Gtx 580 gpu z: NVIDIA GeForce GTX 580 Specs

Meet the Inno 3D GTX 580 OC

We have in our labs Inno3D’s implementation of the GTX 580, the Inno3D GTX 580 OC . As you realize, the card is an overclocked version of Nvidia’s design. The card’s graphics clock and processor clock is boosted to 820 MHz/ 1640 MHz from the native 772 / 1544 MHz, while the memory runs at 1050 MHz

Here is some more information about the Inno3D GTX 580 OC, as the GPU-Z utility reports:

Nvidia’s GeForce GTX 580 graphics processor

As you may know, the GeForce GTX 480 had a troubled childhood. The GF100 chip that powered it was to be Nvidia’s first DirectX 11-class graphics processor, based on the ambitious new Fermi architecture. But the GF100 was famously tardy, hitting the market over six months after the competition’s Radeon HD 5000-series of DX11-capable chips. When it did arrive aboard the GTX 470 and 480, the GF100 had many of the hallmarks of a shaky semiconductor product: clock speeds weren’t as fast as we’d anticipated, power consumption and heat production were right at the ragged edge of what’s acceptable, and some of chip’s processing units were disabled even on the highest-end products. Like Lindsay Lohan, it wasn’t living up to its potential. When we first tested the GTX 480 and saw that performance wasn’t much better than the smaller, cooler, and cheaper Radeon HD 5870, we were decidedly underwhelmed.

Yet like Miss Lohan, the GF100 had some rather obvious virtues, including formidable geometry processing throughput and, as we learned over time, quite a bit of room for performance increases through driver updates. Not only that, but it soon was joined by a potent younger sibling with a different take on the mix of resources in the Fermi architecture, the GF104 chip inside the very competitive GeForce GTX 460 graphics cards.

Little did we know at the time, but back in February of this year, before the first GF100 chips even shipped in commercial products, the decision had been made in the halls of Nvidia to produce a new spin of the silicon known as GF110. The goal: to reduce power consumption while improving performance. To get there, Nvidia engineers scoured each block of the chip, employing lower-leakage transistors in less timing-sensitive logic and higher-speed transistors in critical paths, better adapting the design to TSMC’s 40-nm fabrication process.

At the same time, they made a few targeted tweaks to the chip’s 3D graphics hardware to further boost performance. The first enhancement was also included in the GF104, a fact we didn’t initially catch. The texturing units can filter 16-bit floating-point textures at full speed, whereas most of today’s GPUs filter this larger format at half their peak speed. The additional filtering oomph should improve frame rates in games where FP16 texture formats are used, most prominently with high-dynamic-range (HDR) lighting algorithms. HDR lighting is fairly widely used these days, so the change is consequential. The caveat is that the GPU must have the bandwidth needed to take advantage of the additional filtering capacity. Of course, the GF110 has gobs of bandwidth compared to most.

The second enhancement is unique to GF110: an improvement in Z-culling efficiency. Z culling is the process of ruling out pixels based on their depth; if a pixel won’t be visible in the final, rendered scene because another pixel is in front of it, the GPU can safely neglect lighting and shading the occluded pixel. More efficient Z culling can boost performance generally, although the Z-cull capabilities of current GPUs are robust enough that the impact of this tweak is likely to be modest.

The third change is pretty subtle. In the Fermi architecture, the shader multiprocessors (SMs) have 64KB of local data storage that can be partitioned either as 16KB of L1 cache and 48KB of shared memory or vice-versa. When the GF100 is in a graphics context, the SM storage is partitioned in a 16KB L1 cache/48KB shared memory configuration. The 48KB/16KB config is only available for GPU computing contexts. The GF110 is capable of running with a 48KB L1 cache/16KB shared memory split for graphics, which Nvidia says “helps certain types of shaders.”

Now, barely nine months since the chip’s specifications were set, the GF110 is ready to roll aboard a brand-new flagship video card, the GeForce GTX 580. GPU core and memory clock speeds are up about 10% compared to the GTX 480—the GPU core is 772MHz, shader ALUs are double-clocked to 1544MHz, and the GDDR5 memory now runs at 4. 0 GT/s. All of the chip’s graphics hardware is enabled, and Nvidia claims the GTX 580’s power consumption is lower, too.

	Peak pixel fill rate (Gpixels/s)	Peak bilinear FP16  texel filtering rate (Gtexels/s)	Peak memory bandwidth (GB/s)	Peak shader arithmetic (GFLOPS)	Peak rasterization rate (Mtris/s)
GeForce GTX 460 1GB 810MHz	25.9	47.6	124. 8	1089	1620
GeForce GTX 480	33.6	21.0	177.4	1345	2800
GeForce GTX 580	37.1	49.4	192.0	1581	3088
Radeon HD 5870	27.2	34.0	153.6	2720	850
Radeon HD 5970	46. 4	58.0	256.0	4640	1450

On paper, the changes give the GTX 580 a modest boost over the GTX 480 in most categories that matter. The gain in FP16 filtering throughput, though, is obviously more prodigious. Add in the impact of the Z-cull improvement, and the real-world performance could rise a little more.

A question of balance

Notably, other than the increase in FP16 filtering rate, the GF110 retains the same basic mix of graphics resources as the GF100. We’ll raise an eyebrow at that fact because the GF104 is arguably more efficient, yet it hits some very different notes. Versus GF100/110, the GF104’s ROP rate, shader ALUs, and memory interface width are lower by a third, the rasterization rate is cut in half, yet the texturing rate remains constant.

Not reflected in the tables above is another element: the so-called polymorph engines in the Fermi architecture, dedicated hardware units that handle a host of pre-rasterization geometry processing chores (including vertex fetch, tessellation/geometry expansion, viewport transform, attribute setup, and stream output). The GF104 has eight such engines, while the GF100/110 have 16. Only 15 of the 16 are enabled on the GTX 480, while the GTX 580 uses them all, so it possesses even more geometry processing capacity than anything to come before. (If you want to more fully understand the configuration of the different units on the chip and their likely impact on performance, we’d refer you to our Fermi graphics architecture overview for the requisite diagrams and such. Nearly everything we said about the GF100 still applies to the GF110.)

Also still kicking around inside of the GF110 are the compute-focused features of the GF100, such as ECC protection for on-chip storage and the ability to handle double-precision math at half the rate of single-precision. These things are essentially detritus for real-time graphics, and as a consequence of product positioning decisions, GTX 580’s double-precision rate remains hobbled at one-quarter of the chip’s peak potential.

The GF110 hides under a metal cap that’s annoyingly tough to remove

We detected some trepidation on Nvidia’s part about the reception the GF110 might receive, given these facts. After all, there was a fairly widespread perception that GF100’s troubles were caused at least in part by two things: its apparent dual focus on graphics and GPU computing, and its clear emphasis on geometry processing power for graphics. The GF104’s singular graphics mission and improved efficiency in current games only fed this impression.

Nvidia’s counter-arguments are worth hearing, though. The firm contends that any high-end GPU like this one has plenty of throughput to handle today’s ubiquitous console ports, with their Unreal engine underpinnings and all that entails. The GF110’s relative bias toward geometry processing power is consistent with Nvidia’s vision of where future games based on DirectX 11 should be headed—with more complex models, higher degrees of tessellation, and greater geometric realism. In fact, Drew Henry, who runs Nvidia’s GeForce business, told us point blank that the impetus behind the GF110 project was graphics, not GPU computing products. That’s a credible statement, in our estimation, because the GF100-based Tesla cards have essentially zero competition in their domain, while the GeForces will face a capable foe in AMD’s imminent Cayman GPU.

Our sense is that, to some extent, the GF110’s success will depend on whether game developers and end users are buying what Nvidia is selling: gobs and gobs of polygons. If that’s what folks want, the GF110 will deliver in spades. If not, well, it still has 50% more memory bandwidth, shader power, and ROP throughput than the GF104, making it the biggest, baddest GPU on the planet by nearly any measure, at least for now.

The card and cooler

	GPU clock (MHz)	Shader ALUs	Textures filtered/ clock	ROP pixels/ clock	Memory transfer rate	Memory interface width (bits)	Peak power draw	Suggested e-tail price
GeForce GTX 580	772	512	64	48	4. 0 Gbps	384	244W	$499.99

Amazingly, I’ve put enough information in the tables, pictures, and captions on this page that I barely have to write anything. Crafty, no? We’ve already given you some of the GTX 580’s vitals on the previous page, but the table above fills out the rest, including the $500 price tag. Nvidia expects GTX 580 cards to be selling at online retailers for that price starting today.

Gone are the quad heatpipes and exposed heatsink of the GTX 480 (left),

replaced by a standard cooling shroud on the GTX 580 (right).

Outputs include two dual-link DVI ports and a mini-HDMI connector.

Dual SLI connectors threaten three-way SLI.

The card is 10.5″ long.

Power inputs include one six-pin connector and one eight-pin one.

Although we didn’t find it to be especially loud in a single-card config, the GeForce GTX 480 took some criticisms for the noise and heat it produced. The noise was especially a problem in SLI, when the heat from two cards together had to be dissipated. Nvidia has responded to that criticism by changing its approach on several fronts with the GTX 580. For one, the end of the cooling shroud, pictured above, is angled more steeply in order to allow air into the blower.

Rather than using quad heatpipes, the GTX 580’s heatsink has a vapor chamber in its copper base that is purported to distribute heat more evenly to its aluminum fins. Meanwhile, the blades on the blower have been reinforced with a plastic ring around the outside. Nvidia claims this modification prevents the blades from flexing and causing turbulence that could translate into a rougher sound. The GTX 580 also includes a new adaptive fan speed control algorithm that should reduce its acoustic footprint.

The newest GeForce packs an additional power safeguard, as well. Most GeForces already have temperature-based safeguards that will cause the GPU to slow down if it becames too hot. The GTX 580 adds a power monitoring capability. If the video card is drawing too much current through the 12V rails, the GPU will slow down to keep itself within the limits of the PCIe spec. Amusingly, this mechanism seems to be a response to the problems caused almost solely by the FurMark utility. According to Nvidia, outside of a few apps like that one, the GTX 580 should find no reason to throttle itself based on power delivery.

So who’s the competition?

AMD’s decision a couple of years ago to stop making really large GPUs and instead address the high-end video card market with multi-GPU solutions makes sizing up the competition for the GTX 580 a little bit complicated. We have some candidates, though, with various merits.

If you’re insistent on a single-GPU solution, Asus’ Republic of Gamers Matrix 5870 might be your best bet. This card has 2GB of GDDR5 memory, double that of the standard Radeon HD 5870, and runs at 894MHz, or 44MHz higher than AMD’s stock clocks for the Radeon HD 5870. That’s a modest bump in clock frequency, but Asus has given this card a host of overclocking-centric features, so the user can take it up from there. The ROG Matrix 5870 lists for $499.99 at Newegg, although it’s currently out of stock. We’ve included this card in our test results on the following pages, though it’s looking a little dated these days.

AMD’s true high-end solution is the Radeon HD 5970, pictured above. With dual Cypress GPUs, the 5970 is pretty much a performance titan. The 5970 has always been something of a strange specimen, for various reasons, including the fact that it has been incredibly scarce, and thus pricey, for much of the time since its introduction late last year. The card itself is incredibly long at 12.16″, ruling it out of an awful lot of mid-sized PC enclosures. As a dual-GPU solution based on AMD’s CrossFireX technology, the 5970 has the same potential for compatibility headaches and performance scaling pitfalls as a dual-card CrossFireX config. Also, the 5970 isn’t quite as fast as dual Radeon HD 5870s. Instead, it leaves some of its performance potential on the table, because its clock rates have been held down to keep power consumption in check. If your PSU can handle it, though, AMD expects the 5970 to reach dual-5870 clock speeds with the aid of a third-party overclocking tool with voltage control.

Oddly enough, the 5970 emerged from obscurity in the past week, when AMD notified us of the availability of cards like this Sapphire 5970 at Newegg at a new, lower price. Not coincidentally, that price is $499.99—just the same as the GeForce GTX 580. There’s a $30 mail-in rebate attached, too, for those who enjoy games of chance. That’s a heckuva welcome for Nvidia’s latest, don’t you think?

We tested the 5970 at it stock speed, and in hindsight, perhaps we should have tested it overclocked to dual 5870 speeds, as well, since that’s part of its appeal. However, we had our eyes set on a third, more interesting option.

The introduction of the Radeon HD 6870 largely obsoleted the Radeon HD 5870, and we’d argue that a pair of 6870 cards might be AMD’s best current answer to the GTX 580. Gigabyte’s version of the 6870 is going for $244.99 at Newegg. (You can grab a 6870 for $239 if you’re willing to try your luck with PowerColor or HIS.) Two of these cards will set you back about as much as a single GTX 580. If you have the expansion slot real estate and PSU leads to accommodate them, they might be a good pick. Heck, they’re what we chose for the Double-Stuff build in our most recent system guide.

Naturally, we’ve tested both single- and dual-6870 configurations, along with some in-house competition for the GTX 580 in the form of a pair of GeForce GTX 460 1GB cards clocked at over 800MHz. These GTX 460 cards are the most direct competitors for the 6870, as well.

Our testing methods

Many of our performance tests are scripted and repeatable, but for some of the games, including Battlefield: Bad Company 2, we used the Fraps utility to record frame rates while playing a 60-second sequence from the game. Although capturing frame rates while playing isn’t precisely repeatable, we tried to make each run as similar as possible to all of the others. We raised our sample size, testing each FRAPS sequence five times per video card, in order to counteract any variability. We’ve included second-by-second frame rate results from Fraps for those games, and in that case, you’re seeing the results from a single, representative pass through the test sequence.

As ever, we did our best to deliver clean benchmark numbers. Tests were run at least three times, and we’ve reported the median result.

Our test systems were configured like so:

Processor	Core i7-965 Extreme 3.2GHz
Motherboard	Gigabyte EX58-UD5
North bridge	X58 IOH
South bridge	ICh20R
Memory size	12GB (6 DIMMs)
Memory type	Corsair Dominator CMD12GX3M6A1600C8 DDR3 SDRAM at 1600MHz
Memory timings	8-8-8-24 2T
Chipset drivers	INF update 9. 1.1.1025 Rapid Storage Technology 9.6.0.1014
Audio	Integrated ICh20R/ALC889A with Realtek R2.51 drivers
Graphics
	Asus Radeon HD 5870 1GB with Catalyst 10.10c drivers
	Asus ROG Matrix Radeon HD 5870 2GB with Catalyst 10.10c drivers
	Radeon HD 5970 2GB with Catalyst 10.10c drivers
	XFX Radeon HD 6870 1GB with Catalyst 10.10c drivers
	Sapphire Radeon HD 670 1GB + XFX Radeon HD 6870 1GB with Catalyst 10. 10c drivers
	MSI Hawk Talon Attack GeForce GTX 460 1GB 810MHz with ForceWare 260.99 drivers
	MSI Hawk Talon Attack GeForce GTX 460 1GB 810MHz + EVGA GeForce GTX 460 FTW 1GB 850MHz with ForceWare 260.99 drivers
	Galaxy GeForce GTX 470 1280MB GC with ForceWare 260.99 drivers
	GeForce GTX 480 1536MB with ForceWare 260.99 drivers
	GeForce GTX 580 1536MB with ForceWare 262.99 drivers
Hard drive	WD RE3 WD1002FBYS 1TB SATA
Power supply	PC Power & Cooling Silencer 750 Watt
OS	Windows 7 Ultimate x64 Edition DirectX runtime update June 2010

Thanks to Intel, Corsair, Western Digital, Gigabyte, and PC Power & Cooling 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.

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.

We used the following test applications:

• D3D RightMark beta 4
• Unigine Heaven 2.1
• ShaderToyMark 0.1.0
• TessMark 0.2.2.
• 3DMark Vantage 1.0.2
• Aliens vs. Predator benchmark
• Battlefield: Bad Company 2
• HAWX 2
• DiRT 2
• Left 4 Dead 2
• Sid Meier’s Civilization V
• Metro 2033
• StarCraft II
• Fraps 3.2.3
• GPU-Z 0.4.7

Some further notes on our methods:

• We measured total system power consumption at the wall socket using a Yokogawa WT210 digital power meter. The monitor was plugged into a separate outlet, so its power draw was not part of our measurement. The cards were plugged into a motherboard on an open test bench.

  The idle measurements were taken at the Windows desktop with the Aero theme enabled. The cards were tested under load running Left 4 Dead 2 at a 1920×1080 resolution with 4X AA and 16X anisotropic filtering. We test power with Left 4 Dead 2 because we’ve found that the Source engine’s fairly simple shaders tend to cause GPUs to draw quite a bit of power, so we think it’s a solidly representative peak gaming workload.

• We measured noise levels on our test system, sitting on an open test bench, using an Extech 407738 digital sound level meter. The meter was mounted on a tripod approximately 10″ from the test system at a height even with the top of the video card.

  You can think of these noise level measurements much like our system power consumption tests, because the entire systems’ noise levels were measured. Of course, noise levels will vary greatly in the real world along with the acoustic properties of the PC enclosure used, whether the enclosure provides adequate cooling to avoid a card’s highest fan speeds, placement of the enclosure in the room, and a whole range of other variables. These results should give a reasonably good picture of comparative fan noise, though.

• We used GPU-Z to log GPU temperatures during our load testing.

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.

Power consumption

We’ll kick off our testing with power and noise, to see whether the GTX 580 lives up to its promise in these areas. Notice that the cards marked with asterisks in the results below have custom cooling solutions that may perform differently than the GPU maker’s reference solution.

The GTX 580’s power use when idling at the Windows desktop is quite reasonable for such a big chip. Our test system requires 13W less with a GTX 580 than with a GTX 480, a considerable drop. When we fire up Left 4 Dead 2, a game we’ve found causes GPUs to draw quite a bit of power, then the GTX 580 pulls a little more juice than its predecessor. That’s not bad considering the higher clock rates and additional enabled units, but Nvidia claims the GTX 580 draws less power than the 480, even at peak.

When we asked Nvidia what the story was, they suggested we try a DX11-class workload, such as the Unigine Heaven demo, to see the difference between the GTX 480 and GTX 580. So we did:

Peak power draw is lower for both video cards, but the GTX 580 uses substantially less than the 480. Obviously, much depends on the workload involved. We may have to consider using multiple workloads for power testing going forward.

Noise levels and GPU temperatures

In spite of its relatively high peak power draw, the GTX 580 is among the quietest cards we tested. That’s a testament to the effectiveness of this card’s revised cooling design. Our positive impression of the cooler is further cemented by the fact that the GTX 580 runs 10°C cooler than the GTX 480, though its power use is comparable. The Radeon HD 5970 draws slightly less power than the GTX 580 but runs hotter and generates substantially more noise.

We do have some relatively boisterous contestants lined up here. MSI has tuned its dual-fan cooler on the GTX 460 to shoot for very low GPU temperatures, making it rather noisy. That dynamic gets worse when we slap another card next to it in SLI, blocking the intake for both fans. GPU temperatures shoot up to match the rest of the pack, and noise levels climb to a dull roar. Unfortunately, many GTX 460 cards have similar custom coolers that don’t fare well in SLI. The Radeon HD 6870’s blower is a better bet for multi-GPU use, but it’s still rather loud, especially for a single-card config. Cards that draw substantially more power are quieter and run at comparable temperatures.

Pixel fill and texturing performance

	Peak pixel fill rate (Gpixels/s)	Peak bilinear integer texel filtering rate (Gtexels/s)	Peak bilinear FP16  texel filtering rate (Gtexels/s)	Peak memory bandwidth (GB/s)
GeForce GTX 460 1GB 810MHz	25. 9	47.6	47.6	124.8
GeForce GTX 470 GC	25.0	35.0	17.5	133.9
GeForce GTX 480	33.6	42.0	21.0	177.4
GeForce GTX 580	37.1	49.4	49.4	192.0
Radeon HD 5870	27. 2	68.0	34.0	153.6
Radeon HD 6870	28.8	50.4	25.2	134.4
Radeon HD 5970	46.4	116.0	58.0	256.0

We’ve already looked at some of the theoretical peak numbers above, but we’ve reiterated them here a little more fully. These figures aren’t destiny for a video card. Different GPU architectures will deliver on their potential in different ways, with various levels of efficiency. However, these numbers do matter, especially among chips with similar architectural DNA.

You’d think 3DMark’s color fill rate test would track with the first column of scores above, but it turns out delivered performance is more directly affected by memory bandwidth. That’s why, for instance, the Radeon HD 6870 trails the 5870 here, in spite of a higher ROP rate. The GTX 580 is the fastest single-GPU solution, though it can’t keep up with the similarly priced multi-GPU options.

We’ve shunned 3DMark’s texture fill test recently because it doesn’t involve any sort of texture filtering. That’s tragic and sad, since texture filtering rates are almost certainly more important than sampling rates in the grand scheme of things. Still, this is a decent test of FP16 texture sampling rates, so we’ll use it to consider that aspect of GPU performance. Texture storage is, after all, essentially the way GPUs access memory, and unfiltered access speeds will matter to routines that store data and retrieve it without filtering.

AMD’s samplers are very fast indeed, as the Radeon HD 6870 keeps pace with Nvidia’s biggest, baddest GPU. The Radeon HD 5970 is more than twice as fast in this specific case.

Here’s a more proper test of texture filtering, although it’s focused entirely on integer texture formats, not FP16. Texture formats like these are still widely used in games.

AMD’s texture filtering hardware is generally quite a bit faster than Nvidia’s with integer formats. The deficit narrows as we move to higher quality filtering levels, but the year-old Radeon HD 5870 remains faster than the GeForce GTX 580.

Happily, after struggling in the dark for a while, we finally have a proper test of FP16 filtering rates, courtesy of the guys at Beyond3D. Nvidia says the GF104 and GF110 can filter FP16 textures are their full rates rather than half. What kind of performance can they really achieve?

The GTX 580 comes pretty darned close to its theoretical peak rate, and it’s nearly twice the speed of the Radeon HD 5870. That quite the reversal. The GeForce GTX 460 moves up the chart, too, but doesn’t come anywhere near as close as the GTX 580 to reaching its peak potential. The GTX 580’s additional memory bandwidth and larger L2 cache—50% better on both fronts—likely account for the difference in delivered performance.

Shader performance

	Peak shader arithmetic (GFLOPS)	Peak rasterization rate (Mtris/s)	Peak memory bandwidth (GB/s)
GeForce GTX 460 1GB 810MHz	1089	1620	124.8
GeForce GTX 470 GC	1120	2500	133. 9
GeForce GTX 480	1345	2800	177.4
GeForce GTX 580	1581	3088	192.0
Radeon HD 5870	2720	850	153.6
Radeon HD 6870	2016	900	134.4
Radeon HD 5970	4640	1450	256. 0

In recent months, our GPU reviews have been missing a rather important element: tests of GPU shader performance or processing power outside of actual games. Although some of today’s games use a fairly rich mix of shader effects, they also stress other parts of the GPU at the same time. We can better understand the strengths and weakeness of current GPU architectures by using some targeted shader benchmarks. The trouble is: what tests are worth using?

Fortunately, we have several answers today thanks to some new entrants. The first of those is ShaderToyMark, a pixel shader test based on six different effects taken from the nifty ShaderToy utility. The pixel shaders used are fascinating abstract effects created by demoscene participants, all of whom are credited on the ShaderToyMark homepage. Running all six of these pixel shaders simultaneously easily stresses today’s fastest GPUs, even at the benchmark’s relatively low 960×540 default resolution.

You may be looking between the peak arithmetic rates in table at the top of the page and the results above and scratching your head, but the outcome will be no surprise to those familiar with these GPU architectures. The vast SIMD arrays on AMD’s chips do indeed have higher peak theoretical rates, but their execution units can’t always be scheduled as efficiently as Nvidia’s. In this case, the GTX 580 easily outperforms the single-GPU competition. Unfortunately, this test isn’t multi-GPU compatible, so we had to leave out those configs.

Incidentally, this gives us our first good look at the shader performance differences between the Radeon HD 5870 and 6870. The 6870 is based on the smaller Barts GPU and performs nearly as well as the 5870 in many games, but it is measurably slower in directed tests, as one might expect.

Up next is a compute shader benchmark built into Civilization V. This test measures the GPU’s ability to decompress textures used for the graphically detailed leader characters depicted in the game. The decompression routine is based on a DirectX 11 compute shader. The benchmark reports individual results for a long list of leaders; we’ve averaged those scores to give you the results you see below.

These results largely mirror what we saw above in terms of relative performance, with the added spice of multi-GPU outcomes. Strangely, the Radeon HD 5970 stumbles a bit here.

Finally, we have the shader tests from 3DMark Vantage.

Clockwise from top left: Parallax occlusion mapping, Perlin noise,

GPU cloth, and GPU particles

These first two tests use pixel shaders to do their work, and the Radeons fare relatively well in both. The Perlin noise test, in particular, is very math intensive, and this looks to be a case in which the Radeons’ stratospheric peak arithmetic rates actually pay off.

These two tests involve simulations of physical phenomena using vertex shaders and the DirectX 10-style stream output capabilities of the GPUs. In both cases, the GeForces are substantially faster, with the GTX 580 again at the top of the heap.

Geometry processing throughput

The most obvious area of divergence between the current GPU architectures from AMD and Nvidia is geometry processing, which has become a point of emphasis with the advent of DirectX 11’s tessellation feature. Both GPU brands support tessellation, which allows for much higher geometric detail than usual to be generated and processed on the GPU. The extent of that support is the hot-button issue. With Fermi, Nvidia built the first truly parallel architecture for geometry processing, taking one of the last portions of the graphics pipeline that was processed serially and distributing it across multiple hardware units. AMD took a more traditional, serial approach with less peak throughput.

We can measure geometry processing speeds pretty straightforwardly with a couple of tools. The first is the Unigine Heaven demo. This demo doesn’t really make good use of additional polygons to increase image quality at its highest tessellation levels, but it does push enough polys to serve as a decent synthetic benchmark.

Notice that the multi-GPU solutions scale nicely in terms of geometry processing power; the alternate-frame rendering method most commonly used for load balancing between GPUs offers nearly perfect scaling on this front. Even so, the GTX 580 is still roughly a third faster than the Radeon HD 5970. Among the AMD solutions, only the dual Radeon HD 6870s can challenge the GTX 580 here, in part because of some tessellation optimizations AMD put into the Barts GPU.

TessMark’s multiple tessellation levels give us the chance to push the envelope even further, down to, well, insanely small polygons, and past the Radeons’ breaking point. This vast difference in performance once polygon counts get to a certain level will help inform our understanding of some important issues ahead. We can already see how Nvidia’s architectural choices have given the GTX 580 a distinct advantage on this front.

HAWX 2

Now we enter into disputed territory, and in doing so, we put some of those architectural differences we’ve discussed into play. The developers of HAWX 2 have made extensive use of DirectX 11 tessellation for the terrain in this brand-new game, and they’ve built a GPU benchmark tool based on the game, as well. HAWX 2 is slated for release this coming Friday, and in advance of that, Nvidia provided us with a stand-alone copy of the benchmark tool. We like to test with new games that take advantage of the latest features, but we’ve been hearing strong objections to the use of this game—from none other than AMD. Here’s AMD’s statement on the matter, first released prior to the introduction of the Radeon HD 6800 series and then sent out to us again yesterday:

It has come to our attention that you may have received an early build of a benchmark based on the upcoming Ubisoft title H.A.W.X. 2. I’m sure you are fully aware that the timing of this benchmark is not coincidental and is an attempt by our competitor to negatively influence your reviews of the AMD Radeon HD 6800 series products. We suggest you do not use this benchmark at present as it has known issues with its implementation of DirectX 11 tessellation and does not serve as a useful indicator of performance for the AMD Radeon HD 6800 series. A quick comparison of the performance data in H.A.W.X. 2, with tessellation on, and that of other games/benchmarks will demonstrate how unrepresentative H.A.W.X. 2 performance is of real world performance.

AMD has demonstrated to Ubisoft tessellation performance improvements that benefit all GPUs, but the developer has chosen not to implement them in the preview benchmark. For that reason, we are working on a driver-based solution in time for the final release of the game that improves performance without sacrificing image quality. In the meantime we recommend you hold off using the benchmark as it will not provide a useful measure of performance relative to other DirectX 11 games using tessellation.

Interesting, no? I don’t need to tell you that Nvidia objects. With six days to produce our Radeon HD 6800 series review, we simply didn’t have time to look at HAWX 2 back then. I’m not sure we can come up with a definitive answer about who’s right, because that would require more knowledge about the way future games will use tessellation—and we won’t know that until, you know, later. But we can explore some of the issues briefly.

Without tessellation, the mountains’ silhouettes are simple and straight

With tessellation, they’re much more complex

First, above is a close-up look at the impact of HAWX 2‘s tessellation on some of the mountains over which the entire benchmark scene takes place. This is just a small portion of a higher-resolution screen capture that hasn’t been resized. Clearly, tessellation adds tremendous complexity to the shape of the mountains.

Click the image for a larger version

Above are some images, provided by Nvidia, that reveal the sort of geometric complexity involved in this scene. The lower shot, in wireframe mode, gives us a sense of the polygon sizes. Unfortunately, these images were obviously resized by Nvidia before they came to us, so we can’t really estimate the number of pixels per polygon by looking at them. Still, we have a clear sense that many, many polygons are in use—more than most of today’s games.

Is this an egregious overuse of polygons, as AMD contends? I’m not sure, but I’d say it’s less than optimal, for a few reasons. One oddity is demonstrated, albeit poorly, in the image on the right. Although everything is turned at a nearly 45° angle, what you’re seeing at the center of the picture is something important: essentially flat ground. That flat surface is covered with large number of polygons, all finely subdivided into a complex mesh. A really good dynamic tessellation algorithm wouldn’t find any reason to subdivide a flat area into so many triangles. We’ve seen such routines in operation before, or we wouldn’t know to point this out. And there’s a fair amount of flat ground in the HAWX 2 benchmark map, as shown between the mountains in the image below.

Click the image for the full-sized version

The scene above shows us another potential issue, too, which is especially apparent in the full-resolution screenshot: the silhouettes of the mountains off in the distance appear to be just as jagged and complex as those up close, yet the texture resolution on those distant peaks is greatly reduced. Now, there are reasons to do things this way—including, notably, the way light behaves as it’s being filtered through the atmosphere—but a more conventional choice would be to use dynamic LOD to reduce both the texture resolution and geometric complexity of the far-away peaks.

Finally, although close-up mountains in HAWX 2 look amazing and darn-near photorealistic, very little effort has been spent on the hostile airplanes in the sky. The models have very low poly counts, with obvious polygon edges visible. The lighting is dead simple, and the surfaces look flat and dull. Again, that’s an odd choice.

For its part, Nvidia freely acknowledged the validity of some of our criticisms claimed the game’s developers had the final say on what went into it. Ubisoft, they said, took some suggestions from both AMD and Nvidia, but refused some suggestions from them both.

On the key issue of whether the polygon counts are excessive, Nvidia contends Ubisoft didn’t sabotage its game’s performance on Radeon hardware. Instead, the developers set their polygon budget to allow playable frame rates on AMD GPUs. In fact, Nvidia estimates HAWX 2 with tessellation averages about 18 pixels per polygon. Interestingly, that’s just above the 16 pixel/polygon limit that AMD Graphics CTO Eric Demers argued, at the Radeon HD 6800 series press day, is the smallest optimal polygon size on any conventional, quad-based GPU architecture.

With all of these considerations in mind, let’s have a look at HAWX 2 performance with DX11 terrain tessellation enabled.

Having seen these tests run, I’d say we’re getting fluid enough frame rates out of all of the cards to keep the game playable. The GeForces are much faster, though, which you might have guessed.

We don’t have any great lessons to draw from all of this controversy, but we hope you understand the issues a little better, at least. We expect to see more skirmishes of this type in the future, especially if AMD’s Cayman GPU doesn’t move decidedly in the direction of higher polygon throughput. We’re also curious to see exactly how AMD addresses this one via its promised “driver-based solution” and whether or not that solution alters the game’s image quality.

Lost Planet 2

Our next stop is another game with a built-in benchmark that makes extensive use of tessellation, believe it or not. We figured this and HAWX 2 would make a nice bridge from our synthetic tessellation benchmark and the rest of our game tests. This one isn’t quite so controversial, thank goodness.

Without tessellation

Without tessellation

With tessellation

With tessellation

Here’s a quick look at the subject of this benchmark, a big, slimy slug/tank character from the game. Like a lot of other current games, LP2 has its DX11 effects tacked on in a few places, mostly in the level-end boss characters like this one. Tessellation adds some detail to the slug thing, mostly apparent in the silhouette of the its tail and its, uh, knees. Whatever they’re doing here works, because wow, that thing is creepy looking. I just don’t understand why the guts don’t ooze out immediately when the guys shoot it.

This benchmark emphasizes the game’s DX11 effects, as the camera spends nearly all of its time locked onto the tessellated giant slug. We tested at two different tessellation levels to see whether it made any notable difference in performance. The difference in image quality between the two is, well, subtle.

The Radeons don’t fare too poorly here, all things considered. The only solution that’s faster than the GeForce GTX 580 is a pair of 6870s in CrossFire, in fact. Unfortunately, the low clock speeds on the 5970’s individual GPUs keep it from performing as well as the 6870s in geometry-limited scenarios.

Civilization V

In addition to the compute shader test we’ve already covered, Civ V has several other built-in benchmarking modes, including two we think are useful for testing video cards. One of them concentrates on the world leaders presented in the game, which is interesting because the game’s developers have spent quite a bit of effort on generating very high quality images in those scenes, complete with some rather convincing material shaders to accent the hair, clothes, and skin of the characters. This benchmark isn’t necessarily representative of Civ V‘s core gameplay, but it does measure performance in one of the most graphically striking parts of the game. As with the earlier compute shader test, we chose to average the results from the individual leaders.

The Radeons pretty much clean up here, quite possibly due to their pixel shading prowess. The GTX 580 only manages to match the Radeon HD 5870.

Another benchmark in Civ V focuses, rightly, on the most taxing part of the core gameplay, when you’re deep into a map and have hundreds of units and structures populating the space. This is when an underpowered GPU can slow down and cause the game to run poorly. Unfortunately, this test doesn’t present its results in terms of frames per second. We can use the scores it produces to compare between video cards, but we can’t really tell whether performance will be competent based on these numbers alone. For what it’s worth, I’m pretty confident most of these cards are capable of producing tolerable frame rates at this very high resolution with 8X multisampling.

In this measure of actual gameplay performance, the GTX 580 comes in just behind the Radeon HD 5970. The only single-GPU solution that comes close is the GTX 480, and it’s more than 10% slower than the 580.

StarCraft II

Up next is a little game you may have heard of called StarCraft II. We tested SC2 by playing back a match from a recent tournament using the game’s replay feature. This particular match was about 10 minutes in duration, and we captured frame rates over that time using the Fraps utility. Thanks to the relatively long time window involved, we decided not to repeat this test multiple times, like we usually do when testing games with Fraps.

We tested at the settings shown above, with the notable exception that we also enabled 4X antialiasing via these cards’ respective driver control panels. SC2 doesn’t support AA natively, but we think this class of card can produce playable frame rates with AA enabled—and the game looks better that way.

Once more, the GTX 580 is the fastest single-GPU solution, but it can’t quite catch the dual 6870s or GTX 460s. The Radeon HD 5970 struggles yet again, oddly enough, while the 6870 CrossFireX config performs quite well.

Battlefield: Bad Company 2
BC2 uses DirectX 11, but according to this interview, DX11 is mainly used to speed up soft shadow filtering. The DirectX 10 rendering path produces the same images.

We turned up nearly all of the image quality settings in the game. Our test sessions took place in the first 60 seconds of the “Heart of Darkness” level.

The GTX 480 is in a virtual tie with the Radeon HD 5870, and the GTX 580 breaks that deadlock. Still, all of the dual-GPU solutions are faster, including the Radeon HD 5970.

Metro 2033

This time around, we decided to test Metro 2033 at multiple image quality levels rather than multiple resolutions, because there’s quite a bit of opportunity to burden these GPUs simply using this game’s more complex shader effects. We used three different quality presets built into the game’s benchmark utility, with the performance-destroying advanced depth-of-field shader disabled and tessellation enabled in each case.

Interestingly, the Radeons grow relatively stronger as the complexity of the shader effects rises. By the time we reach the highest quality settings, the 5970 has matched the GTX 580—and the dual 6870s are faster still.

Aliens vs. Predator
AvP uses several DirectX 11 features to improve image quality and performance, including tessellation, advanced shadow sampling, and DX11-enhanced multisampled anti-aliasing. Naturally, we were pleased when the game’s developers put together an easily scriptable benchmark tool. This benchmark cycles through a range of scenes in the game, including one spot where a horde of tessellated aliens comes crawling down the floor, ceiling, and walls of a corridor.

For these tests, we turned up all of the image quality options to the max, with two exceptions. We held the line at 2X antialiasing and 8X anisotropic filtering simply to keep frame rates in a playable range with most of these graphics cards.

Once more, the GTX 580 is the fastest single-GPU solution, supplanting the GTX 480 while solidly improving on its performance.

DiRT 2: DX9

This excellent racer packs a scriptable performance test. We tested at DiRT 2‘s “ultra” quality presets in both DirectX 9 and Direct X 11. The big difference between the two is that the DX11 mode includes tessellation on the crowd and water. Otherwise, they’re hardly distinguishable.

DiRT 2: DX11

When DiRT 2 is at its most strenuous, in the last few graphs above, the GTX 580 handily outperforms the GTX 480. This is one of the games where Nvidia says the GF110’s architectural enhancements, particularly the faster FP16 filtering, pay off.

Conclusions

On the whole, the GeForce GTX 580 delivers on much of what it promises. Power draw is reduced versus the GTX 480, at least at idle, and the card runs cooler while generating less noise than its predecessor. Performance is up substantially, between about 10 and 20%, depending on the application, which is more than enough to cement the GTX 580’s position as the fastest single-GPU graphics card on the planet.

We said earlier that the GTX 580’s competitive picture is a bit murky, but our test results have provided some additional clarity. The Radeon HD 5970 is faster than the GTX 580 across most games we tested, but we still don’t like its value proposition for several reasons. One of those reasons is the 5970’s relatively weak performance with high degrees of tessellation, a consequence of its low default clock speeds. The 5970 is also a very long card and relatively noisy.

Most of all, though, we simply prefer the option of grabbing a pair of Radeon HD 6870s. The 6870 CrossFireX setup was easily the best overall performer of any solution we tested across our suite of games. If you’re willing to live with the multi-GPU compatibility issues of the 5970, you might as well step up to two discrete cards for the same price. Heck, even though the 6870’s cooler isn’t very quiet, the dual 6870 config generated less noise under load than the 5970. We’re also much more comfortable with running two 6870s sandwiched together than we are with two of any flavor of GeForce GTX 460 we’ve yet seen. The custom coolers on various GTX 460 cards are often fine for single-card setups, but they mostly don’t play well with SLI.

With that said, we don’t entirely consider any current multi-card solution a truly direct competitor for the GeForce GTX 580. For one thing, the GTX 580 would make a heckuva building block for an SLI setup itself, and that would be one very powerful solution, likely with decent acoustics, too. (Note to self: test ASAP.) For another, we know that AMD’s Cayman GPU is coming very soon, and it should present more formidable competition for Nvidia’s new hotness.

In fact, we don’t yet have enough information to evaluate the GTX 580 properly just yet. This card is a nice advancement over the GTX 480, but is it improved enough to hold off Cayman? If the rumors are true, we may know the answer before the month is out.

Nvidia GTX 580 Overclocking Guide

Every time a new graphics card comes out, especially one based on a new architecture such as Nvidia’s GTX 580, early adopters and overclockers alike have to get over all sort of problems if they want to squeeze the maximum performance possible out of their brand spanking new GPU, so we are going t make this whole process a lot easier for all those of you GTX 580 owners out there that find themselves stuck in such a situation.

All the info that is shared in this article comes from Softpedia’s own experiments with the GTX 580, Nvidia’s graphics card making its way into our test labs just a few days ago.

For now we are going to limit ourselves to this overclocking tutorial as more info about the GTX 580 architecture as well as its performances will be covered in our review, that is bound to hit real soon.

But getting back to the matter at hand, the first thing that I am going to do is to take a quick look at the card’s default clocks to see where we stand.

As you can certainly see for yourself the GTX 580’s default core clock is set at 772MHz, its memory being clocked at 1002MHz (4008MHz data rate) while the shader clock runs at 1544MHz, being set at double the core’s frequency, as its the case with all Fermi based video cards.

As in the GF100, this can’t be altered by itself, so overclocking these cards is a matter of changing only two frequencies as well as the core’s voltage.

And here is where we came into our first hurdle with overclocking the GTX 580, as voltage tuning utilities that support Nvidia’s new GF110 core are really scarce at this time.

As a hardware reviewer, one runs into this sort of situations all the time, limited software support being one of the main reasons why overclocking results are not covered by every single review out there, especially when we are talking about new architectures that usually come with pre-production drivers and the like.

This is what happened to us when we reviewed the GTX 580 as well, and this is where the idea about writing such an GTX 580 overclocking guide came from, as most review sites out there don’t mention what tools they used in order to overclock, leaving early adopters to search for themselves the right tool for the job.

With this in mind, we set up to bring our users a quick guide that will enable them to unlock the full potential of the GTX 580, Nvidia’s card coming with an impressive overclocking headroom for an flagship product as you will most certainly see for yourself.

Pre-requisites

Before we start, the first thing to do is to download a few free tools from the Web, our main goal being to find a way of changing the core’s voltage without resorting to hardware modes and other stuff like that, the GF110 coming with a CHiL 8266 digital PWM controller which decides just how much juice the core needs.

As its the case with many other PWM controllers used in today’s top end graphics cards this can be also controlled via software, MSI Afterburner certainly being one of the most wide known tools available to overclockers worldwide.

Unfortunately, heading over to MSI’s Afterburner website and downloading these tools gets us the 2.0 version, this coming without voltage control support for the GTX 580 as I soon found out for myself when trying to overclock the card for the upcoming review.

There’s no need to worry though, beta versions of this tool are also available and usually come with support for the latest graphics cards out there.

Right now, the latest beta version is Afterburner 2.1 Beta 4, GTX 580 support making its way in the change log.

Another utility that supports the GTX 580 is Nvidia Inspector tool, this utility looking a lot like GPU-Z although it also comes with a really thorough overclocking panel, this being available for download from our website.

I recommend installing both of these tools and see what works best for you, Nvidia Inspector being also a really good alternative to GPU-Z, so you are really hitting two rabbits with one stone by going with this software.

The last tool that you need in your arsenal before getting to see what your GTX 580 is made off is the FurMark stress testing utility, available for download here.

Now that we got a hold of everything we need in order to overclock the GTX 580, its time for a small disclaimer as you need to understand Softpedia can’t be held reliable for what happens to your video card is anything goes wrong.

Furthermore, we do not encourage overclocking if you don’t know what you are doing, so please make sure you understand all the risks involved before getting started.

Another thing that I need to mention is this guide should also work for overclocking other Nvidia video cards, such as the GTX 480 and other Fermi based cards.

The overclocking process

I’ll assume that, by now, you have downloaded and installed all the utilities mentioned in the pre-requisite section, so we are going to get right into the action.

First thing to do now is to unlock voltage control and monitoring in MSI’s Afterburner tool by heading to the Settings tab found in the bottom right corner of the program’s main panel, the two check boxes needed being right under the General tab, in the Safety properties subsection, called Unlock Voltage Control and Unlock Voltage Monitoring, as you can see in the enclosed picture.

After clicking the OK button, you will get a message informing you these changes will be applied after restarting MSI’s utility, so do as informed.

After restarting the utility, check the Core Voltage slider found at the top of the main Afterburner panel, to see if this worked.

If it didn’t, there is another thing you can try as Afterburner saves all its settings in an config file that is found in the installation directory, called MSIAfterburner.cfg, the values that we are interested in being found in the [Settings] section, as UnlockVoltageControl and UnlockVoltageMonitoring.

Change both of these values to 1 and you are all set to go.

After saving the settings and starting Afterburner the Voltage Control slider should be unlocked.

If this is still not the case, you can resort to the Nvidia Inspector tool, this also allowing core voltage to be changed, although the GPU frequency slider was not available to me (if this were to be enabled you can pretty much give up on using Afterburner as this can do exactly the same things as MSI’s tool).

If this still doesn’t work or if, for whatever reason, you don’t want to change the GPU’s voltage, the GTX 580 can also be overclocked without a voltage increase, but you mileage may vary since the core’s frequency will most certainly be limited by the 1. 035V supplied to the GF110 core.

If you don’t seem to find the overclocking panel in Nvidia Inspector that is because there is a Show Overclocking/Hide Overclocking button that needs to be pressed in order to gain access to them.

For whatever reason, during my experiments, Nvidia Inspector and MSI Afterburner had different maximum voltages available, MSI’s tool featuring a whooping 1.3V, although every report out there, as well as Nvidia Inspector, said 1.138V is the maximum core voltage available through software for thr GTX 580.

A few more experiments showed this is indeed the case as raising the voltage over 1.138V in Afterburner had no result on the overclock achieved, Nvidia Inspector also reporting the voltage is set to 1.138V, so it’s safe to assume this is a bug that report the maximum available voltage wrong.

But moving past all that, with two overclocking tools at our disposal it’s time to crank the voltage all the way up to 1.138V and see where this takes us in terms of performance.

To find the maximum overclocking values for the graphics card, start by gradually increasing the core’s frequency (I recommend 25MHz increments if you are an overclocking noob).

After each increase fire up the FurMark stress testing program (I used MSI’s Kombustor utility but it’s basically the same thing as Kombustor is a redesigned FurMark), by just pressing the big GO! Button, the default settings being OK for testing the card’s stability.

I recommend doing this for about half an hour and if everything works well raise the core frequency once again.

You need to repeat these steps until you get artefacts in the rendered image, until Nvidia’s driver crashes or the computer freezes.

When this happens, don’t worry, as this simply means that you have gone too far and you need to take a slight step back.

Restart you computer and fire Nvidia Inspector and MSI Afterburner again, following the same steps as before, but when it comes to setting the core frequency go 10MHz lower than your last attempt and start FurMark yet again to see how things work out know.

If everything goes well for half an hour this means that you have come pretty close to your GTX 580 maximum core frequency (you can further fine tune it if you want), but if it doesn’t decrease the frequency yet again until you find the right value for you.

Now that you found the maximum frequency for your GPU is time to see what the memory chips hold in store, so repeat the whole process yet again, although this time increase your memory frequency instead of the core’s clock.

In my experiments, I managed to hit an impressive 920MHz for the core and 2100MHz for the memory, although I had to give up on raising the memory frequency further because of the limited time that I had at my disposal for this article, but if you have the time, I am sure these can go a lot higher, although is up to you to find just how high they can actually go.

End of it all, this speed increase got me a 10.4% increase in the overall 3DMark Vantage Performance score, a pretty nice boost for the small amount of work involved.

During this whole time, the fan was set to the auto setting, Nvidia’s GTX 580 cooling system being particularly efficient throughout my tests, although the system got pretty noise at times.

This is however a normal thing to happen since it had to blow out an increased amount of heat, the fan reving up just for a few seconds once in a while, quickly returning to its regular ear-friendly ways, something that we’ll cover in more detail in our upcoming review.

Until then I’ll leave you explore your GTX’s 580 overclocking potential, so please drop me a line and let my know how things worked out for you.

could have been better than GECID.com. Page 1

::>Video cards
>2019
> Gameplay testing of the NVIDIA GeForce GTX 580 video card in the realities of 2019: it could be better

09-05-2019

Page 1
Page 2
One page

In March 2010, the GeForce GTX 480 video card debuted, and in November it was replaced by the GeForce GTX 580. There were both external and internal reasons for such a rush. The first ones include the release of a worthy competitive Radeon HD 6800 series. But the main ones were internal problems — high power consumption and heat dissipation of the GTX 480, frequent breakdowns and a low percentage of good chips produced. Initially, the NVIDIA GF100 GPU was supposed to include all 16 SM blocks, but the company decided to lower the bar to 15 in order to sell more GPUs.

In turn, the GeForce GTX 580 received a modified GF110 chip with a full number of SM blocks, CUDA cores and texture modules. It uses the same Fermi microarchitecture, but with minor improvements that along the way made it possible to increase clock speeds by 8-10% and even slightly reduce power consumption. This had a positive effect on the overall level of performance, but the novelty did not bring any radically new technologies. The size of the video buffer at first also did not change, although later 3-gigabyte versions appeared.

We will evaluate the capabilities of this flagship using the MSI GeForce GTX 580 Lightning as an example. At one time we prepared a text review on it, but it did not stay with us. Therefore, we turned to colleagues from the Overclockers.ua website, who kindly provided it to us for testing.

This is the top version, which was also created for overclocking experiments. Therefore, she received a 16-phase power subsystem, overclocking tools for extreme overclocking, an improved element base and an efficient Twin Frozr III cooler. It consists of a massive base, three nickel-plated copper heat pipes, an aluminum heatsink, and two 90mm fans. In games, the GPU temperature did not exceed 63 ° with a critical indicator of 97 ° C.

The first surprise upon reacquaintance was waiting for us in the GPU-Z utility. At first glance, everything is fine: the GPU frequency is 8% higher than the standard, and the memory is 5% higher. But if you look closely, the program indicates the use of 8 PCIe 2. 0 lanes. They checked it on several test systems, but they did not see the required 16 lines.

This may be a GPU-Z glitch. But there was no time or desire to look for another GeForce GTX 580. And according to tests available online, the difference in performance between 8 and 16 lines is only a few percent. Therefore, even if the video card really works in x8 mode, then factory overclocking is enough to cover the difference. Thus, we can assume that we have a reference model on the test.

At one time, the MSI GeForce GTX 580 Lightning outperformed the overclocked GeForce GTX 480 by 10-18%. Let’s see if anything has changed since then and if the possible x8 mode had a big impact?

Rainbow Six: Siege with the medium preset in HD shows that there were no significant changes: the 580th is still 15-18% better than its predecessor. But, of course, it is impossible to judge by one benchmark, so let’s move on to the next one.

In Middle-earth: Shadow of War , the advantage of the GeForce GTX 580 reaches 25-28%. Here, the superiority of the GF110 over the GF100 in terms of the number of structural blocks and clock frequencies is already fully felt.

In The Crew 2 the advantage of the 580th is retained, but it is at the lowest level — 9-11%.

And finally in Far Cry 5 at a low preset, the 480th absolutely could not oppose its successor. Both suffered from a lack of video memory, but the performance of the GTX 580 was 16-20% higher.

Thus, even if this is not a GPU-Z glitch and the video card really worked in x8 mode, it is still 17-18% better than the GeForce GTX 480. Similar results were obtained in 2010, so we can safely move on to familiarization with the test stand and the main game testing.

The following stand was used for testing:

• Intel Core i7-7740X
• Thermaltake Water 3. 0 Riing RGB 240
• ASUS TUF X299 MARK 1
• 2 x 8 GB DDR4-2133 G.SKILL Sniper X
• Apacer PANTHER AS330 240 GB / 960 GB
• Seagate ST2000DX001 2TB
• Seasonic Snow Silent 1050 1050W
• Thermaltake Core P3
• AOC U2879VF

An external system with AVerMedia Live Gamer 4K was used to record gameplay in Full HD resolution, i.e. without loss of performance.

Traditionally, before the main test of a retro video card, we check how it is doing with driver support. The GTX 580 belongs to the Fermi family, so the latest WHQL driver for it was released in March 2018. As for the GeForce GTX 480.

Therefore, almost all the problems that were in the test of its predecessor have been preserved. That is, Battlefied V refused to launch at all, Forza Horizon 4 hurriedly crashed on Windows, there is no support for Vulkan at all, and Quake Champions just issued a warning, but still started. The only difference is that Fallout 4 immediately recognized the graphics card and offered medium graphics settings.

Otherwise there were no problems. This time, just over 20 games take part in the test. To save time, we decided not to launch the simplest ones, such as DOTA 2, Rocket League, Crossout and others. They started without problems on the 480th, so they would have gone with a bang here. And if you want to know their approximate frame rate, then add 16% to past results.

ZOTAC GeForce GTX 580 review and testing GECID.com. Page 1

::>Video cards
>2010
> ZOTAC ZT-50101-10P

11-17-2010

Page 1
Page 2
One page

Not so long ago we tested new models of video cards based on the improved Barts core manufactured by AMD. The Radeon HD 6870 and Radeon HD 6850 graphics processors are representatives of the middle price range of the new 6800 series, but the NVIDIA GeForce GTX 580 is positioned as the most productive single-chip solution. We will try to confirm or refute these lofty «claims» by conducting our own testing of the capabilities of the new video accelerator.

Video cards based on the GPU of the previous series NVIDIA GeForce GTX 480 were the best in performance among single-chip solutions for half a year. Such superiority of NVIDIA’s product over AMD’s Radeon HD 5870 could not be called absolute. In many applications, and especially in scenes requiring processing speed of tessellation algorithms, NVIDIA GeForce GTX 480 really was the leader. However, other parameters, such as power consumption, heat dissipation, price and noise of the video cards based on the NVIDIA GeForce GTX 480 were seriously inferior to the «top» solution Radeon HD 5870 from AMD. It is precisely because of the high power consumption that NVIDIA specialists have not yet been able to release a two-chip video card based on their «top» core based on the Fermi architecture. AMD engineers, having selected crystals with the lowest possible supply voltage, and therefore with minimal power consumption and heat pack, offered the public a dual-chip video card Radeon HD 5970. Even now it can still be called the most productive graphics accelerator.

The two main problems faced by NVIDIA engineers when releasing the GeForce GTX 480 chip are its high power consumption and low percentage of good chips in production. We will not single out one of these reasons as the main one, but as a result, users received a GeForce GTX 480 with an inferior core of the Fermi architecture. One of the 16 streaming multiprocessors (SM — Streaming Multiprocessors) in it was disabled at the factory. Such a move made it possible to increase the percentage of workable, but cut-down chips for GeForce GTX 480 video cards, and it also gave somewhat lower power consumption and reduced chip heating. Even with this cutback, the GeForce GTX 480 delivers performance that, in the vast majority of applications, outperforms its main competitor from AMD, the Radeon HD 5870 accelerator.

Now, after the release of the first accelerators of the new Radeon HD 6800 line and the imminent appearance of the «top» video cards of this series on the «Cayman» core and the two-chip «Antilles» solution, NVIDIA has dealt a preemptive blow to AMD by introducing an even more powerful GeForce solution to the market. GTX 580. In fact, with a few exceptions, the GeForce GTX 580 video card is a modified and improved version of the GeForce GTX 480. It has a full set of streaming multiprocessors (16 pieces), a slightly reduced heat pack and power consumption against the background of increased operating frequencies. This combination of features gives a significant superiority of the new GeForce GTX 580 over its predecessor.

The conquest of the market of «top» solutions by NVIDIA strongly depends on the pricing of products in this niche from AMD’s direct competitor. The GeForce GTX 580 video card is offered for sale at a price of $500, while the cost of the «top» accelerator from AMD Radeon HD 5870 has already dropped to $330. If we talk about our market, then prices can be roughly predicted: AMD Radeon HD 5870 sells for $380 on average, GeForce GTX 580 is expected to cost $600 and AMD Radeon HD 5970 sells for $650 on average. The price ladder is quite consistent with the performance of these video cards and their capabilities.

NVIDIA’s new GF110 core architecture for the GeForce GTX 580

It has already been said that the GF110 has become an improved modification of the GF100, and the number of changes is quite insignificant. Learn more about the architecture of the GeForce GTX 480 in the review of the ZOTAC GeForce GTX 480 video card. The die of both video cards has a 40-nm manufacturing process and contains more than 3 billion transistors.

The main goal in the changes to the GeForce GTX 580 die was to increase its total performance and computing power. Only two features of the core were redesigned — the FP16 filtering speed was doubled and the performance in the Z-cull invisible surface rejection algorithms was increased (new tile formats were introduced).

The GF110 GPU was able to filter the FP16 texture in one cycle, while its predecessor GF100 did it in two cycles. This will give a good boost in applications that are demanding on the texture performance of the accelerator.

The performance gain in hidden object culling will give the GF110 a better performance in overdraw applications and add efficiency to the available video accelerator memory bandwidth. According to NVIDIA, these two improvements will give a total increase in performance per clock, on average, up to 14%.

The desire to achieve better energy efficiency indicators from the redesigned GF110 chip and increase the yield of working crystals during their production, forced the chip developers to make changes to the new core at the chip level. Various types of transistors were used in the design of the integrated circuit. In places less demanding on performance, transistors with low leakage currents, but with a greater delay, were used, and in other places with increased demands on performance, transistors with high leakage currents, but with increased speed. It was these changes that led to very significant power savings, which made it possible for NVIDIA to increase the core clock speeds by 72 MHz and enable the 16th SM streaming multiprocessor, which was disabled in the GF100 core used in the original GeForce GTX 480 design. One streaming multiprocessor carries 32 CUDA cores, four texture units and one PolyMorph geometry engine, all of which are available in the new edition of the core based on the Fermi design. If we compare the frequency formula of the GeForce GTX 480 (700/ 1401/ 924 MHz) with the GeForce GTX 580, then the latter has raised: the core frequency to 772 MHz, the shader frequency to 1544 MHz and the memory frequency to 1002 MHz, which is an effective frequency of 4008 MHz. Also GF110 now has 512 functional CUDA cores, 64 texture units and 16 PolyMorph engines.

The rest of the core content remained unchanged. There are six Raster Operation Sections (ROPs), each with a 64-bit memory bus, for a total of 384-bit memory bus. Each section computes eight 32-bit integer pixels per clock, for a total of 48 pixels per clock.

After describing the theoretical capabilities of the new GF110 core, let’s move on to the practical part of our review, describe the video card from ZOTAC based on the GeForce GTX 580 video processor that got into our laboratory. GeForce GTX 580 (ZT-50101-10P), presented on the manufacturer’s website:

According to the data in the table, you can see that there are not many differences between the reference solution ZOTAC GeForce GTX 480 and ZOTAC GeForce GTX 580. As already noted, the operating frequencies of the accelerator were changed, the number of stream pipelines became 512, the video card received support for OpenGL 4.1, and its critical operating temperature dropped to 97 °C. The dimensions of the board itself, the rear panel connectors, and the minimum power supply required for this accelerator to operate remain exactly the same as for the GeForce GTX 480. Note that the ZOTAC GeForce GTX 580 video card supports additional NVIDIA PureVideo HD Technology, NVIDIA 3D Vision Surround, NVIDIA PhysX technologies Technology, NVIDIA CUDA Technology and NVIDIA SLI Technology.

We have received a serial ZOTAC GeForce GTX 580 video card with a simple and typical box design for this manufacturer.

The packaging of the video card is black and yellow. On the front side of the cardboard box, the model of the video card, the amount of memory, its type and the bandwidth of the memory bus are indicated. There are also mentions of support for NVIDIA PhysX proprietary technologies and the presence of an HDMI connector. In the upper right corner, the manufacturer draws attention to the support of proprietary technologies: NVIDIA GeForce CUDA, NVIDIA PureVideo HD, NVIDIA SLI.

On the back of the box is a small overview of the capabilities of this video card. The advantages of using technologies are described: NVIDIA 3D Vision Surround and PhysX.

Filling of polygraphy is quite informative, the buyer can immediately learn about all the advantages and characteristics of the product he is purchasing.

The video card itself and additional delivery components are located inside. Together with the graphics accelerator, you can get the following:

• User’s manual;

• CD with software and drivers;

• Disc with licensed version of Prince of Persia: The Forgotten Sands;

• A sticker explaining how to power up the video card and warning about the accelerator getting too hot under load;

• Video card power adapter from two 6-pin connectors to one eight-pin PCI Express;

• Video card power adapter from two MOLEX connectors to one six-pin PCI Express;

• DVI to VGA adapter;

• Mini-HDMI to HDMI adapter.

I was a bit puzzled by the sticker with a warning about the hot surface of the video card at the time of its intensive use. It was exactly the same in the GeForce GTX 480 package, but the design of the cooling system of the latter did not cover most of the radiator with a plastic casing, on the surface of which you could really get burned. In the GeForce GTX 580, almost everything is covered with plastic, which protects the user from unpleasant moments of using the accelerator. I would like to note that the power adapters included in the package indicate the need to use a sufficiently powerful power supply, as it was said in the specification of at least 600 watts. This may cause some problems when choosing a configuration. In general, the equipment should fully compensate for all the nuances of installing this video card in a modern system unit.

The ZOTAC GeForce GTX 580 video card itself is made on a dark textolite, the front side of which is closed by a cooling system with a dark plastic casing.

The GeForce GTX 580 graphics card uses a printed circuit board of exactly the same overall dimensions as the GeForce GTX 480 — its length is 267 mm (10.5″), that is, about a centimeter shorter than the accelerators on the Radeon HD 5870, this can help it fit in almost any modern cabinet

Additional power (in addition to the PCI Express bus) requires one 6-pin and one 8-pin plug. NVIDIA claims that this card has a TDP of 244W, which is slightly less than its predecessor GeForce GTX 480 and significantly less than the Radeon HD 5970, which barely fits the PCI-SIG group’s 300W ceiling. Therefore, for the «top» solution, NVIDIA recommends a 600W power supply or higher. Also in the image above you can see two SLI ports. This will allow you to combine several similar video cards into one subsystem.

On the reverse side of the printed circuit board of the video card there is a GPU power system chip — a CHiL Semiconductor CHL8266 PWM controller using six phases. A similar one was used on the GeForce GTX 480 accelerator board.

There are three transistors for each power phase (one in the upper arm and two in the lower one). This approach allows you to better remove heat from the elements of the power subsystem.

The memory is powered by 1+1 phases (1 phase Vdd + 1 phase Vddq), controlled by Anpec APW7088 controller. In the GeForce GTX 580 graphics card, one dual-channel controller controls two video memory voltages Vdd and Vddq. Thus, in total we get a 6 + 2-phase power system for the ZOTAC GeForce GTX 580 video card.

We were a bit surprised by the use of hex star screws to secure the internal aluminum shroud of the graphics card. At the same time, the radiator itself and the plastic outer casing are fastened with ordinary screws for a Phillips screwdriver. Most likely, this was done as an additional protection against removal of the inner casing, which often sits quite firmly on the thermal interface. If it is inaccurately separated from the board, its elements can be damaged.

It is worth noting a fairly large number of tantalum capacitors used in the PCB filling. Particular attention can be paid to the four tantalum capacitors shown in the image above, they improve the GPU power scheme, as a result of which the temperature of the graphics core drops, compared to solutions based on the standard element base used in the GeForce GTX 480.

The board occupies two slots on the rear panel of the case. For a sufficiently voluminous cooling system, the user will have to free up space inside the case.

There are two DVI ports and one mini-HDMI on the interface panel. Plus, the second slot will be completely occupied by the exhaust grill, which blows heated air out of the system unit. Such a set of output interfaces, together with the adapters supplied, will give the user maximum versatility in connecting monitors and other image output devices.

The NVIDIA GeForce GTX 580 GPU installed here is marked GF110-375-A1.

The frequency scheme of the video card and other characteristics look like this: and shader domains at a frequency of 1544 MHz, respectively. Video memory received 1002 MHz real or 4008 MHz effective frequency.

The tested video card uses GDDR5 memory chips manufactured by SAMSUNG with a total capacity of 1536 MB. The K4G10325FE-HC04 marking indicates that these chips provide an access time of 0.4 ns, which corresponds to a real frequency of 1250 MHz or 5000 MHz effective and provides a significant headroom for overclocking.

Cooling system

Let’s take a closer look at the video card’s cooling system. It is completely devoid of heat pipes, which were used in the GeForce GTX 480.

The GeForce GTX 580’s new cooling design uses an evaporation chamber to effectively dissipate heat from the GPU. The heat coming from the GPU is transferred to the copper pad, which is the wall of the sealed compartment, which contains a liquid with a low boiling point. After reaching a certain temperature, the liquid changes its state of aggregation and turns into a gaseous one. Evenly distributed throughout the inner cavity of the pillow, gas molecules transfer heat to all its remote parts. From the copper cushion, heat is transferred to the aluminum radiator of the cooling system. Having lost the heat necessary for the gaseous state, the gas turns into a liquid, condensing on the walls of the pillow, and flows down through special pores in the copper walls to the starting point of evaporation. Then the cycle repeats again. The turbine-type fan installed in the cooling system drives cool air through the heated fins of the aluminum radiator and blows the heat out of the case.

From the GeForce GTX 480 cooling system, only an additional radiator plate remains here. It covers the upper part of the video card board and provides heat dissipation, through a special thermal interface, from the memory chips and transistors of the power system.

To reduce idle power consumption, the GF110 graphics chip is reduced to 50 MHz and the memory frequency to 67.5 MHz. Simultaneously with these actions, there is a decrease in the supply voltage on the GPU to 0.95 V. As a result, it turns out to significantly reduce the level of energy consumption during system inactivity. On our test bench, the power consumption of the ZOTAC GeForce GTX 580 was approximately the same as that of the ZOTAC GeForce GTX 480, i.e. at the level of 145 watts. Of course, it is logical that in terms of power consumption in idle mode, such a powerful video accelerator cannot compete with video cards of the middle or lower class. Therefore, on average, for video cards like the NVIDIA GeForce GTX 460 1GB GDDR5, the powerful NVIDIA GeForce GTX 580 loses about 20 watts.

Cooling Efficiency

At full load on the NVIDIA GeForce GTX 580, the total system power consumption was 445W. To create this stress mode, we used the OCCT GPU utility, rather than the more familiar FurMark . Since when using the latter, after half a minute, a new overload protection was observed, which was introduced by the manufacturer. As a result, system power consumption was reduced from 445W to 340W. Apparently, this technology has not yet been fully developed, since when working in a similar OCCT GPU utility, there was no reduction in power consumption.

Thanks to the unique cooling system with a vapor chamber, the temperature of the ZOTAC GeForce GTX 580 video card was reduced compared to the «reference» design video cards based on the GeForce GTX 480 chip. 100º, then on the GeForce GTX 580 the temperature rises only to 90 º, which already seems to be an achievement. Due to the fact that the efficiency of the new cooler was increased by an order of magnitude, this allowed the fan to operate at lower speeds with less noise. Despite the overall «hot temper» of the video card, the noise level of the ZOTAC GeForce GTX 580, even at maximum load, is not very high, but is in the region of average values. Moreover, in video games that load the graphics card less than the OCCT GPU stress test, the noise level can be completely described as below average. Therefore, for most gamers, the noise of the turbine of the new video card will definitely not cause inconvenience.

Related news «The author of GPU-Z found a way to disable protection against stress tests on the GeForce GTX 580» — NVIDIA WORLD

A way to warm up the video card to full using FurMark.

November 10, 2010

Fluffy bagels and cubes are now banned.

With the release of the new video card GeForce GTX 580, NVIDIA has joined AMD in the confrontation with utilities that warm up the graphics processor and the video card as a whole to the limit. According to the official statement, special chips are installed on the GeForce GTX 580 video cards that check the consumption currents along the +12 V power lines from the PCI-Express bus slot and power amplifiers. The NVIDIA driver checks the power consumption values ​​and reduces the frequencies by 50% when it detects the launch of potentially dangerous applications, in particular the FurMark and OCCT stress tests, or when a certain power consumption limit is exceeded. This protection should not affect regular games. It is the work of protection that explains the strange readings of preliminary studies of the performance of the GTX 580 in FurMark.

The feasibility of such protection raises many questions. Firstly, studies of real power consumption show that some completely “legitimate” games and applications can cause no less or even more consumption than the same FurMark, for example: PixelShader test from 3DMark 06, Crysis Warhead DX10. Secondly, simply renaming the executable file of the «harmful» program may be enough to bypass the protection in the driver, moreover, it has already been confirmed that the protection does not work for older versions of FurMark. Thirdly, such measures increase the cost of video cards (three monitoring chips + strapping, seats, PCB tracks) and create potential driver stability problems — constant work with the i2c bus can be very expensive, as the authors of third-party utilities like RivaTuner have repeatedly seen.

But what’s done is done, and with the idea of ​​stress testing cards at home, so useful for identifying manufacturing defects, as well as for finding the limits of overclocking, until you have to say goodbye. Undoubtedly, action will generate reaction, for example in the form:

• unofficial driver patches that remove protection, as was the case with SLI and PhysX;
• clever tricks in the next versions of utilities to cheat the driver;
• instructions for hardware «neutralization» of pest chips;
• increased demand for stealing NVIDIA’s internal test called MODS and integrating parts of it into utilities — the company won’t ban itself;
• the emergence of even more «deadly» methods of stress testing, for example, through the CUDA API.

We will cover the further course of the struggle between light and dark forces, and may the most worthy win!

drivermonitoringGeForce GTX 580FurMarkOCCT Perestroïkautilities

comment on similar news

Geeks3D

November 9, 2010

A new version of a small but informative utility.

New version 0.4.8 of the GPU-Z utility has the following changes:

• Added support for GeForce GTX 580, GT 420, GT440 and future variants based on GF104;
• updated formula for TMU count and scene fill rate with texturing;
• Fixed video memory frequency monitoring for AMD Radeon HD 6850 and 6870 video cards;
• Fixed CrossFire detection when using old ATI drivers;
• added siding for voltage monitoring on AMD graphics cards with non-standard VRM;
• PowerColor manufacturer detection corrected.

You can download the latest version of the program from the official site.

GeForce GTX 580GPU-Zutilities

comment on similar news

The closer the release of the GeForce GTX 580, the more information about its performance (of varying degrees of certainty) leaks to the Web. This time, a volley from four benchmarks at once.

3DMark Vantage, Extreme preset:

12871 points — quite consistent with early reports of 12700 points.

H.A.W.X. 2:

Unigine Heaven:

Here we have the promised advantage over the GeForce GTX 480.

FurMark (temperature range):

Such implausible results can mean one of two things: either NVIDIA also introduced FurMark protection in the driver / hardware, or stock cooling system outperforms the best solutions from Zalman or Thermalright.

RumorsHAWX 23DMarkUnigine HeavenGeForce GTX 580FurMark

comment on related news

Beyond3D

The new version of the GPU-Z utility, number 2.46, received support for new video cards from both AMD and NVIDIA, added support for Alder Lake Mobile integrated graphics, and made numerous fixes to the utility.

See the full list of changes below:

• Added support for AMD Radeon RX 6950 XT, RX 6750 XT, RX 6650 XT.
• Improved support for Intel ARC.
• Added support for NVIDIA GeForce RTX 2050 (GA107), NVIDIA A30.
• The updated driver no longer requires a processor with SSE2 support.
• Fixed 2022 AMD drivers are now tagged as «Crimson».
• Fixed detection of Resizable BAR on systems with AGP video cards.

  The new version of the GPU-Z utility, number 2.44, has received changes that relate to informing about the Resizable BAR technology, and also added support for a huge number of video cards, both AMD and NVIDIA.

  GPU-Z

  The list of changes in GPU-Z 2.44.0 is as follows:

  • Improved Resizable BAR detection.
  • Resizable BAR is now reported in the advanced panel.
  • GPU-Z will report «Vista 64» as operating system, not «Vista64».
  • Screenshots are now uploaded via https.
  • Added vendor definition for Vastarmor.
  • Fixed some GeForce RTX 3060 cards being labeled as LHR.
  • Updated AMD Radeon RX 6600 release date.
  • Added support for NVIDIA GeForce RTX 3050, RTX 3080 12 GB, RTX 3070 Ti Mobile, RTX 3050 Ti Mobile (GA106), RTX 2060 12 GB, GT 1010, MX550, GTX 1650 Mobile (TU117-B), RTX A2000 (GA106-B), RTX A4500, A10G, A100 80 GB PCIe, CMP170HX, CMP70HX.
  • Added support for AMD Radeon RX 6400, RX 6500 XT, RX 6300M, RX 6500M, W6300M, W6500M, W6600M.
  • Added support for Non-K Intel Alder Lake, Mobile Alder Lake, and Rocket Lake Xeon processors.

  You can download the free GPU-Z utility from our website.

  video cardsAMDNVIDIAGPU-Z utilities

  comment on related news monitoring its parameters.

  The new version of the GPU-Z utility, number 2.43, received only 5 changes, which is not surprising, since only 4 days have passed since the last release. However, the application contains not only bug fixes, but also additions to the database.

  GPU-Z

  The list of changes in GPU-Z 2.43.0 is as follows:

  • It is now possible to read the power consumption limits in NVIDIA Ampere cards for laptops in the Advanced -> NVIDIA BIOS menu.
  • Fixed a crash on startup on some older Radeon cards.
  • Fixed execution block counter for Intel Rocket Lake.
  • Fixed crash function when taking a screenshot under Windows XP. The bug first appeared in version 2.39.
  • Added support for NVIDIA Quadro RTX 3000 (TU106-B).

  You can download the free GPU-Z utility from our website.

  Rocket LakeGPUvideo cardsAMDNVIDIARadeonGPU-Zutilities

  29

  TechPowerUp website has prepared another update of its popular GPU-Z utility designed to get all available information about your video card and monitor its parameters. The update was numbered 2.42.0.

  In anticipation of the release of a new series of central processors, the release of a fresh version of the utility seems to be quite reasonable. As you might expect, it adds support for Intel Alder Lake-S CPU integrated graphics, as well as several new graphics cards from both NVIDIA and AMD.

  GPU-Z 2.42.0

  Changes in GPU-Z 2.42.0 are listed below:

  • Added support for Intel Alder Lake and Tiger Lake Server.
  • Added display for NVIDIA cards with reduced hashrate in the GPU name field, for example, «GA102 (LHR)».
  • Added support for RTX 3060 variant based on GA104.
  • Added support for detecting Resizable BAR technology in Radeon RX 5000 series cards.
  • Added «-log» command line option that sets the name of the sensor log file and starts logging after running the utility.
  • Improved read stability for EVGA iCX sensors.
  • Radeon HD 5000 Series cards will now display the ATI logo.
  • Fixed an issue where DirectX 12 support was not displayed on AMD Navi 2x cards.
  • Fixed a crash when taking a screenshot.
  • Fixed crash in render test.
  • Fixed a crash on some systems when reporting Resizable BAR.
  • Fixed memory clock reading on some AMD APUs.
  • Added Intel Tiger Lake release date.
  • Added support for NVIDIA RTX 3050 Ti Mobile (GA106), T1200 Mobile, GRID K340, GRID M30, Q12U-1.
  • Added support for AMD Radeon Pro W6800X, Barco MXRT-8700.
  • You can download the free GPU-Z utility from our website.

  Tiger LakegpuvideocardinTinvidiagpu-zulytes

  Comment similar news

  TechPowerUp

  August 10, 200929

  TECHPOWERUP Updated the GPU-Z-Z Up to Vyndi-Z, which received the support of Wind Wending Winds. WDDM 3.0 standard driver.

  In addition, the utility that gives detailed data about the video card and its modes of operation has received an expansion of the database with new video cards from both AMD and NVIDIA.

  GPU-Z 2.41.0

  Changes in GPU-Z 2.41.0 are listed below:

  • Windows 11 detection added.
  • Improved TMU prediction for unknown (future) NVIDIA GPUs.
  • Improved frequency reporting on AMD RDNA2 professional cards.
  • The installer does not add a version number to the program manager, which improves Winget support.
  • Always displays advertised Navi frequencies in the advanced panel, even if some report 0.
  • Fixed «BIOS reading not supported on this device» error on some laptops with NVIDIA dGPUs.
  • Fixed «Browse» button on ASUS ROG version with non-standard DPI settings.
  • Updated Chinese translation.
  • Fixed frequency calculation on old ATI Radeon DDR / 7200 DDR cards).
  • Added transistor count and core size to AMD Cezanne and ATI R100 & RV100.
  • Added support for AMD Radeon RX 6600 XT, Pro W6800, W6600, Radeon HD 7660G (AMD R-464L APU).
  • Added support for NVIDIA CMP 90HX, 50HX, 40HX, 30HX, T1000, T400, A100-SXM-80 GB, A10, A5000, A4000, A3000, A2000, RTX 3050 Mobile Series (GA107-B).

  You can download GPU-Z v2.41.0 on our website.

  Windows 11VideoBIOSvideo cardsAMDNVIDIAGPU-Zutilities

  0929

  The popular set of utilities for OCCT version 9.0 for stress testing has become even more convenient. It now contains a benchmark tool that allows you to test the processor in single-threaded and multi-threaded mode.

  More interestingly, OCCT separates benchmarks for different types of loads. The utility also offers downloading test results online for further comparison.

  OCCT 9.0

  OCCT 9.0 changelog includes:

  • Added benchmark for CPU and memory.
  • Added graph column in benchmark to compare results.
  • Added tools to graph column for quick situation recognition.
  • OCCT now uploads all monitoring data and system information to the database.
  • Major changes have been made to the user interface.
  • Many bug fixes.
  • Shading position corrected.
  • Added a scroll bar on the settings screen.
  • Tab change is forbidden if the test is running.
  • Updated HwInfo to version 7.05.
  • Improved parsing of motherboard characteristics.
  • «Fixed» stream mode no longer enforces stream affinity.
  • Added «—cpu-benchmarks» and «—memory-benchmarks» commands to the command line for running graphed benchmarks.

  OCCT V9.0 — Benchmarks & Leaderboard !

  testingOCCT Perestroïkabenchmarksutilities

  comment on related news

  Overclock 3D

  May 15, 2021

  A couple of days ago, we reported that the AMD Radeon RX 6600 XT and RX 6600 graphics cards appeared on the ECE website, and now the detailed specifications of these cards have been published on the Web.

  Specifications made available by posting screenshots from the GPU-Z utility.

  As you can see from the screenshots themselves, the RX 6600 XT accelerator will have a GPU with 2048 stream processors, 128 TMUs, 32 ROPs, and 128-bus memory, which is offered as 8 GB GDDR6.

  RX 6600 XT graphics card specification in GPU-Z

  As for the RX 6600, it will only have 1792 stream processors, 112 TMUs and also 32 ROPs. The amount and bus of video memory are similar — 128 bits and 8 GB GDDR6.

  RX 6600 GPU-Z Specification

  Both graphics cards support PCI-Express Gen 4, however, like the RX 5500 XT, Navi 23 uses only 8 lanes. A noteworthy point: the GPU-Z utility has fixed support for ray tracing.

  Radeon RX 6600 XTAMDRadeonRX 6600GPU-Z

  Comment ​Related news

  TechPowerUp

  May 13, 2021

  The GPU-Z utility that displays graphics card information has been updated to version 2.39, which received support for Intel Rocket Lake processors, RDNA 2 mobile graphics cards and new NVIDIA CMP mining accelerators .

  Also, the utility has been updated with a database of new video cards, and in addition, a number of errors have been fixed, including very old ones. The full list of changes in GPU-Z 2.39 is below.

  GPU-Z

  • Added support for Intel Rocket Lake integrated graphics.
  • Added support for NVIDIA RTX 3060 Mobile, RTX 3050 Ti Mobile, RTX 3050 Mobile, RTX A5000, T500, CMP 30HX, CMP 40HX, CMP 90HX accelerators.
  • Added support for AMD Radeon RX 6900 XTXH, Radeon Pro W5500M, Barco MXRT 4700.
  • The integrated screenshot feature now captures the correct window area on Windows 10 (does not capture shadow).
  • The VRAM usage sensor has been removed on NVIDIA graphics cards running in TCC mode due to lack of support in the NVIDIA API.
  • XML dump now includes BIOSUEFI, WHQL, DriverDate, DXR, DirectML, OpenGL, and ResizableBAR fields.
  • Added memory type detection on Intel i740.
  • Fixed Resizable BAR detection on some systems.
  • Fixed frequency reading on AMD Mobile RDNA2.
  • Fixed OpenCL detection on some rare systems.
  • Fixed frequency reading on NVIDIA GeForce 6.
  • Fixed BIOS update on some legacy ATI cards.
  • Fixed release dates for ATI RV200 and NVIDIA NV41M.

  Download GPU-Z 2.39.

  testing the video card BIOS GPU-Z utility

  comment on similar news

  The new version of the utility received a database update concerning several new models of video cards, and a number of errors in the utility’s operation have also been fixed.

  GPU-Z utility interface

  Full list of changes in GPU-Z 2.37.0 is as follows:

  • Added memory manufacturer detection on Navi 1x and Navi 2x.
  • Added workaround for NVIDIA Ampere PCIe.
  • Added filter to bypass misread on EVGA iCX.
  • Fixed incorrect detection of some GT218 variants.
  • Improved Russian translation.
  • Added preliminary support for Radeon RX 6700 and RX 6600.
  • Added support for NVIDIA GeForce RTX 3060, RTX 3080 Mobile, RTX 3070 Mobile, RTX 3060 Mobile, RTX A6000, A40, A100-SXM4-40GB, Drive PX2, P106M, Quadro K510M, modified Quadro K6000.
  • Added support for additional NVIDIA GTX 1650 Max-Q, Quadro P1000, GTX 650, GT 430 variants.
  • Added support for AMD Cezanne, Radeon Pro V520, R9 290X ES, Barco MXRT 2600. Celeron 5205U and i7-10810U).
  • Added supplier definition for Yeston.

  You can download GPU-Z v2.37.0 on our website.

  GeForce RTX 3060MOBILE3070 MOBILE3080 MOBILERADEON RX 67006600GPU-ZUTILITIS

  Comment similar news

  TechPowerUp

  29, 200929

  NVIDIA 300 TIs AC AND AND AND AND AND AND AND October 29.

  According to these specifications, the video card will receive 4864 CUDA cores and 8 GB of GDDR6 video memory with a 256-bit bus and a bandwidth of 14 Gb / s, which in total will provide a speed of 448 GB / s. True, the GPU-Z video card page is not complete, and it also contains the wrong number of TMUs, nevertheless, it gives a clear idea of ​​\u200b\u200bthis mid-range accelerator.

  NVIDIA RTX 30 lineup

  The video card will be based on the GA104 processor, the same model as the RTX 3070, but the lower version will receive 1024 fewer cores. But the memory configuration will be the same as in the older model.

  In terms of frequencies, the RTX 3060 Ti will run the processor at a base frequency of 1410 MHz and at a frequency of 1665 MHz in Boost mode.

  RTX 3060 Ti GPU-Z Specs

  It’s worth noting that while NVIDIA hasn’t said anything about preparing the RTX 3060 Ti, production partners are rumored to be already in full swing preparing this card for release in mid-November. The price for it should be a little lower than $ 400.

  RumorsGeForce RTX 3060 TiGPU-Z

  video cards

  In the new version of the utility, the monitoring capabilities of video cards from Intel and AMD have been improved, bugs in the operation and launch of the utility have been fixed, and a huge number of new models of video cards from both NVIDIA and AMD have been added.

  GPU-Z

  The full list of changes in GPU-Z v2.31.0 is as follows:

  • Fixed DirectML detection on new builds of Windows Insider.
  • Added GPU voltage monitoring for Intel integrated graphics.
  • The AMD Radeon Pro driver now reports version number information.
  • Added command line arguments: -install and -installSilent.
  • Replaced installer with InnoSetup.
  • Improved driver version detection on some systems with NVIDIA GPUs.
  • On the «Advanced» tab, if Vulkan or OpenCL cannot be detected, the message «not supported» is displayed instead of «not found».
  • On slow machines, GPU-Z startup has long delays to avoid errors.
  • Added support for NVIDIA GeForce RTX 2070 Super Mobile, RTX 2080 Super Mobile, RTX 2060 Max-Q, RTX 2070 Super Max-Q, RTX 2080 Super Max-Q, RTX 2070 Mobile Refresh, RTX 2060 Mobile Refresh, GTX 1650 Mobile, GTX 1650 Ti Mobile, GeForce MX350, GRID RTX T10 (GeForce Now), Quadro RTX 8000, Tesla P40, Quadro 500M, GeForce GTX 1060 (Microsoft), GeForce GT 610 (GF108), GeForce GT 730M.
  • Added support for AMD Radeon Pro 580, Radeon Pro V340, Apple 5300M and 5500M.

  You can download GPU-Z v2.31.0 on our website.

  Video CartoMdintelnvidiRadeonographic processorygpu-zulytes

  Comment similar news

  TechPowerUp

  March 17, 2002

  Famous information utility GPU-Z, providing detailed information about the video card and its operation, received an update to the version 2.30.0.

  The new version of the utility fixes bugs in its work, added some new models of video cards.

  GPU-Z 2.30.0

  The full list of changes is as follows:

  • Added extended tab for the GPU hardware acceleration scheduler (Windows 10 20h2).
  • Advanced tab now shows WDDM 2.7, Shader Model 6.6, DirectX Mesh Shaders, DirectX Raytracing Tier 1.1.
  • Worked to fix a DirectML bug found on Windows 10 19041 Insider.
  • The graphics device driver registration path is now located in the Advanced -> General tab.
  • NVIDIA VDDC sensor renamed to GPU Voltage.
  • AMD GPU only Power Draw sensor renamed to GPU Chip Power Draw for better understanding.
  • The Windows Basic Display Driver no longer appears in WHQL/Beta status.
  • Updated Renoir 7nm process information.
  • Added support for AMD Radeon RX 590 GME, Radeon Pro W5500, Radeon Pro V7350x2, FirePro 2260, Radeon Instinct MI25 MxGPU, AMD MxGPU.
  • Added support for Intel UHD Graphics (i5-10210Y).
  • Added support for NVIDIA GTS 450 Rev 2.
  • Fixed crash when detecting DirectX 12.

  You can download GPU-Z v2.30.0 on our website.

  testing video cardAMDNVIDIAGPU-Zutilities

  comment on similar news29

  The well-known information utility GPU-Z, which allows you to get detailed information about the video card and its modes of operation, has been updated to version 2.29.0.

  Changed the displayed frequencies for Navi video cards, fixed the utility and added support for new models of video cards from AMD and Intel.

  GPU-Z

  The full list of changes in GPU-Z 2.29.0 is as follows:

  • All AMD RX 5000 (Navi) series cards now display game clocks under GPU Clock instead of base clock.
  • Fixed issue where GPU-Z would forget its window position if the OS exited while the application was running.
  • Fixed GPU-Z crash when stopping AMD driver (during driver update, etc.).
  • Fixed PCIe speed report on Vega.
  • Added support for Intel Iris Plus Graphics 645.
  • Added support for AMD Radeon RX 5600 and 5600 XT, Renoir APU, Radeon Pro Vega II, Radeon HD 8280E.

  Download GPU-Z v2.29.0 is available on our website.

  Renoirvideocardi-Cardrix Vegaradeon RX 5600XTGPU-ZUTILITS

  Comment similar news

  TechPowerUp

  December 10, 2019

  The famous information utility GPU-Z, which allows you to get detailed information about the video card and its operation, received the overwhelming of the 2. 28. 0.

  The new version of the utility adds support for AMD Radeon RX 5500 XT and Radeon Pro W5700 video cards, as well as new drivers for AMD video cards that have not yet been released. Also improved work with other AMD video cards, including integrated ones.

  GPU-Z 2.28.0

  Full changelog of GPU-Z 2.28.0 is:

  • Added support for AMD Radeon RX 5500 XT, Radeon Pro W
  • Added support for upcoming AMD graphics drivers.
  • Fixed 4 GB VRAM warning on Navi maps.
  • Improved detection of AMD RX 470D, RX 560 Mobile, Picasso, Raven Ridge.
  • Fixed frequency reading on old ATI video cards.
  • Added report on DirectX support in ATI R 9 GPU0084

  You can download GPU-Z v2.28.0 on our website.

  Naviamdographic processorrheon RX 5500 XTGPU-ZUTILITS

  Comment similar news

  TechPowerup

  November 19, 2019

  The famous information utility GPU-Z, which allows you to get detailed information about the graphics card and its operation, received reference to version 2. 27 .0.

  The new version of the utility fixes some bugs and optimizes performance. The base of video cards has also expanded significantly, which now includes NVIDIA GeForce GTX 1660 Super, TX 1650 Max-Q, GeForce 945A, Tesla V100-SXM2-16GB, Tesla P4, Tesla K8; AMD Radeon Pro Vega 48 and FirePro A300.

  GPU-Z

  The full list of changes in GPU-Z 2.27.0 is as follows:

  • The Advanced tab now shows the location of the device in the PCI bus.
  • Fixed a crash on very old processors that did not have SSE support.
  • Fixed an issue that caused the EVGA ICX fan speed to not be reported on GeForce 20 graphics cards.
  • Fixed sensors displaying «0» on some AMD CrossFire builds.
  • Improved default frequency reporting on NVIDIA, even without a driver installed.
  • Fixed incorrect memory frequency reporting on NVIDIA when two cards with different memory types are installed.

  You can download GPU-Z v2.27.0 on our website.

  GPUsGPU-Z utilities

  comment on related news

  TechPowerUp

  September 12, 2019

  TechPowerUp has prepared another update to its popular GPU-Z utility designed to get all the available information about your graphics card and its parameters. The update was numbered 2.25.0.

  The new version boasts the placement of information about supported graphics technologies, improved stability, improved and expanded hardware databases.

  GPU-Z

  The full list of changes in GPU-Z 2.25.0 is below:

  • The first tab now shows the status of Vulkan, DirectX Raytracing, OpenGL and DirectML support.
  • Fixed blue screen in QEMU/KVM virtual machines caused by MSR access.
  • Improved frequency display for AMD Navi.
  • The Advanced tab now displays base, game and boost frequencies in Navi.
  • Added an exception for stuck fan frequencies when fan stop is activated on AMD graphics cards.
  • Added exception for 65535 rpm fan speed displayed in Navi.
  • When the BIOS upload to the site is completed, the message Finished is displayed.
  • Added support for NVIDIA Quadro P2200, Quadro RTX 4000 Mobile, Quadro T1000 Mobile.

    The latest version received only 5 changes. It is designed to fix bugs and slightly expands the hardware database.
    The list of changes in GPU-Z 2.24.0 is as follows:

    GPU-Z

    • Fixed a digital signature error when running on Windows Vista.
    • Added support for NVIDIA GeForce 305M, Quadro P620.
    • Added support for Intel HD Graphics (Xeon E3-1265L V2).
    • Fixed typos in the Advanced -> Vulkan section.
    • Added PCI Vendor ID for Dataland manufacturer.

    You can download the GPU-Z 2.24.0 utility from our website.

    overclocking GPU-Z utility

    comment on related news

    TechPowerUp

    July 3, 2019

    TechPowerUp has prepared another update of its popular GPU-Z utility designed to get all the available information about your graphics card. The update was numbered 2.22.0.

    Given the hot July, filled with many hardware releases, the release of a new version of the utility is not surprising. As expected, the new version received support for AMD Navi graphics cards, the NVIDIA RTX Super series, and the PCIe 4. 0 bus. Moreover, the utility now has the ability to determine the support of a new bus by a video card. In addition, the utility will report if its current version is not able to determine the GPU model.

    GPU-Z

    Changes in GPU-Z version 22.2.0 are as follows:

    • Added preliminary support for Radeon RX 5700 and 5700 XT (Navi).
    • If a GPU-Z.ini file exists in the GPU-Z directory, the utility will read and write settings to that file instead of the registry, making GPU-Z completely portable.
    • If the utility detects an unknown GPU, GPU-Z will display a notification requiring validation.
    • Added support for PCI-Express Gen 4.
    • Added support for NVIDIA RTX 2060 Super, RTX 2070 Super, RTX 2080 Super, Tesla T4, Quadro T2000 Mobile.
    • Added support for AMD FirePro S7150, ATI FireStream 9250.
    • Added support for Intel HD Graphics 620.
    • Added temperature sensor for AMD SoC.

    You can download the free GPU-Z utility from our website.

    Testing-crankcasenaviSHISHISHICHICHICHICHIGEFORCE RTX 2060 SUPER2070 SUPER2080 SUPERGPU-ZUTILITS

    Comment similar news

    TechPowerup

    February

    TechPUWERUP website.

    There were quite a few changes. The most important of them is the expansion of the utility base with new video cards, both from NVIDIA and AMD. The rest of the changes relate to the operation of the program and bug fixes.

    GPU-Z 2.17.0

    Full changelog in GPU-Z 2.17.0:

    • Added support for NVIDIA GTX 1660 Ti, Titan RTX, RTX 2080 Mobile, RTX 2070 Mobile, RTX 2060 Mobile, Quadro RTX 4000, GTX 650 (GK106), Quadro P5200.
    • Added support for AMD Radeon VII, Radeon HD 8400E.
    • Added support for Intel Amber Lake GT2 (Core i7-8500Y).
    • Added support for Radeon Adrenalin 2019 version detection.
    • Simplified some sensor names: GPU Clock, Memory Clock, Shader Clock.
    • Unified sensor names from «Memory Used / Memory Usage» to «Memory Used».
    • Improved the crash reporting system, which asks clarifying questions about the problem.
    • The drop-down Advanced panel will only show «Memory Timings» if information about it is available.
    • OpenCL «Max Packet Size» is now formatted as an inactive value.
    • The word «missing» is now displayed instead of empty when there are no supported built-in OpenCL kernels.
    • Added support for «missing» in OpenCLDP, SP, Half FP.
    • Fixed «file creation error» when running GPU-Z.
    • Fixed GPU and memory load monitor in RX 580 2048 SP.
    • Fixed missing Boost frequencies in GTX 1660 Ti and some Pascal cards.
    • Fixed missing fan sensor on RTX cards without a monitor connected.
    • Fixed a crash on startup on Windows XP.
    • Fixed a crash when opening a DXVA 2.0 report on Windows XP.
    • Fixed power consumption limit report on older NVIDIA cards.
    • Fixed crash when saving BIOS on older NVIDIA graphics cards.
    • Fixed incorrect VRAM reporting on 16 GB Vega.
    • Fixed crashes due to physical memory access.

      GPU-Z version 2.16

      You can download the GPU-Z utility from our website.

      IGPEVGANVIDIAGPUsGeForce RTX 20602080GPU-ZUtilities

      Comment on related news

      This time only 5 changes have been made. The main one can be considered support for the integrated graphics processor in the Intel Core 9 CPUth generation. Bugs from previous versions have also been fixed.

      GPU-Z v.2.14.0

      The full list of changes in GPU-Z 2.14.0 is as follows:

      • Boost frequencies are used to calculate scene and texture fill rates when possible.
      • Fixed lost Intel GPU temperature sensor.
      • Fixed incorrect frequency on some Intel IGPs («12750 MHz»).
      • The energy sensor is now marked with «W» and «%».
      • Added support for Intel Coffee Lake Refresh.

      You can download the GPU-Z utility from our website.

      Coffee Lake Refreshigpintelnvidiagpu-zulytes

      Comment similar news

      Techpowerup

      October 12, 2018

      Techpowerups updated its information utility, GPU-ZZ, to version 2. 12.0, to version 2.12.0

      The release of the latest version of the popular monitoring utility is mainly dedicated to the new NVIDIA Turing architecture. All but one of the changes relate to support for the new hardware capabilities of NVIDIA 20xx-series video cards. Another change concerns a lot of old accelerators, and it’s quite interesting. Now the GPU-Z utility can detect fakes of old video cards.

      GPU-Z detected a fake video card

      The list of changes in GPU-Z v2.12.0 is as follows:

      • Added detection of fake video cards using old rebranded NVIDIA GPUs (G84, G86, G92, G94, G96, GT215, GT216, GT218, GF108 , GF106, GF114, GF116, GF119, GK106).
      • Added ability to save BIOS for NVIDIA Turing graphics cards.
      • Added monitoring of several fans on the Turing.
      • Added fan percentage monitoring on Turing.
      • Added information about HDMI and DisplayPort to the Advanced tab.
      • Power consumption of NVIDIA graphics cards is now displayed in both TDP percentages and watts.
      • Fixed a hang caused by Valve’s anti-cheat system.
      • Turing bandwidth fix with GDDR6 memory.
      • Fixed tips for using the system memory sensor.
      • Fixed broken monitoring of Radeon RX 400 GPU usage on new drivers.

      Just before the New Year, Nvidia’s graphics partner EVGA surprised many with the introduction of the GeForce GTX 580 Classified Ultra. The video card was developed together with professional overclockers Vince «k|ngp|n» Lucido and Ilya «TiN» Tsemenko, as a result we should get one of the fastest models on the market. The team really managed to introduce a new «monster» with a 14+3-phase power system, high-quality components such as Super Low ESR SP-Cap and NEC Proadlizer capacitors, as well as high-frequency coils, and various overclocking technologies. We note the support of Evbot, a special BIOS version and the presence of contact points for direct voltage measurement. Finally, the video card uses a powerful and expensive cooling system with an 80mm fan.

      But that’s not all. To ensure that sufficient power is supplied in extreme cold conditions, the EVGA graphics card contains two 8-pin PCI Express power connectors and another 6-pin. Together with 75 watts supplied via the PCIe x16 interface, a high-end graphics card can draw up to 450 watts from the power supply. If you’re planning on doing some extreme overclocking with liquid nitrogen (LN2) for example, then you don’t have to think about supplying additional power — two professional overclockers really did their best in this regard. Among other things, with EVGA GeForce GTX 580 graphics cards, you can assemble the fastest 4-Way SLI configuration.

      As you might expect, video cards are already factory overclocked. The California based company is targeting 772/1544/1002 MHz for its single GPU flagship, but EVGA has bumped the clock speeds to an amazing 900/1800/1053 MHz — we got over 145 MHz boost for the GPU. As is usually the case with models of this level, the amount of memory has been doubled to 3072 MB. How much will such pleasure cost? Almost 540 euros.

      » Photostrecke

      GPU of the new EVGA GeForce GTX 580 Ultra Classified, like all modern chips from the Californian manufacturer, is manufactured using a 40-nm process technology at TSMC factories. The transition to a more modern 28nm process is expected only with the upcoming generation of «Kepler» GPUs. The announcement is rumored to take place in April 2012. Therefore, the GeForce GTX 580 is still the fastest graphics card with a single Nvidia GPU with 512 «Fermi» architecture stream processors. The GPU contains 16 Stream Multiprocessors (SMs), each consisting of 32 ALUs (Stream Processors). Four TMUs are connected to each SM, for a total of 64 texture units.

      Compared to the previous flagship of the line, there were no changes in the memory configuration. Nvidia still used GDDR5 memory chips connected via six 64-bit controllers — they gave a total of 384-bit memory bus width. As usual, eight ROPs are connected to each memory controller, for a total of 48 ROPs. Initially, the NVIDIA GeForce GTX 580 graphics card came out with 1.5 GB of memory, but a few weeks later the Californian company introduced a new computing card that had twice the amount of memory. And in our case, we got 3072 MB of memory, which should be enough for almost any task.

      EVGA didn’t want to be left behind either, as Nvidia chose 772/1544/2004 MHz for its flagship single-GPU graphics card. In the case of the EVGA GeForce GTX 580 Ultra Classified, we get very decent frequencies of 900/1800/1053 MHz. Such frequencies became possible thanks to a modified board layout and an improved cooling system.

      Whether EVGA’s efforts were justified, we’ll find out in the benchmarks section.

      But first, let me give you the key specifications:

      Manufacturer and model	EVGA GeForce GTX 580 Classified Ultra
      Retail price	540 euro
      Manufacturer website	http://www. evga.com/
      Technical specifications
      GPU	GF110
      Process	40 nm
      Number of transistors	3.0 billion
      GPU clock speed	900 MHz
      Memory clock	2106 MHz
      Memory type	GDDR5
      Memory capacity	3072 MB
      Memory interface	384 bit
      Memory bandwidth	202.2 GB/s
      Shader Model Version	5.0
      Number of stream processors	512 (1D)
      Stream processor frequency	1800 MHz
      Texture blocks	64
      ROP	48
      Pixel fill rate	28.8 Gpixel/s
      SLI/CrossFire	SLI

      Thanks to the high clock speeds, we get higher memory bandwidth and pixel fill rate than the reference model. Namely, 202.2 GB / s and 28.8 Gpixel / s.

      An updated power system, powerful cooling system, high-quality components and higher clock speeds make the EVGA GeForce GTX 580 Classified Ultra the fastest graphics card in its category. Whether this will be the case in practice remains to be seen.

      <>Test & Review: EVGA GeForce GTX 580 Classified Ultra
      Impressions I

      149-215-002 GeForce 500-Series NVIDIA GeForce GTX 580 | Junk

      • Description

      • Technical condition

      • Equipment

      Buy as a legal entity

      Delivery methods
      
      after placing an order
      

      Pick up from warehouse at
      

      _Sheremetyevo-1
      ,
      Lobnya MO, st. Sports, 1A
      
      

      Pick up from a mobile pickup point in Moscow
      

      timetable

      
      

      Ask seller a question

      PCIe 2.0 / GDDR5 / 1.5GB / 384 bit / 244 W / 6-pin+8-pin

      More

      • Description

      • Technical condition

      • Equipment

      Used video card GAINWARD DUAL GeForce® GTX 580 1. 5GB / NE5X580010CB-1100F

      The video card was removed from the system unit used in the organization’s office for 8 years.

      >>>Cooling system:
      2×FAN 80mm
      2×HeadSink (Aluminum Heat Sink with Copper Tubes)

      >>>Video Card: GAINWARD DUAL GeForce® GTX 580 1.5GB / NE5X580010CB-1100F
      1×FAN — OK
      2×DVI-D — OK
      1×HDMI — not tested
      1×DP — not tested
      Driver installation — OK
      Auxiliary power supply 6-Pin+8-Pin — OK
      OCCT 3D 1366×720 — OK

      >>>FurMark Benchmark test data:
      Max. temp. — 78°C
      Resolution : 1366×720
      Configuration : Standard HD with 4x anti-aliasing
      Min. FPS — 32
      Max FPS — 34
      Average FPS — 32
      (see photo)

      Technical condition

      Power on test:

      Checked. Works. Ready for use.

      Package

      • Composition

      • one
        ×
        GeForce 500 Series
        GTX 580 1. 5GB
        MSI
        DUAL NE5X580010CB-1100F / 1.5GB / 783 MHz / 384 bit / PCI Express 2.0 16x / 2xFan / GDDR5 / 1xHDMI / 1xDP/ 2xDVI-D

      Power on test:

      Checked. Works. Ready for use.

      • Composition

      • one
        ×
        GeForce 500 Series
        GTX 580 1. 5GB
        MSI
        DUAL NE5X580010CB-1100F / 1.5GB / 783 MHz / 384 bit / PCI Express 2.0 16x / 2xFan / GDDR5 / 1xHDMI / 1xDP/ 2xDVI-D

      Description

      Video card used GAINWARD DUAL GeForce® GTX 580 1.5GB / NE5X580010CB-1100F

      The video card was removed from the system unit used in the organization’s office for 8 years.

      >>>Cooling system:
      2×FAN 80mm
      2×HeadSink (Aluminum Heat Sink with Copper Tubes)

      >>>Video Card: GAINWARD DUAL GeForce® GTX 580 1.5GB / NE5X580010CB-1100F
      1×FAN — OK
      2×DVI-D — OK
      1×HDMI — not tested
      1×DP — not tested
      Driver installation — OK
      Auxiliary power supply 6-Pin+8-Pin — OK
      OCCT 3D 1366×720 — OK

      >>>FurMark Benchmark test data:
      Max. temp. — 78°C
      Resolution : 1366×720
      Configuration : Standard HD with 4x anti-aliasing
      Min. FPS — 32
      Max FPS — 34
      Average FPS — 32
      (see photo)

      Technical condition

      Power on test:

      Checked. Works. Ready for use.

      Equipment

      • Composition

      • one
        ×
        GeForce 500 Series
        GTX 580 1. 5GB
        MSI
        DUAL NE5X580010CB-1100F / 1.5GB / 783 MHz / 384 bit / PCI Express 2.0 16x / 2xFan / GDDR5 / 1xHDMI / 1xDP/ 2xDVI-D

      0001

      Each new generation of graphics accelerators pursues the same goal — to be as fast as possible before the previous one. While the next series of chips from NVIDIA has not yet been released, I suggest you plunge a little into the past and compare two single-chip tops. In the ring Leadtek GeForce GTX 580 and Point Of View GeForce GTX 480 . In order not to make allowances for the difference in nominal frequencies, the cards, in addition to the nominal, were tested at equal frequencies of the graphics core, and here another intrigue arises: can an overclocked GeForce GTX 480 reach the nominal GeForce GTX 580?

      Theoretical research on the Fermi architecture has already been carried out on our portal — I recommend reading the article “NVIDIA GTX 480 Review and Testing” by ALSTER. The map from Point Of View also appeared in our reviews: Best of the Best. Review Point Of View GeForce GTX 480 TGT Tuning

      A brief review of the appearance of the video card from Leadtek. It comes in traditional, if not unique, packaging. The box is still the same supercar, only the names and indices of video cards are different.

      The reverse side of the box, as usual, is reserved for a brief description of the card’s features.

      The graphics card is packed securely in polyurethane foam. The accelerator is rigidly fixed and even covered from above with a thin plate of protective material. Leadtek has taken very serious safety precautions and damage in transit is almost impossible. The package includes two power adapters, a DVI-VGA adapter and a driver disk.

      Reference design and branded sticker — no wiring or cooling features observed. The most reliable and surest way not to spoil the opening is to release a reference — I fully support Leadtek’s undertaking.

      Here are both cards before the “battle”. The GeForce GTX 480 looks slightly longer due to the non-reference cooling system.

      Characteristics of video cards can be evaluated and compared by the screenshots of the GPU-Z program (I used the ROG Edition just for the love of red and black colors).

      Test bench and test method:

      Processor	Intel Core i7 990X (3.46 GHz) + Noctua NH-C14
      Motherboard	EVGA Classified E760, BIOS 83
      Video card	Leadtek GeForce GTX 580 and Point Of View GeForce GTX 480
      RAM	ADATA Plus series DDR3-1866 3*2048Mb
      Power supply	Enermax Revolution 85+ 1020W
      Hard disk	Intel SSD 510 series 250 Gb
      Housing	Dimastech Benchtable
      Monitor	Philips 244E 1920*1080
      Keyboard	Logitech Illuminated Keyboard
      Mouse	Logitech MX518

      Operating system	Windows 7 Home Premium 32-bit
      Driver version	GeForce ForceWare 280. 26
      Additional software	MSI Afterburner 2.2.0 beta 8
      Additional software	CPU-Z 1.58 ROG Edition, GPU-Z 0.5.5 ROG Edition

      Test kit

      Synthetics:

      • 3D Mark 11
      • 3D Mark Vantage
      • Unigine Heaven

      Game Tests:

      • Aliens vs Predator
      • Metro 2033
      • Street Fighter IV
      • Just Cause 2
      • Lost Planet 2
      • Mafia 2
      • Dirt3
      • World In Conflict

      As I said in the introduction, testing was carried out for each card in the nominal and overclocked modes. Overclocking on the graphics core was 900 MHz. It is worth noting that for the GTX 480 this is a very good result and it cannot be argued that every copy will reach such frequencies. The percentage increase was 14% for the Leadtek GeForce GTX 580 and 15% for the Point Of View GeForce GTX 480.

      Let’s start the debriefing. Synthetic 3D Mark gave victory to the overclocked GeForce GTX 580 in all presets, though the advantage decreased as the task became more difficult. When overclocked, the GeForce GTX 480 was able to bypass its older sister in the nominal mode in all presets, but at the same time, the noise during operation became unbearable, all three fans rotated at 100%.

      The second synthetic test turned out to be less favorable to the outgoing generation. Probably it’s also in the optimization of drivers, this was observed for NVIDIA earlier.

      The game Aliens vs Predator demonstrates that the “old man” is ready to overclock the current flagship, but just by a little bit.

      A new test in our reviews — here the gaps are more impressive, but the general order is preserved.

      The distance of 13 frames between the nominal and the overclocked state is typical for both cards, but with this comparison, 7 frames of separation in favor of the GeForce GTX 580

      Lost Planet 2 confirms the trend — the GeForce GTX 480 in overclocking can only overtake and catch up with the nominal GeForce GTX 580, but nothing more.

      Mafia II — the picture is the same, there is not even much to comment on

      Scanty gaps in absolute terms become logical when it comes to percentage gains and gaps.

      And here, on the contrary, the performance is too high, it seems that the ceiling of the processor has been reached.

      A synthetic benchmark from Russian programmers shows us that even with Russian code nothing can be done about the alignment of world forces.

      World in Conlict is not so obvious, but confirms the outline of the test — the positions remain the same.

      Conclusion

      What we got as a result: overclocked by 15% (from 763 to 900 MHz) GeForce GTX 480 catches up with the nominal Leadtek GeForce GTX 580 video card. So the upgrade is justified if the increase is such a significant figure. With regard to Leadtek products, we can say the following:
      managed to keep all the good things in the reference cards. When choosing from such samples, the decisive factor will certainly be the warranty period and price.