Introducing the GTX 570 – the GTX 480’s Performance at $349
Less than a month ago we reintroduced Nvidia’s “Tank”, the GTX 580 as a much leaner, meaner and faster machine – all the while improving on the thermals, power draw and noise of the reference GTX 480. The Tank refers particularly to Nvidia’s flagship video cards which are equipped to handle any gaming situation at high resolution and with maximum details and with maximum filtering and anti-aliasing applied. However, there is another brand-new tank, the GTX 570 that has just launched bringing with it all of the features of its big brother, the GTX 580, but at a lower price and with somewhat reduced performance . . . a “lighter” tank, if you will.
Nvidia advertises their new high-performance GPUs as “the World’s Fastest DX11 GPUs” and we now bring you the details of our GTX 570 performance showdown with the reference GTX 480, the reference GTX 580, the reference Diamond HD 5870 and the reference HD 6870 to see if we can verify Nvidia’s claim. On top of that, we also added in our HD 6850, three GTX 460s; 1 GB and 768 MB versions, as well as the highly overclocked EVGA FTW GTX 460 for a total of ten video cards to see where the new GTX 470 sits in terms of value for dollar as we test performance in 23 modern games.
Here is the brand new reference GTX 570 (lower image) compared with the reference GTX 580 released almost a month ago. Can you spot the only obvious identifying difference between these two cards?
It is good to see that the GTX 570 only requires two 6-pin PCIe connectors unlike the GTX 580 (and the GTX 480/470) which require the 8-pin+6-pin PCIe connectors. Below we see our family of ten cards that we will benchmark for you – GTX 580/GTX 470/GTX 280/GTX 460-1GB/GTX 460-1GB OC/GTX 460-768MB/HD 5870/HD 6870 and HD 6850. Only our GTX 480 is not pictured here.
The reason we are benching ten cards for you is to give you relative price to performance and we would also like to show you how a top card of two generations ago – the GTX 280 – will fair; it will also represent the GTX 275 as the performance is very similar. If fact, the GTX 275’s to the GTX 280’s performance is similar to what we will discover today between the GTX 480 and the new GTX 570.
Of course, the cards that we will be most closely comparing is our GTX 570 with the GTX 480 and AMD’s top two cards, the HD 5870 and the HD 6870. Clearly the GTX 470 is designed to be outclassed by its bigger brother, the GTX 580, but it will be interesting to see how the performance of a $349 GTX 570 compares with the performance of the GTX 480 – a $500 video card released just eight months ago. AMD’s HD 5870 was released about 14 months ago and it is still their fastest single-GPU video card; the HD 6870 was only intended to replace the HD 5850 performance-wise for less money and we have yet to see AMD’s newest high-end “Cayman” HD 6900 series video cards which will compete with the GTX 580/570.
Nvidia released its long awaited GeForce GTX based on its brand new Fermi DX11 GF100 architecture back in April of this year, six months later than AMD’s own DX11 Cypress video cards. This new Fermi GPU – Graphics Processing Unit – a term originally originated by Nvidia is a continuation of their strategy since their G80 which launched over three year ago to create a General Purpose Processor – co-equal with the CPU – that also renders amazing graphics. The culmination of Nvidia’s efforts with their GF100 DX11 Fermi architecture; the GTX 480, their flagship GPU – up-until-this-moment – is the fastest single GPU with the caveat that it runs rather hot and the cooling solutions based on the reference design are rather noisy.
Things have been changing very rapidly as just over ten weeks ago, we introduced Nvidia’s new refined GTX 400 series ‘Tank’, the Galaxy GTX 480 SuperOverclock on a mature process, which Galaxy called “the fastest GTX 480 card in the world.” This overclocked GTX 480 was already the “fastest single GPU video card” in the slower-clocked reference version which we covered in this review. We found that the new Galaxy GTX 480 SOC is not only super-fast, but it is also 30 dBA quieter than the reference version and is also 30C cooler thanks to its impressive and well-engineered 3-slot design and Arctic-Cooling VGA cooler – and all for a suggested etail price of $489. Well now, enter the completely redesigned Nvidia Tank – at $499 suggested etail pricing. Best of all, the GTX 580 is designed to be faster and more efficient than even the super-overclocked GTX 480s.
We saw AMD introduce their new line up, HD 68×0 series to replace HD 58×0 series in our review here. We found out that the “Barts” GPU it is based on is only a mid-range launch so far with the HD 6870 only slightly faster than the HD 5850; the best part is that it replaces it for less money. We will use the HD 6870 and the HD 5870 to show you where the GTX 580 fits in relation to them and we also wait for AMD’s high end “Cayman” HD 6900 series to be released, hopefully this month. An evaluation such as this one can only give you the equivalent of a “snapshot” of a moment in time and we shall attempt to determine the value of this new video card in relationship to the others right now.
Nvidia’s new GTX 570 now comes with a MSRP of $349. So we need to answer the question: Is it worth the $100 premium over the $250 or so dollars that one would currently spend for AMD’s top single-GPU video card – a HD 5870?
To properly bring you this review, we are using our reference Diamond HD 5870 (850/1200 MHz) as well as our reference stock-clocked AMD HD 6870 (900/1050 MHz) which we put through their paces this week with the very latest WHQL drivers – Catalyst 10-11, although Catalyst 10-10 is still the most current WHQL drivers for HD 68×0 series. We are also tossing a GTX 280 into the mix; the approximate equivalent of the GTX 275 from the last generation to see how GTX 570 compares – the fastest single-GPU card of two generations past versus the cards of this generation .
You will see us pit our HD 5870 and the HD 6870 against the new GTX 570, both stock and overclocked, and also against the reference GTX 480 and also versus our reference GTX 580 in 23 modern games and in 2 synthetic benchmarks generally using 1680×1050, 1920×1200 and/or 2560×1600 resolutions. Since we are using the fastest of the fast single-GPU video cards, it makes sense to test them at the highest resolutions and with the most demanding playable settings. Since we are matching the top single-GPU video cards to each other in a performance showdown, we do not include the dual-GPU HD 5970, nor CrossFire, nor SLI configurations.
Before we do performance testing, let’s take a look at the GTX 480 and quickly recap its new DX11 architecture and features of the original Fermi GF100 which we covered in our reviews of the GTX 480, published here, here and here. Senior Editor BFG10K reviewed GTX 470 here and here and Senior editor MrK covered GTX 465 here.
We also recently examined the performance of Galaxy’s GTX 480 SuperOverclock and we also reran GTX 480 against stock and overclocked versions of HD 5870, HD 6870 and HD 6850 here just a few weeks ago. Our very latest review covered the GTX 580 less than a month ago. Now you are up to date.
The GeForce GTX 570 was designed from the ground up to deliver exceptional tessellation performance, which is a key component of Microsoft’s DirectX 11 development platform for PC games. Tessellation allows game developers to take advantage of the GeForce GTX 570 GPU’s tessellation ability to increase the geometric complexity of models and characters to deliver far more realistic and visually rich gaming environments. You will soon see that the clocks of Nvidia’s GTX 570 are clocked higher than the reference GTX 480 version and that we were also able to go even further than the reference core clock that Nvidia set for the GTX 570 while still remaining cool and quiet. Here is the specification chart for the GTX 580 at a glance; right away we notice its lower TDP of only 219W and that the new GPU now supports the new HDMI 1.4a connector standard.
Needless to say, the new Fermi GF110 GTX 570 brings a lot of features to the table that current Nvidia customers will appreciate, including improved CUDA’s PhysX, 2D and 3D Surround to drive up to 3 LCDs with GTX SLI and Tri-SLI, superb tessellation capabilities and a really fast GPU in comparison to their GT200 series and even their GF100 GTX 480 series. Let’s see how Nvidia breaks down the enhancements of their new GTX 570 to the reference GTX 480 in terms of performance.
While the GTX 480 and GTX 5×0 share the same SM configuration, the newer GTX 5×0 has improved performance on a clock-per-clock basis by improvement in two key areas. The new GTX 570 now supports full FP16 texture filtering and new tile formats that increase efficiency of up to 5% or more in many cases over the GTX 470. Besides that, Nvidia has increased the clock frequencies and the number of CUDA cores in the GTX 480 from 480 cores to 512 in the GTX 580 and there are also more texture units and SMs all operating more efficiently. Check out a quick comparison chart which portends that the GTX 570 and the GTX 480 will perform very similarly to each other – much the same way that the GTX 280 performs compared with the GTX 275.
Beauty is more than skin deep
The GF100 Fermi GTX 470 was completely re-engineered at the transistor level into the GF110 GTX 570. Through a complete Fermi redesign on a mature process on TSMC’s 40 nm, the GTX 570 achieves higher clockspeed than the GTX 470 with less power and two hundred million fewer transistors. In other words, Nvidia increased the CUDA core count from 448 to 480, upped the clock speed and lowered the power requirements. This has lead to an amazing reduction in noise from the VGA cooling fan that now brings it into a much lower db range. In fact, our own ears tell us that the GTX 570 is now about as quiet as the HD 5870 – both cards do not suffer from the loud and sometimes startling “spin up” of the GTX 480/470 when they are under load in a game. How has Nvidia achieved this?
Nvidia’s new vapor chamber
Vapor chamber cooling is not new to the PC world and AMD Graphics first began shipping video cards with vapor chamber coolers in 2007 and has continued to develop them on every product generation since, including the $180 Radeon HD 6850. However, this kind of cooling is new for Nvidia’s GTX 580 and GTX 570. The GTX 570 employs a custom sealed copper vapor chamber to efficiently remove heat from the GPU. It then dissipates the heat by blowing the GPU-heated air through a large dual-slot heatsink and out the back of the video card and thus out of the PC case. But there is more to quietly cooling a hot GPU than a vapor chamber. Nvidia has redesigned the GTX 470’s reference fan completely. The new GTX 570 fan has been re-engineered to produce a lower pitch and tone that is less noticeable to human hearing.
Not once in the past few days did this reviewer notice the noise coming from the GTX 570 – in sharp contrast to the GTX 480 which would sometimes be quite noticeable during a game. In fact, the GTX 570 features a new fan speed control algorithm that is adaptive; it smooths the ramp up and down of fan RPMs that are far less noticeable than the GTX 470’s. This improved programmable fan controller has enabled fine-grained and continuously variable control which handles multiple fan profiles simultaneously that respond instantly to the temperature changes and it is also found in competing Radeon products own internal micro-controllers.
To add to the SLI experience, even the cover of the GTX 570 has been redesigned so that its cover is angled so as to offer better airflow between two cards in tight SLI configurations.
Can you tri-SLI your GTX 580?
Tri-SLI is supported by GTX 570 and there is improved scaling for SLI with GTX 570. There are also recently more compelling reasons besides increased performance to consider GTX 570 SLI which includes being able to experience Nvidia’s multi-display 2D/3D Surround. You will also require a less powerful PSU to run your GTX 570 SLI than with powering GTX 470 SLI. And because of its cover’s new angled design, a GTX 570 can be used in SLI configuration with another GTX 570 and still get decent cooling in many X58 motherboards that currently overheat using two GTX 470s in SLI. Also, by using the latest GeForce 260 drivers, each card can keep its own unique clocks or they can be set asynchronously. Because of severe time constraints on this article, SLI will be examined in depth in a further article as well as 3-panel 2D Surround versus Eyefinity.
New Power Monitoring Hardware – or no more Furmark!
In order to stay below the 300 W power limit imposed by the PCIe specification, NVIDIA has added a power draw limitation system to their card. When either Furmark or OCCT are detected, sensors measure the incoming current and voltage to calculate the total power draw. If the power draw exceeds a certain predetermined limit, the GTX 580 will automatically downclock to avoid damage to hardware component. After the power draw drops back to safe limits, the GPU returns to normal clocks much the same as in thermal management.
Because of this, we will no longer use Furmark for showing power draw and will return to using games to illustrate real world situations. Currently, this power management only switches on when Furmark or OCCT are detected and it should not limit overclocking unless Nvidia extends this management to regular PC games. Evidently this works by having the GeForce driver detect the program and treat it as a virus; but we have found a workaround using a very old version of FurMark – probably for the last time in our testing as Nvidia responds to this with better security measures.
Let’s flip the GTX 570 0ver and check out the other side:
As a total package, the new GTX 570 looks (and sounds) great! It looks and feels as solid and as heavy at $350 as the $500 GTX 580. Let’s show you the results of our 72-hour test drive, shall we? We will put it to the test in 23 PC games and in two synthetic tests. But first, head to the next page to check out our test bed configuration.