What's new
  • Please do not post any links until you have 3 posts as they will automatically be rejected to prevent SPAM. Many words are also blocked due to being used in SPAM Messages. Thanks!

NVIDIA GeForce GTX 580 Review

Status
Not open for further replies.

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,264
Location
Montreal
Even before NVIDIA’s Fermi architecture made it into the hands of enthusiasts, it was being criticized on a number of fronts. From power consumption to supposed profit margins to how many chips could effectively be produced; speculation ran wild and for the most part NVIDIA proved their detractors wrong in the months following launch.

Through all of this success, there were was still one small problem: the flagship GTX 480 didn’t really fit into the new realities of a market that was highly focused upon efficiency. It was a class-leading product in terms of overall performance but it fell behind in the performance per watt category against AMD’s HD 5800 and HD 5900 series. High temperatures and noise weren’t to everyone’s liking either and with AMD’s refreshed cards drawing ever closer, NVIDIA needed to dig deep and offer up a response. They have and it’s called the GTX 580.

The GTX 580 is what you would call the tip of Fermi’s “mid-life kicker” iceberg and is meant to keep the title of the world’s fastest DX11 GPU firmly within NVIDIA’s grasp. To do this, their engineers took the GF100 architecture and basically optimized it for better overall performance, lower power consumption and greater efficiency throughout the rendering pipeline. The result is a revised GF 100 core named the GF110 which has rendering power where it counts and should compete well against AMD’s upcoming high end offerings.

At it is most basic, the GTX 580 uses a full-enabled GF100 core with additional rendering and efficiency features walking hand in hand with some transistor rationalization on a microarchitectural level. Considering the outgoing GTX 480’s raw and unadulterated horsepower along with the possibilities of the GF110, not many will likely complain about these improvements necessitating a change in product family names. Especially when you consider the GTX 580 is only the beginning of NVIDIA’s top to bottom refresh.

When the GTX 480 was launched, one of the main topics of conversation was how late NVIDIA was to the DX11 party. As a result AMD had months of free sailing and massive sales figures. Now, a little more than seven months later both companies are launching their mid-life refreshes within a few weeks of one another. This really begs the question of whether NVIDIA has officially erased most of the lead AMD enjoyed over the last year or so. We have a feeling the answer will only arrive once actual availability of the GTX 580 hits the channels but word on the street is this will be a hard launch.

So what we are looking at is a potential market-leading card from NVIDIA that should be available soon after you read this. But will it maintain a sizable enough lead over the GTX 480 to justify its price of $499?

 
Last edited by a moderator:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,264
Location
Montreal
GF110; Something Old, Something Borrowed….

GF110; Something Old, Something Borrowed….


At the heart of the GTX 580 beats a revised GF100 core which has been christened GF110 for this somewhat new generation of products. Since most of the features are the same between the two cores, we invite you to visit our dedicated GF100 article where we go into all of the advancements the Fermi architecture brings to the table. This section meanwhile will used to discussing the new items NVIDIA has built into the GF110 which allow it to outpace the older series on a number of levels.


One of NVIDIA’s main focuses for the GF110 was to increase the overall performance per watt over past iterations of Fermi. As it stood the GTX 480 was and still is a massively powerful card but it hit up against a power consumption wall due to a number of inefficiencies within the architecture.

To address some of the inherent power consumption issues Fermi exhibited, NVIDIA basically rearranged their layout so more of the faster, higher leakage transistors were placed on the critical rendering paths instead of being used for periphery tasks. Meanwhile, the slower low leakage transistors were placed where speed wasn’t a primary concern.

Strategically distributing the transistors in this way allows for a small speed-up in overall rendering performance. More importantly it also means the fastest transistors will now be fully utilized instead of being used for non critical tasks and thus lowering overall performance per watt.


From a high-level architectural standpoint, not much has changed between the GF100 and the GF110. The layout still features 512 CUDA cores, 64 Texture Units, 48 ROPs and six 64-bit GDDR5 memory controllers along with a hefty count of 3 billion transistors.

Where the GF110 differs from the GF100 is its ability to feature higher clock speeds while enabling all 16 Streaming Multiprocessors without pushing astronomical power consumption figures. This means the new flagship GTX 580 will finally feature the full 512 cores many were hoping to see from the GTX 480.


By enabling this extra SM, the GTX 580 gains more than just 32 CUDA cores. Four additional texture units along with their associated cache structure are also added to the equation but the most important addition-for DX11 apps at least- is the single PolyMorph Engine which is attached to the SM. The extra tessellator contained in this unit could go a long way towards helping out with the higher tessellation workloads which second generation DX11 games will feature.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,264
Location
Montreal
…And Many Things New

…And Many Things New


While NVIDIA was prioritizing critical rendering paths with higher speed transistors, some additional improvements were made to the underlying Fermi architecture as well. Most of these were relatively minor in the grand scheme of things but when compounded they can lead to some impressive performance increases in certain scenarios.

While the GF100 architecture fully supported FP16 HDR texture formats, the GF110 now has the capability to process these textures at a higher throughput. With this “full speed” FP16 texture filtering, the TMUs within cards like the GTX 580 are able to operate at a slightly higher efficiency than the previous generation.


In addition to the increased FP16 performance, two other areas were prioritized: z-cull efficiency and the L1 cache. An overall bump in z-cull efficiency will mean quicker processing of certain draw calls which are sent through the GF110’s Raster Engine. In addition, the 64KB of shared memory and L1 cache now has additional configuration options which can in theory augment texture performance by speeding up the texture units’ communication with the rest of the rendering pipeline.

Some may remember that NVIDIA’s GF104 core handled instructions in a slightly different manner than the higher end Fermi GPUs. This was mostly due to the larger number of cores per Streaming Multiprocessor. However, since the GF110 maintains the same 32 cores per SM, it maintains the same instruction issuance as the GF100.


All of the advances we have been talking about can amount to some significant improvements in framerates across a cross section of games. Since the architectural enhancements are specifically targeted to certain areas of the rendering process, the impact they have varies from one game to the next. However, in DX11 apps or games that use a large amount of texture data, the focus upon high level geometry performance does prove to be beneficial.

The focus upon transistor layout also allowed for higher clock speeds so when the butcher’s bill is tallied, some games can see a performance jump of about 30%.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,264
Location
Montreal
NVIDIA’s Focus upon Acoustics and Heat

NVIDIA’s Focus upon Acoustics and Heat


One of the main critiques leveled against the GF100-based cards was their rampant heat production leading to high fan speeds. Using a GTX 480 in particular was never what we would call a completely silent experience but many of the critiques were blown a bit out of proportion in our opinion. Nonetheless, NVIDIA went back to the drawing board in order to completely redesign their high-end cooling solutions in order to focus upon lowering heat and shrinking the acoustical profile of their flagship products.


The first step was to discard the inefficient and massive heatpipe setup which came with the GTX 480. The replacement is a vapor-chamber cooler that quickly whisks away heat from the core in order to distribute it evenly across a large aluminum fin array.

A vapor chamber design is broken into a number of components. There is a copper base-plate that makes direct contact with the core so the water contained therein will quickly vaporize on the evaporator and make its way through the chamber to the condenser. The condenser wick is placed up against the upper cover in order to disperse the heat generated as the hot water vapor condenses. Finally, there is a transportation wick for liquid return that is used to move the condensed water back to the vaporization wick. Think of this like a massive flat heatpipe which is infinitely more efficient at dispersing heat over a large surface area.

In order for this method to be effective, the entire chamber needs to be sealed and put under vacuum. This is due to the fact that water vaporizes much easier in an environment with extremely low air pressure. Thus, it is very important that a vapor chamber cooler is well made without any manufacturing defects or the air pressure within the vapor chamber will decrease and this will result in lowered heat dissipation capabilities.


Other than the custom vapor chamber, there are additional features packed into the GTX 580 what are used to lower its overall noise profile.

Through testing, NVIDIA found the GTX 480’s fan had blades that were vibrating slightly which created certain tonal characteristics that could be annoying to some people. To rectify this, a tension ring was added around the fan’s edge and hub’s bottom was filled in to reduce friction. The whole setup was then placed closer to the fin array to allow the fan to spin at lower speeds when pushing cool air into the heatsink. For SLI systems, a small indent was added shroud’s rearmost portion which should allow for slightly better airflow.


The result of all these changes is of course a temperature reduction but additional benefits have been reaped in the acoustical department as well. According to NVIDIA, the GTX 580 should be quieter than a GTX 285 without any sacrifices in the thermal department due to “new” adaptive fan control. Basically, this mean the fan will ramp up in a much more linear fashion rather than the sudden jumps we saw with the GTX 480. Since it adjusts fan speed in real time based on core temperature it never really needs to run at high speeds since temperatures are kept in check from the get-go.


Most ultra high end cards exhibit absolutely epic power consumption numbers and the GF100 was no different. However, in order to better manage voltage fluctuations and power spikes, NVIDIA has implemented support for real-time monitoring of 12V voltage readings. If the reading on any of the PSU’s rails drops or increases by a set amount, the VRM modules on the card will immediately compensate. This should not only lower overall power consumption but also protect the card against “dirty” power from cheap PSUs.

In addition, the hardware monitoring modules are able to work hand in hand with the GF110 core to dynamically adjust performance to keep consumption within NVIDIA’s specifications. Overclocking won’t be affected by this unless you want to push things to obscene limits with exotic cooling but power “viruses” like Furmark which stress the GPU beyond its design limits will see their effectiveness reduced.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,264
Location
Montreal
The New NVIDIA Lineup

The New NVIDIA Lineup



Since the release of the first Fermi-based cards, NVIDIA has been slowly adding products to their lineup in an effort to counteract some of the inroads AMD had made with their own DX11 GPUs. There is currently a reasonably strong lineup of GeForce-branded cards available but there are still gaps at certain price points.

The GTX 580 slots into one section of the market where NVIDIA already had a strong presence: the ultra high end. With a suggested retail price of $499 it officially takes the cake as the most expensive single GPU card currently available. However, this is a far cry from the $549 to $599 many were expecting. How this will compare to AMD’s upcoming Cayman boards is anyone’s guess but we’re willing to bet there’s a bit of padding applied just in case some price cuts need to be made in the GTX 580’s price. We should also mention that additional 500-series cards are expected in the coming months so stay tuned for reviews of those as well.


While the GTX 480 and 580 are similar to one another from a high level architectural standpoint, the new GF110-based card clearly takes the lead for on-paper specifications.

Enabling the final SM within the architecture has allowed for 32 CUDA cores and four texture units above and beyond what the GTX 480 originally offered. The performance increase these items bring to the table shouldn’t be all that significant but they should give some additional horsepower in some situations.

The increased focus upon transistor efficiency has allowed an increase in the core clock speeds by slightly over 10%. GDDR5 memory speeds have also reached a first for the Fermi architecture by finally hitting the 4 Gbps mark and pushing the GTX 580 up above 192 GB/s of memory bandwidth. The fact that all of this is achieved while maintaining a slightly lower TDP than the GTX 480 really does speak volumes about how well the original GF100 architecture has evolved in less than a year.

So what does this mean for the GTX 480 whose price is still hovering between the $469 and $499 marks? According to NVIDIA, it will be gradually phased out as stock dries up in the retail channels. We will also see additional 500-series cards start taking over from the other first generation cards in the list above.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,264
Location
Montreal
A Closer Look at the GTX 580

A Closer Look at the GTX 580



The first hint NVIDIA’s newest card is a far cry from the GTX 480 it will be replacing is the design of the heatsink shroud. Gone is the massive finger-burning external heatsink and heatpipes that distinguished the outgoing flagship card, it has been replaced with a vast expanse of high endurance plastic.

Changes in the external heatsink design aside, the GTX 580 retains the same dimensions as its predecessor at 10 ½” long.


This card still uses a standard blower-style heatsink assembly but most of the changes are done under the hood and we will be taking a look at them in the next section.

Even though NVIDIA has effectively lowered the TDP of the Fermi architecture and the revised heatsink should result in overall lower temperatures (which has a huge effect on power consumption), the GTX 580 retains the 6-pin plus 8-pin power connector layout from the GTX 480.


The GTX 580 is compatible with three-way SLI via a pair of connectors on the card’s side. Above these connectors is a secondary vent for heat exhaust.

NVIDIA has retained the same backplate throughout most of their GTX 400 and now GTX 500 series lineups. It features a pair of DVI outputs and a single mini HDMI 1.4a connector and you will need a pair of these cards to run in Surround mode. Expect most of NVIDIA’s board partners to ship their cards with mini HDMI to HDMI adaptors.


When designing the GTX 580’s PCB, NVIDIA took the reference GTX 480’s layout and modified it a bit. The most noticeable difference is the lack of a fan cutout on the newer card for additional air circulation towards the fan along with a quartet of large modules used to provide additional capacitance for the core. There are a few more monitoring units installed on the PCB as well which we discussed in the last section.
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,264
Location
Montreal
Under the Hood

Under the Hood



Popping the lid off of the GTX 580 reveals the main vapor-chamber equipped heatsink as well as a large aluminum retention assembly that runs the length of the card. This black secondary heatsink is supposed to disperse additional heat from other components located throughout the PCB and disperse it efficiently.

Meanwhile, the main VRMs are given small openings in the retention assembly so they are directly cooled by the fan.


The copper valor chamber runs the entire length of the fin array which allows it to be directly cooled by the aluminum fins. These densely packed fins sport closed tops in order to channel the fan’s airflow towards the areas that most need it. In our opinion, this setup should be quite a bit more efficient than standard heatpipes since the entire surface of the chamber has its heat dispersed rather than the minimal contact heatpipes usually make with the cooling fins. The fan is also extremely close to the fins in order to maximize the amount of cool air that is pushed into them.


When compared to the GTX 480, the two heatsink is approximately the same size but on the newer card it has been pulled slightly closer to the fan. Other than the obvious change towards a vapor chamber cooler, it is the fan which has received most of NVIDIA’s engineering attention. As we discussed in a previous section, a retaining ring was added to stop fin cavitations and there is now a solid base on the fan’s underside. This is all to reduce the amount of noise the GTX 580 generates when under load.

 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,264
Location
Montreal
Partner Cards from ASUS & EVGA

ASUS Geforce GTX 580 Voltage Tweak





As with most other launches in the last month or so, ASUS isn't releasing an reference-clocked cards this time around but is rather focusing upon giving users a small overclock on all mass production cards. This amounts to only 10Mhz on the GTX 580 but considering this card will retail for the same price as all other GTX 580s, we'll take what amounts to a free clock speed increase.

One of ASUS' claims to fame is their Voltage Tweak feature that allows users to increase the graphics card's core voltage in order to push overclocks to the next level. In this case, ASUS claims some impressive overclocking headroom can be gained by using their included software. In their example, a GTX 580 could be pushed over the 1100Mhz mark. We'll be testing this VERY soon.


EVGA GeForce GTX 580, Black Ops Edition & Waterblock Edition







EVGA will be releasing a whole lineup of GTX 580 cards along with the standard reference version. There will be a Superclocked, CoD Black Ops Edition and waterblock-equipped card which will all retail with a price premium over the stock card. The Black Ops Edition in particular is interesting since even though it doesn't actually come with the game itself, it features a custom heatsink sticker and an included poster. We expect to see additional cards from EVGA in the future since the overclocking headroom on the GTX 580 should allow them to release SSC and FTW branded products.
 
Last edited:

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,264
Location
Montreal
Test System & Setup

Test System & Setup

Processor: Intel Core i7 920(ES) @ 4.0Ghz (Turbo Mode Enabled)
Memory: Corsair 3x2GB Dominator DDR3 1600Mhz
Motherboard: Gigabyte EX58-UD5
Cooling: CoolIT Boreas mTEC + Scythe Fan Controller (Off for Power Consumption tests)
Disk Drive: Pioneer DVD Writer
Hard Drive: Western Digital Caviar Black 640GB
Power Supply: Corsair HX1000W
Monitor: Samsung 305T 30” widescreen LCD
OS: Windows 7 Ultimate N x64 SP1


Graphics Cards:

NVIDIA GTX 580
NVIDIA GTX 480 (Ref)
NVIDIA GTX 470 (Ref)

ATI HD 5970 2GB (Ref)
ATI HD 5870 1GB (Ref)
ATI HD 5850 1GB (Ref)
ATI HD 6870 1GB (Ref)
ATI HD 6850 1GB (Ref)



Drivers:

NVIDIA 262.99 Beta
ATI 10.10 WHQL + 10.10d App Profiles


Applications Used:

Aliens Versus Predator
Battlefield: Bad Company 2
DiRT 2
Just Cause 2
Lost Planet
Metro 2033
Starcraft 2
Unigine: Heaven


*Notes:

FOR MORE INFORMATION ABOUT OUR BENCHMARKING PROCESS PLEASE SEE THIS ARTICLE

- All games tested have been patched to their latest version

- The OS has had all the latest hotfixes and updates installed

- All scores you see are the averages after 3 benchmark runs

All game-specific methodologies are explained above the graphs for each game

All IQ settings were adjusted in-game
 

SKYMTL

HardwareCanuck Review Editor
Staff member
Joined
Feb 26, 2007
Messages
13,264
Location
Montreal
Aliens Versus Predator (DX11)

Aliens Versus Predator (DX11)


When benchmarking Aliens Versus Predator, we played through the whole game in order to find a section which represents a “worst case” scenario. We finally decided to include “The Refinery” level which includes a large open space and several visual features that really tax a GPU. For this run-through, we start from within the first tunnel, make our way over the bridge on the right (blowing up several propane tanks in the process), head back over the bridge and finally climb the tower until the first run-in with an Alien. In total, the time spent is about four minutes per run. Framerates are recorded with FRAPS.


1680 x 1050





1920 x 1200





2560 x 1600



 
Status
Not open for further replies.

Latest posts

Twitter

Top