Slashdot Mirror

Insightful? Really mods? While you are throwing insults you MIGHT want to read the festering SJW shitshow they are trying to shove on Linux, which is racist and sexist as fuck with an explicit stated goal to get rid of meritoracy and instead base contributions on how high you rank in the Oppression Olympics...yeah because developing extremely complex kernel code should be based on what your skin color is and whether you are a hufflepuff (no shit the one heading this bunch of whack-a-doodles calls herself a hufflepuff) not whether you can ACTUALLY WRITE GOOD FUCKING CODE.

And ya wonder why more and more are looking at the SJW movement and the regressives and going "Yeah can't stand the right....but at least they aren't batshit like these nutters, think I'll switch". I mean for fucks sake who gives a single flying flipping fuck (other than regressives because ALL they care about is being racist sexist fucks) what color someone writing KERNEL CODE is? Torvalds has certainly never given a shit, he treats ALL who act like morons as moronic no matter what color they were and only gave a shit about the quality of the code, not about whether they are a "protected class" they needed to be coddled and infantilized (cuz never forget the regressives are all about soft bigotry of low expectations) because that is the nice thing about meritoracy, cream rises to the top, shit gets flushed like it should.

Be be sure to screaming "INCELS" and "Muh FEE FEES!" at the top of your lungs and call everyone an "IST!", because I'm sure designing an OS based on promoting skin color and how many adjectives one can add to their choices in who to fuck will make a really quality product...yeah and my mama was a Kaiju and my name is Godzilla.

https://www.hardocp.com/news/2... read the other links. Nvidia has also apparently blacklisted HardOCP for posting all of this information to the public.

Seriously, every single gamer out there should look hard at what nvidia did, say "fuck you" buy a AMD card on their next upgrade/new rig, send them a picture and tell them that this is the result of the GPP program.

Indeed. Sounds like Kyle Bennett and HardOCP might as well accept their backtracking as an apology because although they're too arrogant to ever admit they were wrong... they're apparently too stupid to realize that they just did.

It's Nvidia and ATI's shortsightedness that we are in the situation we are in.
They should have ramped up production to address demand 8 months ago.

Unfortunately, they can't. TSMC has given each company a wafer allocation (silicon fabs take years to build and wafers are allocated years in advance). Also, TSMC has bigger companies to feed...

* Apple SoCs for iPhones (100millon chips or so)
* Bitmain the leading ASIC for Bitcoin mining (buying about 20,000 wafers/month)

Basically, there's no "extra" fab capacity to be had to ramp up production...

Here is an interesting article on what Raja was doing with RTG by HardOCP's Kyle Bennet (even talked about Intel interest in the AMD graphics). Kyle did also predict that Raja would not return when he went into Sabbatical a couple of months ago. The article is from a year and a half ago, so it is not about the current status: Kyle has since written that AMD seems to be on a good track with the internal shuffling and in its best form in years.

GHz for GHz, Kaby Lake (Jan 2017 desktop release) is only about 20% faster than Sandy Bridge (Jan 2011 desktop release). 20% improvement in 6 years. I'm still telling people with Sandy Bridge systems not to bother upgrading. Unless you want more cores (i3 to i5 or i7), some of the newer features (like USB-C support), or want lower power consumption, there's no reason to stop using a Sandy Bridge system.

Clock speed has also been relatively static. 3.6-3.9 GHz in 2011 to 4.4-4.5 GHz in 2017. A 19% increase. Combine the two and you get an underwhelming 42% improvement in processor speed in 6 years.

Even as recently as the late 1990s, by the time a system was 6 years old, it was far beyond obsolete. For example, November 1995 saw the release of the 200 MHz Pentium Pro. If you skip ahead 6 years, you find the 2.0 GHz Pentium 4 released in August 2001. A 900% increase just in clock speed in 6 years.

PC sales are lackluster because there's no reason to upgrade at anywhere close to the rate we had to upgrade in the past.

The 64 can only trade blows with the 1080 till you throw MSAA at it.

https://www.hardocp.com/articl...
The 64 is using 475w compared to 325w for the 1080, not to mention you can get an AIB 1080 for cheaper than the 64.

I don't remember the name though and I didn't think much of it either. This was when people were experimenting with Peltier cooling, and watercooling tended te be entirely custom jobs.

Alright I remembered the Vapochill name.

https://www.hardocp.com/articl...

Quite understandably maybe, it puts a fridge in your computer rather than your computer in a fridge.

Oops wrong one
http://www.hardocp.com/article...

http://www.hardocp.com/article...

PC sales are slowing, and this is why everyone runs around saying 'THE PC IS DYING OMG'

When in fact, Intel's cpu's arent getting much faster... [H]ardOCP recently tested a Kaby Lake 7700K vs Sandy Bridge 2600K http://www.hardocp.com/article... and the 7700K was only about 20% faster in a couple of tests... If you have a non current generation computer, you can put a fast SSD in it (if you dont have one already) and a faster GPU and you're fine for 99% of things (though with Sandy Bridge you miss out on things like M.2, PCIe 3.0 etc

More people I know have been building a PC rather than buying an HP or something prebuilt as well

+1
Going from Sandy Lake to Kaby will net you 15-20% (though it is also DDR4 2666MHz vs DDR3 2133MHz)
http://www.hardocp.com/article...

For awhile, it got even worse than that...

Given that is a next-gen architecture, it does not do well in newer APIs like DX 12 and in fact, in Vulkan seems to be pretty much destroyed by the RX 480 competition: http://www.hardocp.com/article...
Now, the fact that AMD cannot clock their parts high and uses more power than nVidia on a similar process, shows that nVidia did get that part of the equation right once more. But it seems to be that there is competition this time, the AMD parts use more power but give you more bang/buck and seem to be even faster with newer games, so make a good investment for the future.

Oh wait you can

http://www.alienware.com/

Not for you ? Oh if only there were someplace that would let you pick your components and they would build the PC for you

https://www.google.com/search?...

Tooo hard to figure out what you need ? If only there were a guide of some kind

http://www.tomshardware.com/

http://www.hardocp.com/

That is coming with Zen which will be coming along with a new socket which will allow them to combine the APU and CPU lines along with a completely new architecture designed by the same guy who made the Athlon64

So there really is no point in releasing a new chip until the new socket boards by the OEMs are ready to go, especially not just for PCIe 3 which test after test has shown has a completely negligible effect on performance even with 3 way crossfire. The simple fact of the matter is we have yet to saturate PCIe 2 yet and with AAA titles costing so much to make AND the fact we have just started on a new console generation that came out of the gate with lower performance than midrange gaming PCs? I seriously doubt we'll see PCIe 3 used as anything but a bullet point on a box for the foreseeable future, its just not needed.

That was a pretty not in-depth performance review
http://www.hardocp.com/article...
http://www.hardocp.com/article...
http://www.hardocp.com/article...

That was a pretty not in-depth performance review
http://www.hardocp.com/article...
http://www.hardocp.com/article...
http://www.hardocp.com/article...

That was a pretty not in-depth performance review
http://www.hardocp.com/article...
http://www.hardocp.com/article...
http://www.hardocp.com/article...

No, it doesn't. HardOCP did a test with the new Haswell E series, as well as normal Haswell and Ivy Bridge chips, and then the AMD FX-9590. In every case, the AMD chip lost. Sandra Drystone, Sandra memory bandwidth, Hyper PI, Cinebench, POV Ray, Handbrake, LAME, WinRAR, and games, in call cases it scored below the Haswell chip. In most cases it scored below the Ivy Bridge chip, sometimes substantially. For example in Cinebench the Haswell-E 8 core scored 19.31, the normal Haswell 4 core scored 9.93, the AMD scored 7.93. Also the AMD chip was clocked 500 MHz higher than the Intel chips (all were OC'd, HardOCP is a performance site).

Also please remember that normal Haswell has a TDP of around 90 watts.

Right now, AMD chips just are not a very good showing in terms of power per watt. Intel also is able to be price competitive because their more midrange chips compete with AMD's higher end. The Bulldozer architecture has not proven to be efficient, and Intel also gets to lean on their lead in lithography. All Intel's lines are on 22nm these days and they are rolling out 14nm chips for sale now. AMD is still using a 32nm process.

http://www.hardocp.com/article...

Well... "nice". You still need a rather budget-unfriendly GPU to run with decent graphics settings at those resolutions.
http://hardocp.com/article/2013/11/11/geforce_gtx_780_ti_vs_radeon_r9_290x_4k_gaming/

TLDR version: a single 780Ti or 290X *can* produce playable framerates, but in recent games you will have to turn AA and quality settings down quite a few notches to get there.

http://hardocp.com/ is a good one for reviews on hardware performance and overclocking for gaming.

AMD designed this chip for maximum performance in minimum die space. They managed to cram Titan-level performance in 435mm^2. That's including a 512-bit memory bus AND 64 ROPs, so they're not exactly cutting corners!

The Titan uses a 551mm^2 die-size, and although some of that is fused-off, the majority of the difference is because Nvidia designed it wide and slow for power first, performance second. This is because the part was targeted first-and-foremost at professionals, where performance/watt and cooler noise is actually a concern.

By prioritizing die space over efficiency, AMD were able to offer their card at the $550 launch price-point. AMD is betting that hardcore enthusiasts won't care about power, especially when the card destroys the Titan at 4k resolutions. I guarantee you Nvidia could not make a profit at the same price, and that's why their reaction part (GTX 780 Ti) will be priced at $650.

You can't expect companies to work miracles when all they have is the same old 28mn process. You can emphasize efficiency or die size, but you can't do both!

http://www.hardocp.com/article/2012/05/08/inside_mind_stuart/

I saw it years ago, when everyone was wondering if it was real, lol.

Reminds me, I need some more nyquil...

If you have more time, you may want to learn what the "Hadoop" world is all about.

Not to be confused with Hardocp

Not sure how this is "damning". I'd have thought it would prove the principle that the optimizations aren't app specific.

What am I missing?

It's not app-specific, it's app *name* specific. It's analogous to the Quake/Quack benchmark scandal years (OMG, more than a decade...time flies) ago. Samsung wrote this boosting protocol to enable itself when running benchmarks and *only* when running benchmarks. There is no legitimate way to invoke it, so no user will ever see the benefit of it when running any app *other than* the benchmark itself.

For the inevitable car analogy: you take a Samsung car for a test drive, and when you floor it you feel 200hp worth of acceleration. Since the car is identical in almost every other aspect to competing HTC cars and Motorola cars (same price, similar trim, same engine) but they only make you feel about 150hp worth of acceleration, you opt for the Samsung car. Only when you drive it off the lot, you only feel 150hp worth of acceleration. You take it back to the dealer thinking something's wrong only to be informed the car will only give you 200hp when in "test drive by prospective customer" mode, and now that you've bought the car you're no longer in that category and cannot invoke it.

Ooh, Duelling Benchmarks! Can I have a go?

So we have a problem. Now the hard work of narrowing the problem down can begin. My money is on all of the above. Subtle errors all over the place that nobody could test for and thus couldn't know they needed finding and fixing.

You mean narrowing down the problem that is already known and already being worked on?

Perhaps the problem is rather, why does this article, which pretends nothing of this is already known, exist? If this is a new issue, they totally failed to show it.

More than that, this frame latency issue is new to the recent drivers - possibly even restricted to the 12.11 beta drivers, which one might expect to have the occasional issue. Further, other review sites that investigate the smoothness of gameplay, even if not by quite the same method (ex: Hard|OCP), have not found the issues that Tech Report has, which leads me to suspect that it might not be a universal issue.

I think that Tech Report has been very irresponsible in their handling of this issue. They've been quick to condemn, ignoring that the driver is _not_ a final version, and apparently unwilling to investigate the disparity between their older results with the same cards/older drivers (which had no such frame latency issues) and their new results. Frankly, I'm not willing to give them any regard as a review site any longer - their frame latency methodology certainly has merit, but they seem to be utterly incompetent in actually analyzing or investigating the results.

Oh, we have learned this. Which is why decent review sites don't just publish a "single number" representation of speed. They post a complete FPS graph for similar runs through each game, so you can compare side-by-side

Who is still running a CRT?

This is not a CRT-only problem.

Who wants any program to change the resolution of their screen?

Gamers.

This strikes me as the wrong solution to the problem:

Not surprising, since you're ignoring the underlying problem. Your 2560x1600 desktop on that 30" LCD is going to kill the ability of your videocard to display a modern game at an acceptable frame rate. Many gamers will not accept windowed half-screen (or whatever fraction is required) gaming on their $1K LCD.

A program should instead request the "current monitor's resolution" (because there can be more than one!) set its display area to that size, and then tell the window manager to "fullscreen" it by removing title bar and border decorations and moving it to (0,0) of that monitor. But NEVER EVER RESIZE MY MONITORS.

No. Windows and OSX have figured this out. Linux window managers (at least one popular one) need to as well.

The window manager should always be superior to the app, and one should always be able to manage the window (task switch, move to another desktop, etc) using the window manager, regardless of what the app thinks it is doing.

Irrelevant to your desired scheme, where keyboard hotkeys would still be required. In Windows and OSX you can still task switch, move to another desktop, etc. using such hotkeys. Yet the game controls the resolution of the monitor in fullscreen mode.

You are correct in saying that the video card makes a huge difference. But so does the processor. For that matter, so does having sufficient memory. If you don't believe me, read http://www.hardocp.com/article/2011/10/11/amd_bulldozer_fx8150_gameplay_performance_review/4 and notice how even the i5 2500k has nearly 50% more average fps (from 40.8 to 57.2) than the amd fx8150 on a fairly high-end AMD Radeon HD 6970 even at only 1920x1200 resolution and noAA/noAF. Then try extrapolating that to a 2560x1600 screen (1.78x the pixels) and that would be 23 average fps vs. 32 average fps -- the difference between smooth and choppy. Note that the same review has other games with no noticeable difference between the processors, but the only game of the few reviewed that I play happens to be Civ V.

How about a shooting it?

http://www.youtube.com/watch?v=LG6Qx127xgs from http://www.hardocp.com/news/2012/09/25/iphone_5_vs_50_cal/

I don't care for Anad's benches much because they seem to like synthetic compute benchmarks. That is really all kinds of not useful information for a game card. I want to see in game benchmarks. If any compute stuff is going to be benchmarked, let's have it be an actual program doing something useful (like Sony Vegas, which uses GPUs to accelerate a lot of what it does).

Personally I'm a HardOCP fan when it comes to benchmarks. Not only are they all about game benchmarks, but they are big on actual gameplay benchmarks. As in they go and play the game, they don't run a canned benchmark file. This does mean that it isn't a perfect, "each card sees the precisely equal frames" situation, but it is far more realistic to the task they are actually asked to do, and it all averages out over a play session. I find that their claims match up well with what I experience when I buy a card.

http://hardocp.com/article/2012/05/03/nvidia_geforce_gtx_690_dual_gpu_video_card_review is there 690 benchmark. It's a selection of newer games, generally played with triple head (the game displayed across three monitors at once) on a 690, 2 680s SLI'd and two 7970s CF'd.

A roundup of reviews from the usual major sites as well as others not mentioned in the summary above: Overclockers Review, Anandtech Review, Anandtech Undervolting/Overclocking, HardwareSecrets, Bit-tech, PCPer, Tweaktown, Hard OCP, The Inquirer, Techspot, Computer Shopper, Tom's Hardware, ExtremeTech, PC Mag, Overclockers Club, and Guru 3d

All the new generation, ALL that high price, and it still comes up close with amd's new cpus in multithreaded performance ?

http://www.hardocp.com/article/2011/11/14/intel_core_i73960x_sandy_bridge_e_processor_review/6

no wonder there have been 3 opteron (bulldozer) supercomputer orders in the last 3 weeks.

• Overclockers
• pcperspective
• Hardware canucks
• hardocp
• neoseeker
• tweaktown
• hexus

http://www.pcper.com/reviews/Processors/Intel-Sandy-Bridge-E-Review-Core-i7-3960X-and-X79-Chipset-Tested
http://www.hardocp.com/article/2011/11/14/intel_core_i73960x_sandy_bridge_e_processor_review
http://www.legitreviews.com/article/1773/1/
http://www.anandtech.com/show/5091/intel-core-i7-3960x-sandy-bridge-e-review-keeping-the-high-end-alive

The bulldozer architecture is heavily optimized for highly threaded applications with a heavy reliance on integer operations. This is well represented by today's server workloads, not todays desktop applications. But more importantly for AMD's future this also represents the trending path of tomorrows applications.

No it doesn't. AMD marketing would like you to believe every application is going to go massively parallel, but they're not the ones who actually have to write the software. It is not easy to thread all types of software (the low hanging fruit has already been picked), and it can be hard or impossible to get gains beyond two or three threads for many types of code.

A great example of this is Battlefield 3, where the 8150 outperforms the i72600k.

Er, what? The 2600k outperformed the 8150 when both were clocked at stock speeds. The 8150 won in the overclocked test.

I shouldn't use the terms "outperformed" or "won", however, as this test was very sloppily done. Carefully read the description. Apparently the BF3 beta lacks facilities for repeatable benchmarking, so they just played on a live server with real players. This guarantees lots of noise and poor repeatability. And you can see that noise in the data: the BD average frame rate went up when overclocked, but the i5 and i7 averages went slightly down. That shouldn't ever happen in a CPU benchmark, not when you're raising the clock speed of the processor by over 1 GHz.

In fact, note that all the average FPS results fall in the range ~50.5 to 54 regardless of CPU type and clock, and the overclocked i7-2600K loses to every non-OC result, including itself! This test isn't CPU limited in any way. It's just a fancy way of generating random numbers with no correlation to CPU performance.

Unfortunately today this also means thatwhether Bulldozer or Sandybridge is faster today depends on the application. As from the above test we can almost assuredly guess that BF3 does more integer work, while Civ 5 does more floating point work.

You're assuming games load up all cores. Few games use more than 2 or 3 cores, even recent releases. This is for two related reasons. First, it's hard to scale game logic to huge numbers of cores. Second, game developers know that it's only recently that new PC sales ticked over to a dual-core on average, much less quad or better, and they want to spend most of their time working on things which will benefit all their customers rather than putting out a lot of effort to help only the 5% or less who own high end hardware.

(This is also why SLI/CrossFire has always been plagued by poor game support, and ATI & Nvidia have had to try various schemes to incentivize developers to spend time on multi-GPU.)

Benchmarkers who managed to actually create CPU-limited gaming tests almost universally found that Sandy Bridge stomped all over Bulldozer. SB's per-thread performance is much better, which is a better match to today's (and tomorrow's) software.

As an aside, as a server administrator today I would buy Bulldozer over Sandybridge based processors in a heart beat. Most of the "scale out" boxes such as web caches, database servers, etc., are highly multithread integer driven workloads. In this case bulldozer is going to destroy sandybridge, plain and simple.

I think you're getting a bit ahead of yourself. Client BD certainly hasn't destroyed client SB, even in highly multithreaded integer workloads (it's more like it wins some, loses others), so what reason is there to believe anything will be different in servers? Keep in mind that Intel has yet to even release its high end SB CPU and platform (6-core/12-thread desktop, 6C/12T server, and 8C/16T server); all existing SB CPUs are mainstream desktop/notebook (4C/8T max with integrated gr

The correct phrase is: Relying on benchmarks that are not relevant to your application is a fool's errand.

Yes, yes, yes.

The bulldozer architecture is heavily optimized for highly threaded applications with a heavy reliance on integer operations. This is well represented by today's server workloads, not todays desktop applications. But more importantly for AMD's future this also represents the trending path of tomorrows applications. A great example of this is Battlefield 3, where the 8150 outperforms the i72600k. Unfortunately today this also means thatwhether Bulldozer or Sandybridge is faster today depends on the application. As from the above test we can almost assuredly guess that BF3 does more integer work, while Civ 5 does more floating point work.

However, less obvious than the multithreading issue is the push away form using the CPU for floating point operations. This is one both Intel and AMD having been slowly gambling on for quite some time, putting floating point operations on the GPU. AMD has just taken a more "committed" approach to this. Its also something that may pay off big time.

As an aside, as a server administrator today I would buy Bulldozer over Sandybridge based processors in a heart beat. Most of the "scale out" boxes such as web caches, database servers, etc., are highly multithread integer driven workloads. In this case bulldozer is going to destroy sandybridge, plain and simple. Also to those citing supercomputers, those tend to be floating point driven as they are generally for simulation.

It can work on any DX9 GPU without dedicated support. http://hardocp.com/article/2011/07/18/nvidias_new_fxaa_antialiasing_technology/1

Best possible? Maybe for single-card, single-display. But SLI scaling sucks compared to AMD's CrossFireX on their latest series.

by [H]ard|OCP
http://www.hardocp.com/article/2011/03/24/asus_geforce_gtx_590_video_card_review

from summary

"We truly thought the GTX 590 was going to make the Radeon 6990 look bad, but the fact of the matter is that NVIDIA made the 6990 look that much better. The GTX 590 is not the "World's Fastest Single Card Solution" as stated on our page 1 slides; the Radeon HD 6990 is very much retaining that title. Hail to the King, baby!"

According to this review, the 590 is actually pretty quiet.

The clock speeds were purposely lowered in order to keep the acoustics in check. This differs from AMD's explanation of down-clocking the core clock speed in the Radeon HD 6990 in order to keep power levels down within spec. AMD has focused majorly on power efficiency this generation, and NVIDIA is focusing on acoustics. To this, I will say that NVIDIA has succeeded. At idle and at full load while gaming, I simply could not hear this video card.

You missed Price... Price is still a big cause of piracy... and then you have obnoxious DRM which you claim is dead

I can name at least 2 PC games ive purchased, which i then obtained torrented copies, because it was easier to make the torrents run 'out of the box' than the purchased copies

As for DRM, theyre trying to use it as much as possible, though a few companies are getting the hint, most are pro DRM, and they heavier the better as far as theyre concerned. Then you have incidents like http://www.hardocp.com/news/2011/03/11/ea_forum_ban_prevents_game_access63/ getting a temp ban on a forum, which gets you banned from Single Player

Finally you have companies wanting the First Sale doctrine to be scrapped, as they dont want people buying second hand games/music/software as it hurts their precious business model of 'well make $x of every man woman and child in the world and if we dont, "ITS A LOST SALE TO PIRACY"'

Here is a little something I saw today that about sums up how ridiculous I think our current internet is:

http://www.hardocp.com/image.html?image=MTI5NjY2NzEwNHRrdERDNHBLY1ZfMV8xX2wuanBn
 

Sounds like you're talking about the quack.exe fiasco.

HardOCP is famous for their real gameplay ratings. They go and actually play through the game while testing performance. They then find the highest settings that the reviewer finds playable. Now while there is some subjectivity to it they do back it up with FPS numbers, and it is the same reviewer trying everything out. So it gives real, in game, actually playing, results. I find it maps nicely to what actually happens when I get a card and play games.

http://hardocp.com/article/2010/11/09/nvidia_geforce_gtx_580_video_card_review

http://www.pcper.com/article.php?aid=1034
http://www.hardocp.com/article/2010/11/09/nvidia_geforce_gtx_580_video_card_review
http://www.anandtech.com/show/4008/nvidias-geforce-gtx-580
http://www.legitreviews.com/article/1461/1/
http://www.techreport.com/articles.x/19934
http://www.bit-tech.net/hardware/graphics/2010/11/09/nvidia-geforce-gtx-580-review/1

The land wasn't so cheap, but probably cheaper than CA.