texture Units

    128

    160

    Raster Units

    64

    64

    SM Count

    40

    Tensor Cores

    320

    RT Cores

    40

    Graphics Features

    Directx

    12 (12_1)

    12 Ultimate (12_2)

    Opengl

    4.6

    4.6

    OpenCl

    3.0

    3.0

    9000 CUDA

    9000 9000 9000 9000 9000 9000

    004 5.

    2

    7.5

    Vulkan

    1.1

    1.2

    Board Design

    Heating

    165W

    80W

    2x 6-0003 9000

    IGP

    Benchmarks

    3DMark Graphics

    3DMark is a benchmarking tool designed and developed by UL to measure the performance of computer hardware. Upon completion, the program gives a score, where a higher value indicates better performance.

    NVIDIA GeForce GTX 980

    NVIDIA Quadro RTX 4000 Max-Q

    Blender bmw27

    Blender is the most popular 3D content creation software. It has its own test, which is widely used to determine the rendering speed of processors and video cards. We chose the bmw27 scene. The result of the test is the time taken to render the given scene.

    NVIDIA GeForce GTX 980

    NVIDIA Quadro RTX 4000 Max-Q
    +280%

    Th200 RP

    Th200 RP is a test created by Th200. It measures the raw power of the components and gives a score, with a higher value indicating better performance.

    NVIDIA GeForce GTX 980

    NVIDIA Quadro RTX 4000 Max-Q
    +38%

    Key Differences

    Why is NVIDIA Quadro RTX 4000 Max-Q better than NVIDIA GeForce GTX 980?

    Newer — Released 4 years later

    Has 38% more performance

    Consumes 52% less power — 80W vs 165W

    More modern manufacturing process — 12nm vs 28nm

    Has 4GB more memory

    More advanced memory type — GDDR6 vs GDDR5

    Has 86% higher bandwidth — 416.0 GB/s vs 224.4 GB/s

    Has 14% higher pixel fill rate — 88.32 GPixel/s vs 77.82 GPixel/s

    Has 42% higher texture fill rate — 220.8 GTexel/s vs 155.6 GTexel/s

    Has more texture units +32

    Has 512 more shading units

    or GeForce GTX 980?

    The Quadro RTX 4000 Max-Q delivers 38% better performance, consumes up to 52% less energy and holds 4 GB more memory. Quadro RTX 4000 Max-Q 3990X is more powerful than GeForce GTX 9 according to our research80.