Power, Temperature, & Noise — AMD’s Radeon HD 6870 & 6850: Renewing Competition in the Mid-Range Market
by Ryan Smithon October 21, 2010 10:08 PM EST
- Posted in
- GPUs
- AMD
- Radeon
- 6870
197 Comments
|
197 Comments
IndexBarts: The Next Evolution of CypressSeeing the Future: DisplayPort 1.2Seeing the Present: HDMI 1.4a, UVD3, and Display CorrectionHigh IQ: AMD Fixes Texture Filtering and Adds Morphological AAWhat’s In a Name?NVIDIA’s 6870 Competitor & The TestCrysis: WarheadBattleForgeStarcraft IIMetro 2033HAWXCivilization VBattlefield: Bad Company 2STALKER: Call of PripyatDIRT 2Mass Effect 2WolfensteinCompute & TessellationPower, Temperature, & NoiseFinal Words
Last but not least in our look at AMD’s new Radeon 6800 series is our look at power consumption, GPU temperatures, and the amount of noise generated. With efficiency being one of the major design goals for Barts, AMD stands to gain a lot of ground here compared to the 5800 series for only a minor drop in performance.
Looking quickly at the voltages of the 6800 series, we have 4 samples – 2 each of the 6870, and 2 each of the 6850. Both of our 6870 cards have an idle voltage of 0.945v and a load voltage of 1.172v, and seeing as how they’re both based on AMD’s reference design this is what we would expect for a design that is based around a single VID.
However our 6850 results, which include a non-reference card in the form of XFX’s customized 6850, are much more interesting. While our reference 6850 has a load voltage of 1.094v, our XFX card reports a load voltage of 1.148v. We’ll be taking a look at the XFX 6850 in-depth next week in our 6850 roundup, but for now this leaves us with the question of whether AMD is using variable VIDs, or if XFX is purposely setting theirs higher for overclocking purposes.
Radeon HD 6800 Series Load Voltage |
|||||
Ref 6870 |
XFX 6870 |
Ref 6850 |
XFX 6850 |
||
1. ![]() |
1.172v |
1.094v |
1.148v |
Finally our EVGA GTX 460 1GB FTW card has a VID of 0.975v, which compared to all the other GTX 460 cards we’ve tested thus far makes it quite notable. This is lower than any of those other cards by 0.012v, a property we believe is necessary to sell such a heavily overclocked card without causing a similarly large rise in power/heat/noise. It’s also for this reason that we question whether NVIDIA could actually supply suitable GF104 GPUs in high volumes, as GPUs capable of running at this voltage are likely coming from the cream of the crop for NVIDIA.
For our tests, please note that we do not have a pair of reference 6850s. For our second 6850 we are using XFX’s customized 6850 card, which means our results will undoubtedly differ from what a pair of true reference cards would do. However as the 6850 reference design will not be widely available this is less important than it sounds.
As always we start our look at power/temp/noise with our look at idle power. Because we use a 1200W PSU in our GPU test rig our PSU efficiency at idle is quite low, leading to the suppression of the actual difference between cards. But even with this kind of suppression it’s still possible to pick out what cards have a lower idle power draw, as the best cards will still result in a total system power draw that’s at least a couple of watts lower.
AMD’s official specs call for the 6800 series to have a lower idle power draw than the 5800 series, and while we can’t account for all 8 watts we do manage to shave a couple of watts off compared to our 5800 series cards. The Crossfire results are even more impressive, with the 6870CF drawing 11W less than the 5870CF.
Compared to the 6800 series the GeForce GTX 460 768MB does manage to hang on to top honor here for a single card by a watt, however in SLI our 1GB cards do worse than our 6800 series cards by 10W.
Looking at load power consumption it’s clear from the start that AMD’s efficiency gains are going to pay off here. On the latest iteration of our power consumption chart the 6850 underconsumes even the already conservative 5850 by 20W under Crysis and 25W under FurMark, showcasing how AMD was able to reduce their power consumption by a significant amount while giving up much less in the way of performance.
Compared to the 6800 series NVIDIA does notably worse here, with all of the GTX 460 cards pulling down more power than the 6870 and the GTX 470 being in a league of its own. While NVIDIA was competitive with Cypress on power, they’re not in a position to match Barts. They can deliver Barts-like performance (and then some), but they have to consume more power to do it.
Up next is our look at GPU temperatures, starting with idle temps. As we mentioned in our GTX 460 review, NVIDIA ended up producing a very effective reference cooler for the GTX 460, utilizing an open-air design that by dissipating air inside and outside of the case is capable of reaching temperatures fully exhausting coolers can’t match. As a result all of the GTX 460 cards top our charts here.
Prior to the GTX 460 series this is a metric the 5850 always did well in, so we had expected a similar performance from the 6850, only to leave disappointed. What we’re ultimately looking at is a matter of the quality of the cooler: the 6850 may consume less power than the 5850 at idle, but it packs a weaker cooler overall, allowing it to approach these temperatures. For a gaming card such as the 6800 series idle temperatures are almost entirely superficial once we get below 50C, but even so this tells us something about the 6850 reference cooler.
Thanks to the GTX 460’s open-air cooler, all of our GTX 460 cards top our temperature chart even with their higher power consumption. The trade-off is that all of these cards require a well-ventilated case, while the Radeon 5800 and 6800 series will tolerate much poorer cases so long as there’s enough ventilation for the card to pull in air in the first place.
As was the case with idle temperatures, the reference 6850 ends up doing worse than the 5850 here thanks to its less effective cooler; however the 6870 ends up doing better than both the 6850 and 5870 due to its more effective cooler and its lower power consumption compared to the 5870. While these cards can’t quite touch the GTX 460 series, we’re still looking at some of the coolest cards among our current benchmark suite.
Meanwhile our XFX 6850 ends up doing the best out of all of our cards here, however this will come at a cost of more noise. We’ll touch on this more next week in our 6850 roundup.
Last but not least is idle noise, which isn’t much of a story with modern cards. With the exception of the GTX 470/480, the latest GeForce and Radeon cards are both capable of running up against the noise floor of our testing environment.
Under load we once again see an NVIDIA GTX 460 card top the chart thanks to its open-air design. This is followed very closely however by the Radeon 6850, which at 47.7dB is our third-quietest card and finally showing off the advantages of the tradeoffs AMD made with the reference cooler. The 6850 may not be as cool as the 5850, but it’s quite a bit quieter. As for the XFX card, this is where XFX has to pay the piper, as their 6850 card ends up being as loud as a 5870 in exchange for their lower temperatures.
Meanwhile the 6870 ends up being quite a bit louder than both the GTX 460 series and the 6850, coming in at 55.2dB. This is a definite leg-up compared to the 5870 and nicely cements the fact that the 6870 is intended to be the 5850’s replacement, but it means the GTX 460 series spoils the results here. Once custom-design vendor cards come out for the 6870, I suspect we’re going to see someone quickly sell a 6870 with a less aggressive cooler, which for the costs of higher temperatures would afford less noise.
Compute & Tessellation
Final Words
IndexBarts: The Next Evolution of CypressSeeing the Future: DisplayPort 1. 2Seeing the Present: HDMI 1.4a, UVD3, and Display CorrectionHigh IQ: AMD Fixes Texture Filtering and Adds Morphological AAWhat’s In a Name?NVIDIA’s 6870 Competitor & The TestCrysis: WarheadBattleForgeStarcraft IIMetro 2033HAWXCivilization VBattlefield: Bad Company 2STALKER: Call of PripyatDIRT 2Mass Effect 2WolfensteinCompute & TessellationPower, Temperature, & NoiseFinal Words
PRINT THIS ARTICLE
HD6870 on a 300W PSU? | Page 3
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
I’m planning to build a mini-ITX PC in a SG05/SG06 but I’m not sure if the 300W is enough for my configuration
http://www.silverstonetek.com/product.php?pid=210&area=en
Setup:
Asus P8H67-I mini-ITX
core i5 2500K
Corsair XMS 8GB Dual Channel DDR3 1333
OCZ Vertex 3 90GB
I want to use a Sapphire HD6870 1GB but if the PSU cannot supply the amount of power it requires I will to put in a HD6850.
Since it’s a H67 chipset I’m not going to overclock the CPU. I’m not installing a DVD drive nor any other components besides the 120mm fan.
www.extreme.outervision.com/PSUEngine generates a Minimum PSU Wattage of 249W and a recommended PSU Wattage of 299W
Can u guys advise me if this configuration is going to work on the default 300W PSU? Or do I need the 450W version? The thing is that the 450W PSU isn’t any good:
http://www.overclock.net/t/889834/silverstone-st45sf-total-crap
http://www.silverstonetek.com/product.php?pid=276&area=en
Cheers!
See less
See more
Reply
Save
Like
41 — 56 of 56 Posts
Quote:
Originally Posted by Unoriginal Sin
That’s a vary poor calculator and also some very poor advice.. if you don’t know don’t post.. you’re not helping.
Click to expand…
Quote:
Originally Posted by pioneerisloud
So much wrong it hurts. Commercial PSU calculators usually over estimate power usage by a LOT.
![]()
Use this one:
http://www.overclock.net/t/1140534/psu-calc-final-release
According to our own PSU Guru’s here at OCN, his proposed build will require 375w, assuming an overclock (which H67 won’t do), and assuming full system loads will ever be used. With that taken into effect, a good 300w will be enough, if everything is kept at stock.Click to expand…
Quote:
Originally Posted by Unoriginal Sin
That’s a vary poor calculator and also some very poor advice.. if you don’t know don’t post.. you’re not helping.
Click to expand…
Apparently PSU Guru’s on OCN is «Trash» as well.
For the record, the PSU calculator I used came up as 376 watts.
Go for it, buy a PSU that meets the bare minimum requirements! I promise you wont regret it?
Go google 6870
Sorry for posting a link to a PSU calculator that came up 1 watt higher than the one on here.
… friend or customer, I would NEVER throw the bare minimal power supply at someone. I’m entitled to my own opinion, you want to tell people they are wrong, go to page 1 and quote them all.
From guru: «Radeon HD 6870 — On your average system the card requires you to have a 500 Watt power supply unit.»
Lets use his advice since mine was completely smashed and laughed at.
I STILL think this is a 400 minimum / 450 watt system.
See less
See more
Reply
Save
Like
heaviest i pulled on my inwin commander 750 w is 286 watts, and that includes EVERYTHING except monitors. ie — except monitors in my sig, everything including cpu and gpu pulled 286 watts tops under load.
(zalman fan controller i have has a live digital power meter, and it displays instantaneous power draw on a small led screen on the case)
Reply
Save
Like
Quote:
Originally Posted by unity100
heaviest i pulled on my inwin commander 750 w is 286 watts, and that includes EVERYTHING except monitors. ie — except monitors in my sig, everything including cpu and gpu pulled 286 watts tops under load.
![]()
(zalman fan controller i have has a live digital power meter, and it displays instantaneous power draw on a small led screen on the case)
Click to expand…
And you’ve got a MUCH more power hungry CPU, assuming overclocked even, and a HD6950 which draws a LOT more than a 6870.
Reply
Save
Like
I dont understand why all the fuss. This should already be solved. A 300Watt PSU is bare minimum, and probably wont last for a long amount of time. It IS the bare minimum because of PSU efficiency. You wont get all the 300 watts into the system. Plus, max efficiency is usually found at around 82% load. 300/.8 = 375. Shoot for a 400 watt PSU and know that your in the clear.
Reply
Save
Like
Quote:
Originally Posted by pioneerisloud
And you’ve got a MUCH more power hungry CPU, assuming overclocked even, and a HD6950 which draws a LOT more than a 6870.
Click to expand…
i didnt do any overclocks until this point. currently the meter shows 142 watts. no power management is active.
so i think anyone with a single card (not one that sucks power too much) would be well off for a while with a 550 watts psu.
Reply
Save
Like
Quote:
Originally Posted by HexATL
From guru: «Radeon HD 6870 — On your average system the card requires you to have a 500 Watt power supply unit.»
Lets use his advice since mine was completely smashed and laughed at.
I STILL think this is a 400 minimum / 450 watt system.Click to expand…
This is not a yoga camp you know?
Either way, if Phaedrus said that he’s wrong.. maybe he meant 2x 6870s.. otherwise 500W for one 6870 is simply unneeded, even on a heavily overclocked Gulftown or Nehalem you won’t be pulling nowhere near 500W with a single 6870
See less
See more
2
Reply
Save
Like
Quote:
Originally Posted by Unoriginal Sin
This is not a yoga camp you know?
Either way, if Phaedrus said that he’s wrong.
. maybe he meant 2x 6870s.. otherwise 500W for one 6870 is simply unneeded, even on a heavily overclocked Gulftown or Nehalem you won’t be pulling nowhere near 500W with a single 6870
Click to expand…
300 watt system = buy 400 watt power supply
Reply
Save
Like
Quote:
Originally Posted by MacNcheese
I dont understand why all the fuss. This should already be solved. A 300Watt PSU is bare minimum, and probably wont last for a long amount of time. It IS the bare minimum because of PSU efficiency. You wont get all the 300 watts into the system. Plus, max efficiency is usually found at around 82% load. 300/.8 = 375. Shoot for a 400 watt PSU and know that your in the clear.
Click to expand…
Efficiency comes into the power being drawn from the WALL. So yes, if its 82% efficient, the unit will draw 375 from the wall, but it’ll still put out 300w to the components.
The PSU in question has 264w continuous 12v rating. It’ll handle his build fine. Doing any normal loading (gaming and such), he’ll never pass 260w with that setup, ever. He’ll more than likely be seeing around 175-200w at most power draw from the unit doing even the MOST HEAVY of gaming.
Reply
Save
Like
Quote:
Originally Posted by HexATL
300 watt system = buy 400 watt power supply
Click to expand…
Are we talking about the same thing!?… this is not «recommend me a PSU».. if it was I would agree with you.. he asked if his 300W PSU would suffice, and it does.. it’s as simple as that.
Reply
Save
Like
I recently asked Phaedrus about the same power supply for a stock 9800gt and 2500k.
As you can see here and here
a 6870’s max power usage is at around 163watts, which is about 40 more watts than the 9800gt.
http://tpucdn.com/reviews/Axle/GeForce_GT_240/images/power_maximum.gif
http://tpucdn.com/reviews/HIS/Radeon_HD_6870/images/power_maximum. gif
What I got from that is the FSP unit will power the system you listed but it will use most of the rated power.
So if you use it for gaming or as a htpc, its just enough, but if you plan on having it on 24/7, then you should look at the 450w unit.
See less
See more
Reply
Save
Like
Quote:
Originally Posted by NFSxperts
I recently asked Phaedrus about the same power supply for a stock 9800gt and 2500k.
As you can see here and herea 6870’s max power usage is at around 163watts, which is about 40 more watts than the 9800gt.
http://tpucdn.com/reviews/Axle/GeForce_GT_240/images/power_maximum.gif
http://tpucdn.com/reviews/HIS/Radeon_HD_6870/images/power_maximum.gifWhat I got from that is the FSP unit will power the system you listed but it will use most of the rated power.
So if you use it for gaming or as a htpc, its just enough, but if you plan on having it on 24/7, then you should look at the 450w unit.![]()
Click to expand…
You’re comparing a GT240, but you said 9800GT. 9800GT draws a good bit more power than a GT240.
Reply
Save
Like
If you look at the chart, the 9800gt is 5 places down at 124watts
http://tpucdn.com/reviews/Axle/GeForce_GT_240/images/power_maximum.gif
See less
See more
1
Reply
Save
Like
Quote:
Originally Posted by NFSxperts
I recently asked Phaedrus about the same power supply for a stock 9800gt and 2500k.
As you can see here and here
a 6870’s max power usage is at around 163watts, which is about 40 more watts than the 9800gt.
http://tpucdn.com/reviews/Axle/GeForce_GT_240/images/power_maximum.gif
http://tpucdn.com/reviews/HIS/Radeon_HD_6870/images/power_maximum.gif
What I got from that is the FSP unit will power the system you listed but it will use most of the rated power.
So if you use it for gaming or as a htpc, its just enough, but if you plan on having it on 24/7, then you should look at the 450w unit.![]()
Click to expand…
If we were talking about a dedicated folding/mining rig then that would be correct.. you don’t want to run a value PSU @ 100% load 24/7 because that will degrade the capacitors pretty fast, however that isn’t the case here… and really, if you manage to keep the PSU cool(open platform, low ambient temp), then you have nothing to worry about even if you keep it at very high loads for extended periods of time
See less
See more
1
Reply
Save
Like
Running a graphics card with two 6-pin connectors on a 300 watt PSU is a bad idea. A 300W PSU like that is for computers with onboard video or a low powered graphics card without 6-pin connectors. You have to account for the wattage of the motherboard and everything else too.
I have an i5 750, 5770, 2 ram dimms, and 3 hard drives powered by a 400W Corsair CX400 PSU. It would not boot if I overclock the CPU to 3.8GHz. Put in a higher capacity PSU and it boots fine. I would lean towards 450W to 500W for a 6870.
Reply
Save
Like
Quote:
Originally Posted by pioneerisloud
The 300w PSU will handle your build JUST FINE. The PSU in question can handle 264w on the 12v rail. That 6870 probably draws right around 100w or so at most. Your CPU will draw at MOST 95w. That leaves around 60-70w or more to power the rest of the system. That’s MORE than enough. Its a good quality 300w, 80+ Silverstone unit. It’s not like a junk Logisys or CoolMax.
Click to expand…
See less
See more
1
Reply
Save
Like
Quote:
Originally Posted by Riou
Running a graphics card with two 6-pin connectors on a 300 watt PSU is a bad idea. A 300W PSU like that is for computers with onboard video or a low powered graphics card without 6-pin connectors. You have to account for the wattage of the motherboard and everything else too.
I have an i5 750, 5770, 2 ram dimms, and 3 hard drives powered by a 400W Corsair CX400 PSU.It would not boot if I overclock the CPU to 3.8GHz. Put in a higher capacity PSU and it boots fine. I would lean towards 450W to 500W for a 6870.
Click to expand…
The reason for your system not booting lies somewhere else.. the CX400 is a solid unit, that system should’t draw more than ~250W at full load.. nowhere near the limits of the PSU in question
See less
See more
1
Reply
Save
Like
41 — 56 of 56 Posts
- This is an older thread, you may not receive a response, and could
be reviving an old thread. Please consider creating a new thread.
Top
AMD Radeon HD 6870 — 51 secret facts, review, specifications, reviews.
Top specifications and features
- Passmark score
- 3DMark Fire Strike Score
- 3DMark Fire Strike Graphics test score
- 3DMark Vantage Performance test score
- 3DMark Cloud Gate GPU benchmark score
Passmark
AMD Radeon HD 6870 test score:
2174
Best score:
30117
Performance
AMD Radeon HD 6870:
1589
Best score:
Memory
AMD Radeon HD 6870:
387
Best score:
General Information
AMD Radeon HD 6870:
1556
Best score:
Features
AMD Radeon HD 6870:
88
Best score:
Description
AMD Radeon HD 6870 graphics card based on TeraScale 2 architecture has 1700M transistors, tech. 40 nm process. The frequency of the graphics core is 900 MHz. In terms of memory, 1 GB is installed here. DDR5, clocked at 1050 MHz and with a maximum throughput of 134.4 Gb/s. The texture size is 50.4 GTexels/s. FLOPS is 2.1.
In tests, the AMD Radeon HD 6870 video card showed itself as follows — according to the Passmark benchmark, the model scored 2174 points. At the same time, the maximum number of points for today is 260261 points. According to the 3DMark benchmark, the video card scored 3090 points out of 49575 possible.
Directx version — 11.
In terms of compatibility, the video card is connected via the PCIe 2.0 x16 interface. In terms of cooling, the heat dissipation requirements here are 151 watts.
In our tests, the video card scores 656436 points.
Why AMD Radeon HD 6870 is better than others
No merits
- Passmark score 2174 . This parameter is lower than 65% of products
- 3DMark Fire Strike Score 2954 . This parameter is lower than 49% of products
- 3DMark Fire Strike Graphics 3090 test score.
This parameter is lower than 57% of products
- 3DMark Vantage Performance test score 17488 . This parameter is lower than 42% of products
- 3DMark Cloud Gate GPU test score 26012 . This parameter is lower than 47% of products
- 3DMark 11 Performance GPU Score 4151 . This parameter is lower than 50% of products
- GPU base clock frequency 900 MHz. This parameter is lower than that of 67% of goods
- RAM 1 GB. This parameter is lower than that of 79% of goods
Review AMD Radeon HD 6870
Performance
Memory
general information
Functions
Ports
Tests in benchmarks
AMD Radeon HD 6870 Review Highlights
GPU base clock
The graphics processing unit (GPU) has a high clock speed.
900MHz
max 2457
Average: 1124.9MHz
2457MHz
GPU memory frequency
This is an important aspect calculating memory bandwidth
1050MHz
max 16000
Average: 1468 MHz
16000MHz
FLOPS
A measure of the processing power of a processor is called FLOPS.
2.1TFLOPS
max 1142.32
Average: 53 TFLOPS
1142.32 TFLOPS
RAM
Graphics card RAM (also known as video memory or VRAM) is a special type of memory used by a graphics card to store graphics data. It serves as a temporary buffer for textures, shaders, geometry, and other graphics resources that are needed to display images on the screen. More RAM allows the graphics card to work with more data and handle more complex graphic scenes with high resolution and detail.
Show all
1GB
max 128
Average: 4.6 GB
128GB
Number of PCIe lanes
The number of PCIe lanes in graphics cards determines the speed and bandwidth of data transfer between the graphics card and other computer components through the PCIe interface. The more PCIe lanes a video card has, the more bandwidth and ability to communicate with other computer components.
Show all
16
Mean value:
Pixel rendering speed
The higher the pixel rendering speed, the smoother and more realistic the graphics and the movement of objects on the screen will be.
Show all
29 GTexel/s
max 563
Average: 94.3Gtexel/s
563 GTexel/s
TMUs
Responsible for texturing objects in 3D graphics. TMU provides textures to the surfaces of objects, which gives them a realistic look and detail. The number of TMUs in a video card determines its ability to process textures. The more TMUs, the more textures can be processed at the same time, which contributes to better texturing of objects and increases the realism of graphics.
Show all
56
max 880
Average: 140.1
880
ROPs
Responsible for the final processing of pixels and their display on the screen. ROPs perform various operations on pixels, such as blending colors, applying transparency, and writing to the framebuffer. The number of ROPs in a video card affects its ability to process and display graphics. The more ROPs, the more pixels and image fragments can be processed and displayed on the screen at the same time. A higher number of ROPs generally results in faster and more efficient graphics rendering and better performance in games and graphics applications.
Show all
32
max 256
Average: 56.8
256
Number of shading blocks
The number of shader blocks in video cards refers to the number of parallel processors that perform computational operations in the GPU. The more shader units in the video card, the more computing resources are available for processing graphics tasks.
Show all
1120
max 17408
Mean value:
17408
Processor cores
The number of processor cores in a video card indicates the number of independent computing units capable of performing tasks in parallel. More cores allow for more efficient load balancing and processing of more graphics data, leading to improved performance and rendering quality.
Show all
14
max 220
Mean value:
220
L2 cache size
Used to temporarily store data and instructions used by the graphics card when performing graphics calculations. A larger L2 cache allows the graphics card to store more data and instructions, which helps speed up the processing of graphics operations.
Show all
512
Mean value:
Texture size
A certain number of textured pixels are displayed on the screen every second.
Show all
50.4 GTexels/s
max 756.8
Average: 145.4 GTexels/s
756.8 GTexels/s
Architecture name
TeraScale 2
GPU Name
Barts
Memory bandwidth
This is the rate at which the device stores or reads information.
134.4GB/s
max 2656
Average: 257.8 GB/s
2656GB/s
Effective memory speed
The effective memory clock speed is calculated from the size and information transfer rate of the memory. The performance of the device in applications depends on the clock frequency. The higher it is, the better.
Show all
4200 MHz
max 19500
Average: 6984.5 MHz
19500MHz
RAM
Graphics card RAM (also known as video memory or VRAM) is a special type of memory used by a graphics card to store graphics data. It serves as a temporary buffer for textures, shaders, geometry, and other graphics resources that are needed to display images on the screen. More RAM allows the graphics card to work with more data and handle more complex graphic scenes with high resolution and detail.
Show all
1GB
max 128
Average: 4.6 GB
128GB
GDDR Memory Versions
Latest GDDR memory versions provide high data transfer rates for improved overall performance
Show all
5
Mean: 4.9
6
Memory bus width
A wide memory bus indicates that it can transfer more information in one cycle. This property affects the performance of the memory as well as the overall performance of the device’s graphics card.
Show all
256bit
max 8192
Average: 283.9bit
8192bit
Die size
The physical dimensions of the chip that houses the transistors, microcircuits, and other components necessary for the operation of the video card. The larger the die size, the more space the GPU takes up on the video card. Larger die sizes can provide more computing resources such as CUDA cores or tensor cores, which can result in increased performance and graphics processing capabilities.
Show all
255
max 826
Average: 356.7
826
Length
247
max 524
Average: 250.2
524
Generation
A new generation of graphics card usually includes improved architecture, higher performance, more efficient use of power, improved graphics capabilities and new features.
Show all
Northern Islands
Manufacturer
TSMC
PSU Wattage
When choosing a power supply for your graphics card, consider the graphics card manufacturer’s power requirements, as well as other computer components.
Show all
450
max 1300
Mean value:
1300
Year of manufacture
2010
max 2023
Mean value:
2023
Heat Dissipation (TDP)
The Heat Dissipation Requirements (TDP) is the maximum amount of energy that can be dissipated by the cooling system. The lower the TDP, the less power will be consumed.
Show all
151W
Average value: 160 W
2W
Process technology
The small size of the semiconductor means it is a new generation chip.
40 nm
Average: 34.7 nm
4 nm
Number of transistors
1700 million
max 80000
Average: 7150 million
80000 million
PCIe version
Considerable speed is provided for an expansion card used to connect a computer to peripherals. The updated versions have impressive throughput and provide high performance.
Show all
2
Average: 3
4
Width
111mm
max 421.7
Average: 192.1mm
421.7 mm
Height
36mm
max 620
Average: 89.6mm
620 mm
Purpose
Desktop
Sales start date
2010-10-22 00:00:00
Mean value:
Release price
$239
max 419999
Average: $5679.5
419999 $
OpenGL version
OpenGL provides access to the graphics card’s hardware capabilities for displaying 2D and 3D graphics objects. New versions of OpenGL may include support for new graphical effects, performance optimizations, bug fixes, and other improvements.
Show all
4.4
Mean value:
DirectX
Used in demanding games, providing enhanced graphics
eleven
max 12. 2
Mean: 11.4
12.2
OpenCL version
Used by some applications to enable GPU power for non-graphical calculations. The newer the version, the more functional it will be
Show all
1.2
max 4.6
Average: 2.2
4.6
Shader model version
The higher the shader model version in the video card, the more functions and options are available for programming graphic effects.
Show all
5
max 6.7
Average: 5.9
6.7
Has HDMI output
HDMI output allows you to connect devices with HDMI or mini-HDMI ports. They can transmit video and audio to the display.
Show all
Yes
HDMI version
The latest version provides a wide signal transmission channel due to the increased number of audio channels, frames per second, etc.
Show all
1.3
max 2. 1
Mean: 1.9
2.1
DVI outputs
Allows connection to a display using DVI
2
Mean: 1.4
3
Number of HDMI connectors
The more there are, the more devices can be connected at the same time (for example, game/TV type consoles)
Show all
1
Average: 1.1
3
mini-DisplayPort
Allows you to connect to a display using a mini-DisplayPort
2
Mean: 2.1
8
Interface
PCIe 2.0 x16
HDMI
Digital interface used to transmit high definition audio and video signals.
Show all
Yes
Passmark test score
The Passmark Video Card Test is a program for measuring and comparing graphics system performance. It conducts various tests and calculations to evaluate the speed and performance of a graphics card in various areas.
Show all
2174
max 30117
Average: 7628. 6
30117
3DMark Cloud Gate benchmark score GPU
26012
max 196940
Average: 80042.3
196940
3DMark Fire Strike Score
2954
max 39424
Average: 12463
39424
3DMark Fire Strike Graphics 9 test score0022
It measures and compares the ability of a graphics card to process high-resolution 3D graphics with various graphic effects. The Fire Strike Graphics test includes complex scenes, lighting, shadows, particles, reflections, and other graphical effects to evaluate the graphics card’s performance in gaming and other demanding graphics scenarios.
Show all
3090
max 51062
Average: 11859.1
51062
3DMark 11 Performance GPU Score
4151
max 59675
Average: 18799.9
59675
3DMark Vantage Performance score
17488
max 97329
Average: 37830.