Slashdot Mirror
Haswell Integrated Graphics Promise 2-3X Performance Boost
crookedvulture writes "Intel has revealed fresh details about the integrated graphics in upcoming Haswell processors. The fastest variants of the built-in GPU will be known as Iris and Iris Pro graphics, with the latter boasting embedded DRAM. Unlike Ivy Bridge, which reserves its fastest GPU implementations for mobile parts, the Haswell family will include R-series desktop chips with the full-fat GPU. These processors are likely bound for all-in-one systems, and they'll purportedly offer close to three times the graphics performance of their predecessors. Intel says notebook users can look forward to a smaller 2X boost, while 15-17W ultrabook CPUs benefit from an increase closer to 1.5X. Haswell's integrated graphics has other perks aside from better performance, including faster Quick Sync video transcoding, MJPEG acceleration, and support for 4K resolutions. The new IGP will support DirectX 11.1, OpenGL 4.0, and OpenCL 1.2, as well." Note: Same story, different words, at Extreme Tech and Hot Hardware.
http://en.wikipedia.org/wiki/SGI_IRIS
is that Intel provides very nice open source drivers for their integrated GPUs
the Hot Hardware link confirms DisplayPort 1.2, which is the only thing I /really/ care about. The others are nice, but 4K out of the laptop means my next mid-range laptop can be my primary desk machine as well. This should push along the display manufacturers after their decade of stalling (perhaps soon we'll see screens in the 20-24" range with more resolution than our 5" displays have).
They might even be able to turn up their graphics in WoW now :D
Think of these chips with integrated graphics like hybrid cars. You're not gonna go down to the drag strip with them, or haul a camper, or pick up the 10 kid carpool group. But for the vast majority of trips you'll get to the same destination is basically the same amount of time, with less noise and higher efficiency.
Discrete graphics still significantly outrun Intel's offerings. We get a 150% performance increase when a 900% performance increase is warranted to compete with current cards (GeForce 680MX). Guess I'll never get integrated graphics if I can avoid it.
Intel isn't competing with discrete graphics solutions, though.
And yes, the speed increase isn't spectacular when compared to the other options in the marketplace, but they're not exactly "alternatives", and they're certainly not "competing".
- Nec Impar Pluribus, or so I'm told.
New Intel GPUs are surprisingly competent. No, they don't stand up to higher end discrete solutions but you can game on them no problem. You have to turn down the details and rez a bit in some of the more intense ones, but you can play pretty much any game on it. (http://www.notebookcheck.net/Intel-HD-Graphics-4000-Benchmarked.73567.0.html). For desktops I always recommend dropping $100ish to get a reasonable dedicated card but for laptops, gaming on an integrated chip is realistic if your expectations are likewise realistic.
Gone are the days of the GMA 950 that sucked at even simple GDI+ rendering. The integrated GPUs now are competent, though lower end (in keeping with their power profile).
Wouldn't these kinds of things be more accurately described as GPUs with integrated CPUs?
It's been 10 years since Intel started panicking when they realized a Pentium core could be tucked into a tiny corner of a GPU, as far as transistor count went.
(-1: Post disagrees with my already-settled worldview) is not a valid mod option.
Making a 4k display isn't as simple as manufacturers just wanting it bad enough. I know people like to look at little phone screens and say "If these can be high rez, why can't big displays be higher rez!" but all that shows is a lack of understanding of the situation.
Transistors cost money and pixels require them. How many pixels a display has is not a small part of its cost. So you can't just say "Let's have 4k or 8k desktop displays, should be hard!" because it in fact is.
That isn't to say we won't, it is coming, but it will be some time.
Also there are plenty of other technologies that you need for higher rez like interconnect speed (as you note with DP 1.2), video memory, video processing power and so on. Display makers haven't been "stalling" it is something that hasn't been very doable. If you looked around, you could find that there were (and are) a few examples of higher rez displays but they were expensive and plagued with issues like low refresh rate and requiring multiple dual link DVI connections to run.
Seriously, people need to stop pretending like companies could just give us some awesome new technology if they wanted to bad enough. No, not really. There's a lot that goes in to something like a higher rez display. You don't just wish it into existence.
So chill. Higher DPI displays will happen at some point, probably sooner rather than later. However it isn't a situation of "stalling". It is a situation of R&D, production costs, and all the technology needing to exist.
If you want a 4k display right now, go get a Sony PVM-X300. It's a no-shit 4096 x 2160 30" display. Just don't bitch about the cost.
You mean a $300 part that is a CPU and GPU combined has a slower GPU component that a $500 dedicated GPU? Shocking. Utterly shocking.
So unexpected that you can't even name one!
Intel GPUs are fine for 99% of use. Heck, most games run fine on them. Sure the latest Call of Honor: Medal of Duty will not run on UItra, but most games will be fine on medium and low settings.
Performance improves in ways you might not even expect.
I guess it improves it in such an unexpected way I didn't even notice. In the two desktop computers I have in my household, I originally built them using integrated video cards and then upgraded to discrete cards couple months later when I had some more time to pick out something and some spare cash. Neither my wife nor I noticed any difference in normal desktop performance for office related software or web browsing. The only difference seen was in video games. My work issued laptop has integrated GPU, and I'm not sure what performance could be improved on it other than maybe a faster hard drive (there is only so fast I can type, click through documents, and my code runs on a cluster instead of locally...).
Or to put it in automotive terms: even a family car needs the ability to get onto the highway without being a threat to public safety.
Yes, while this is true, it really isn't relevant. You look foolish if you try to claim hybrids are not usable because they can't drive at highway speeds as they are already capable of that. Likewise, integrated GPUs are quite fast enough for a the vast majority of basic computer use and only a hindrance to specific uses that many people may or may not need (i.e. not every one does high end gaming, video editing, etc.).
Except your analogy is total nonsense. Modern operating systems do in fact benefit from having a decent discrete GPU. Performance improves in ways you might not even expect.
Nope. They benefit from having 3D acceleration, yes, but the integrated graphics on modern Intel chips is a discrete core. It just happens to be on the same die as the CPU. My laptop's CPU is clocked at 1.2GHz dual core, with two extra cores for the video clocked at 300-500MHz. Those cores are dedicated to the video only, and it's *plenty* fast enough for normal use on the operating system, with all of the blingy effects. Switching to a discrete graphics card won't make any difference at all, because the video cores are physically separated from the CPU cores, and have a completely different execution pipeline so wouldn't be able to run OS calls anyway.
Intel's integrated video is enough to run most games these days. I game on that laptop and while the graphics aren't as fast as my desktop's 6970, they're plenty adequate for gaming on the go... and I'm not just talking about ancient games here, either: it's good enough for Civ5 in WINE, and also for stuff like Torchlight II, which it'll run at max on the laptop's 1366x768 screen. You won't be playing the latest Call of Duty at maximum settings on a dual 1920x1080 display with Intel's integrated graphics, but then again, the people who want to do that won't be bothering with integrated graphics to begin with, will they? A significant portion of Steam's userbase are using Intel integrated graphics these days....
Wow so rather than the 11 FPS you were getting, you might be able to get 22 FPS!
You can almost play a video game at those speeds! Well done!
The technology is out there, witness the few korean dead-cheap dumb high-res screens.
They only cost more than similar lower, hd-res of the same featureless no-name brands.
What is lacking is a huge market, so economy of scales kicks in and produced ueber-high-resolution screens is worthy.
Currently the biggest chunk of all produced flat pannel end up in TV screens. It makes more sense economically for the constructor to just put the same pannels into computer screens, than to market a special different type of pannels with higher res targetting the small niche market of users who want a PC monitor *and* also want higher resolution.
At least we can count on Apple and their "retina" buzzword to make higher resolutions fashionable, and thus increase enough demand that the big brands will start noticing.
Meanwhile, try to get a no-name high-res IPS pannel imported from korea on ebay.
"Sufficiently advanced satire is indistinguishable from reality." - [Tips: 1DrYakQDKCQ6y52z6QbnkxHXAocMZJE61o ]
http://www.engadget.com/2013/04/12/seiki-50-inch-4k-1300/
$1300 for a 4k display. Granted, it's locked to 30Hz, but for most of us 60Hz will be as fast as we need to go (though we'll get more for that god-awful 3D crap they keep trying to push). 4k @ 50 is very close the 2560x1600 30" monitor I have for pixel size, which is fine enough for me at my working distance.
We stalled at 1920x1080 because every moved to TV production. Now that 4k/8k has broken free, we can get over that hump. Not saying there aren't hurdles, but the consumer-limit has been breached and I expect the next to years to result in a shift. Note: there is no material broadcast at 60 frames at 1080, but people are all bonkers over 240Hz displays anyway. They'll be the same ones who wanted 1080p devices to watch their (upscaled) DVDs.
Is it just my observation, or are there way too many stupid people in the world?
Haswell parts are expected to be 10-15% faster than Ivy Bridge, which was itself barely any faster than Sandy Bridge.
Anyone remember the days when computing performance doubled or even tripled between generations?
I have a desktop PC running a Sandy Bridge i5-2500K running at a consistent 4.5GHz (on air). At this rate, it could be another couple generations before Intel has anything worthwhile as an upgrade... I suspect that discrete-GPU-buying home PC enthusiasts are going to continue to be completely ignored going forward while Intel continues to focus on chips for tablets and ultrabooks.
No benefits to a discrete GPU?
Ripping/Transcoding (thank you CUDA and OpenCL)
Running games at resolutions and detail levels that look better than doom
Image processing (thank you CUDA and OpenCL)
Video decoding/decompression (thank you CUDA and OpenCL)
Intel is doing remarkably with with HD4000, and OpenCL performs pretty well, but that won't come close to matching the 48 to 3072 GPU cores present in modern discrete video cards.
The Christian Right is Neither (Christian nor right). See: Matthew 23, Matthew 25, Ezekiel 16:48-50
IIRC transcoding / decoding with Intel's quicksync is actually VERY competitive with a discrete GPU. And all of those CUDA / OpenCL tasks are hardly representative of the average user.
As parent said, for the 99% use case, Intel integrated are sufficient.
Of course, when it comes down to raw performance comparison for high performance applications integrated solutions won't be able to keep up with current discrete solutions.
But when you take other criteria into account like the volume that is used by discrete hardware in a casing, the energy consumption and subsequently the need of a cooling systems, then integrated solutions become a lot more attractive.
They probably use the SIMD instruction set (aka SSE, formerly MMX) for parallelization. Honestly, I'd rather write to a GPU using a common language, but parallel technology does exist on the CPU. Inflexible, single purpose parallel instructions, but ones that would work for that task.
thank you CUDA and OpenCL
OpenCL-heavy tasks can be done on a compute server at home or in a data center, and you can SSH (or VNC or RDP or whatever) to use an application on a compute server from your laptop. The only real use case I see for carrying an OpenCL powerhouse with you, apart from running shaders in a high-detail 3D game, is for editing huge images or high-definition video in a vehicle or some other place with no Wi-Fi. One workaround is to downscale the video to low definition (e.g. 320x180), edit the low-definition video while away from the net, and then export the edit decision list (EDL) back to the compute server to render the result in high definition. I used to do that with AviSynth.
Running games at resolutions and detail levels that look better than doom
Games are the other reason for carrying a beefy GPU with you. But Skyrim looks better than Doom, Doom II, and Doom 3, and Skyrim runs playably on the HD 4000 at 720p medium.
actually, video editing doesn't really benefit from a discrete GPU since the damn encoding support is still crap. Most of the various software I've looked at still get more bang from a better CPU then GPU encoding and if you're in the industry like ILM/Pixar, then you aint using GPU encoding anyhow - its mainly dedicated ASICS and such. For someone doing it as a hobby, they're buying a video card specifically supported by their software so it makes no god damn difference to 99.99 percent of the folks out there that onboard graphics suck.
In my case, small business owner; I've been planning a new build for 4th quarter (part of my 4yr replacement cycle) based on a Xeon E3 1275 with onboard graphics because the system purpose doesn't need much in the way of a GPU. It's a development system (builds and Database work) so why waste money. Hell all of my employees systems are onboard graphics just to save a few bucks that's better spent on more ram or a slightly better cpu. As with anyone, trade-offs are required when building/specing our systems and as a business, we tend to go with the cheapest configurations we can get. Keep in mind that the cheapest configuration does not mean the cheapest parts. We learned a long time ago that spending a bit more for quality hardware resulted in less downtime.
Mod me up/Mod me down: I wont frown as I've no crown
How long until we finally have Intel and other CPU vendors create a unified memory model now that we have a GPU on die? I mean if anything I'd think the point would be to have your on-die GPU integrate with a discrete card so that both low and high-end setups gain something from this. PS4 will have a unified memory model; how long until the rest of us do on our desktops?
And all of those CUDA / OpenCL tasks are hardly representative of the average user.
There's a meme lately in Slashdot comment sections that everything must be made for "the average user" without any room to grow. I see it popping up whenever anybody mentions limits of a product sold to the public, especially artificial market-segmenting limits. Where did it come from?
Only they are failing to compete with $20 cards as well, and their best offering is smoked by SOC (sorry, lingo - System On a Chip) like the AMD A10 in the graphics department.
In the two desktop computers I have in my household, I originally built them using integrated video cards and then upgraded to discrete cards [...] The only difference seen was in video games. My work issued laptop has integrated GPU, and I'm not sure what performance could be improved on it
That's because your work laptop's work load probably doesn't have any 3D. If your job description included CAD or other 3D modeling, you might notice more of a difference with a beefier GPU.
not every one does high end gaming, video editing
Room to grow is another factor. Consider someone who buys a computer and then decides he wants to do non-Flash gaming or edit high-1080p video from his smartphone's camera. Suddenly his laptop has become obsolete. Is he necessarily going to have the money to buy a whole new laptop?
The 680 isn't mainstream, by any means. Haswell brings the higher-end iGPU up to the performance levels of a GeForce GTX 650, which definitely is more mainstream.
When AMD makes a decent open source driver I will use their graphics cards. So far I use intel GPUs and Nvidia ones.
You're in luck. AMD's open source driver trounces NVIDIA's.
The Iris Pro has similar performance to a GeForce GTX 650. Please let me know where you can get a GTX 650 for under $20.
You'd have to go back more than one generation to find an Intel iGPU that is slower than a $20 discrete card.
Yes, you have to back off on rez and settings. Guess what? That's fine, and expected for something as low power profile as an integrated GPU. Fact remains you can game on it just fine, even new games
One could game just fine on an original PlayStation or a Nintendo DS, and new DS games were still coming out until perhaps a few months ago. It's just that the settings have to be scaled so far back that things look like paper models of what they're supposed to be. The DS in particular has a limit of 6000 vertices (about 1500-2000 polygons) per scene unless a game enables the multipass mode that dramatically lowers frame rate and texture resolution. Fortunately, the HD 4000 in Ivy Bridge runs games with detail comparable to the PS3.
Wow, that will bring it up to almost the same speed as the 2 year old AMD APUs if I'm not mistaken, lol. Talk about being behind! I was amazed when the first couple P-series graphics adapters came out built into the first Sandy Bridge chips. You could actually play Skyrim on an i3-2100 at low settings and it killed at HD video playback. Now for $110, my demo unit at my shop is an A10 APU with a 6.9 graphics rating. It can play Starcraft II at almost maxed settings at 60FPS at 1280x1024 and the CPU is just a hair slower than an i5-2400 for a crap-ton less money. At least $60 if I remember correctly. The 1866 native memory controller helps too since even Ivy Bridge only hits 1600. So then it's better at video encoding and gaming than any i5. Intel is really playing catch-up at this point. I don't know why everyone's all doom and gloom over AMD getting crushed by Intel. I would have thought that was over by now, especially after releasing Trinity, Zambezi, and Vishera. Those 3 really are better than Intel in almost every way.
Twice nothing is still nothing, although getting a 1.5x increase for low-wattage applications is nice to hear.
End result, I'm still going to get people complaining to me that The Sims runs slow. Only difference is it'll be stop-motion instead of slideshow.
If we colonize Mars, it won't be the World Wide Web anymore. UWW?
I do HPC engineering for a living, and I really don't see the point in private discrete GPUs anymore. We've added 8000 Teslas to our cluster, and I've come to prefer using them over CPUs simply for performance reasons. But likewise I've come to prefer IGPs to discrete cards for private use in the last 2-3 years. There is no game that isn't playable on an Ivy Bridge IGP (last I've run is Skyrim on 1920p and settings in the middle between average and max, 40-50 FPS), the power usage is lower (in general but also when watching movies), complexity is tremendously lower (which translates into more stable drivers), it's cheaper and fwiw lighter.
Sure, if you're a CAD guy or 3D artist, you'll be able to to bigger stuff faster, but apart from those highly specific needs by a tiny part of the population (who can and should buy "specialised hardware", that means discrete GPUs), there is little advantage over IGPs.
You mention transcoding media, hardly a common task, but what's the problem with one core chugging away at it in the background while you use your other system resources? A GPU may do it quicker, but either you can't use it to it's full capacity for transcoding while at the same time playing that AAA title, or you're not needing the resources at the moment anyway, so "quicker" becomes nothing but a luxury.
VIdeo decompression is a moot point, as 500 MHz ARM chips can do full HD via DSP decoders, and you've got plenty of the latter on modern x86 chips.
The only somewhat "valid" point is e-peen: you'll get higher benchmark scores and feel better for having high-end hardware, which is up to everyone personally. I like the feeling of my tiny little "thingie" reaching the same goals more efficiently, with lower power usage, thermal emission and complexity.
captcha: tearful
Perhaps this will convince NVIDIA not to underclock their GPUs. Now that the baseline is much higher, they will have to deliver awesome performance to be relevant in the notebook scene.
er, no. While I agree these chips are great for most uses (I have them in 2 of my 3 primary computers at home), if you want to game at all, you need something more. Even low-requirements WoW is basically unplayable on the latest 4000 series chip on medium settings even if combined with a quad core i7.
Yeah but last I checked even a lousy $30 discrete just curbstomps them and likewise the AMD APUs beat them pretty badly in the GPU dept.
So unless they pulled a rabbit out of their hat I'll be telling folks the same thing I have always said about Intel IGPs, which is good for office units and not much else. I mean sure for spreadsheets and basic video they are fine, but IMHO you are better off getting even a low end discrete over using the Intel IGP.
ACs don't waste your time replying, your posts are never seen by me.
I can, try a hardware accelerated desktop in Win 7 or 8 and then try the same without the acceleration, with will be MUCH more responsive and snappy. Also by taking some of that load off the CPU you leave more cycles for the jobs that the user cares about, another benefit.
ACs don't waste your time replying, your posts are never seen by me.
Haven't looked at the latest cards, have you? One of the reasons that AMD went with GCN over their previous VLIW design is that GCN allows for core parking, with core parking when you are doing non GPU intensive jobs the GPU can put to sleep all the cores you no longer need thus bringing the wattage and heat WAY down, down almost to IGP levels without having to be stuck with only IGP levels of performance.
And as far as noise goes most of the cards have a passively cooled variant, can't get more quiet than that and again without giving up the huge performance advantage the discrete cards give you.
ACs don't waste your time replying, your posts are never seen by me.
Only they are failing to compete with $20 cards as well, and their best offering is smoked by SOC (sorry, lingo - System On a Chip) like the AMD A10 in the graphics department.
The AMD A10 is not a "SoC" any more than Intel's offerings are. Both AMD and Intel are currently offering CPUs with integrated GPUs – it's just that the marketing is slightly different, and that each company emphasizes its own strength (AMD has better GPUs, Intel has better CPUs).
For these to reasonably be considered a "SoC", the whole northbridge (or whatever they're calling it now) would have to be moved onto the main die. That hasn't happened yet, though Intel is starting to move that way with Haswell.
You mention transcoding media, hardly a common task, but what's the problem with one core chugging away at it in the background while you use your other system resources?
Also note that Intel's recent IGPs (from Sandy Bridge onwards) have a dedicated video transcoding block, and it's much faster than using all your cores to transcode. It's also faster than discrete GPU video transcoding. Literally the only caveat is that a particular software encoder might produce higher quality results (but Intel is working on that, and they'll be on third generation transcoder hardware/firmware by Haswell).
I'm well aware of this and it only addresses the power consumption of the system and not the additional space discrete hardware requires. I wasn't talking about the noise cooling systems will generate.
Where space is limited, like in most hand held mobile devices, APUs have advantages over discrete CPUs and GPUs, despite their lower raw performance. Also the new gaming console from Sony, the PS4 will use an IGP from AMD, based on their A10 APU.
arstechnica has a more in-depth look [including architectural details] at:
http://arstechnica.com/gadgets/2013/05/a-look-at-haswell/
Like a good neighbor, fsck is there
Best quality encoding is always done in software because it requires multiple passes, however, when you're talking about actual editing, effects and such (even a simple blur) benefit from GPU support by an order of magnitude. Image processing is massively parallel. Ever use Apple's motion, for example? It's GPU support allows you to do in hardware in real-time what used to take hours in After Effects, where the GPU support sucks.
When you're doing any sort of composting or image processing, you need a GPU if you want any sort of WYSIWYG capability. Oddly enough, though, when it comes to production quality 3d rendering, many of the best renderers, such as Pixar's Renderman, are entirely software (some others do use GPU assist, but almost none are pure GPU). This will likely change in the future as brute force path tracing and MLT becomes more reasonable to do on GPU, but for the moment, software is still king.
The fastest $25 graphics card on newegg is a radeon 5450, which even the current HD4000 beats.
If we allow up to $50, we get a GT620, which still gets narrowly beaten.
You need to get to $75 cards to find ones that beat the current HD4000, and will be about level with the GT3e. The current AMD A10 graphics are about 40% faster than the HD4000, and hence will be about 42% slower than the GT3e.
So no, we're not seeing any kind of kerb stomping here.
Actually, the whole north bridge is on the chip, and has been since LGA1156 for intel. For AMD, they only moved it on with socket FM2 (the most recent APUs).
The only thing that's external is the "platform host controller", which is a renamed south bridge. Haswell is integrating chunks of the south bridge onto the CPU too.
Both Sony and MSFT chose the APU because of PRICE because they plan on it being another pricing slugfest and you watch, it'll bite them both right in the ass. Don't get me wrong, for something like a netbook or a tablet where there literally is no room for a fan to move any air? Then an APU makes perfect sense, it also makes perfect sense on an office box where all they will be doing is non graphics intensive tasks like spreadsheets.
Mark my words it won't take game devs a year and a half to totally max out the Jaguar APU and then for the rest of the life of the console it'll be hamstringed by the APU, because the jaguar is based on bobcat which was AMD's answer to the ATOM, it was NOT designed to perform heavy lifting, nope it was built to be cheap and run at a low enough power it could be used in netbooks and tablets while still besting Intel Atom in just about every way.
Again don't get me wrong, I own an Asus EEE that has the E350 Bobcat APU and it does beat atom pretty badly, hell i can even play games like Torchlight and L4D on the thing, but compare it to anything other than an Atom, even as low as a Celeron, and its just gonna get creamed. Again this isn't a big deal in a portable, but in a game console where its gonna have to do 1080P with ragdolls and physics? yeah its not gonna take long at all for the game devs to be hamstringed by the jaguar APU and its lack of performance. Hell friend check out this comparison chart of the E450 (which the jaguar is based on) and other chips, even the 1.2GHz Celeron beats it by nearly 10%.
So I don't know WTF Sony and MSFT were thinking except "We gotta get the cheapest thing we can so we don't lose our shirts in the price war" because that quad core A series APUs you find in the $399 Worst Buy specials will be able to cream their brand new console on launch day. Only the fact that a console OS is so tiny compared to a full OS (although to be fair the console OSes have been bloating up with all the new features both sides has been bolting on) and the fact the game devs can optimize the living shit out of their code will buy them some time but if it takes even 2 years to max out those chips it'll be a miracle.
ACs don't waste your time replying, your posts are never seen by me.
Yeah, no argument there when it comes to desktop performance and high performance tasks. Here users want performance and they get performance with advanced discrete hardware. I would neither choose an APU over discrete hardware in my desktop machine nor recommend it to other people who use their computers for similar task, because here I prefer modularity.
And sure it won't take game devs very long to find the boundaries of APUs, that's a problem for any system where hardware is difficult to upgrade or cannot be upgraded, like in gaming consoles. Discrete hardware won't do much for these devices since those are not meant to be upgraded by the consumer, because that might be too inconvenient to have the user worry about these 'highly complex' problems. And this is where such solutions are used, because of the price, price of the hardware, price of the space required for hardware and cooling system and the simplicity of not having to deal with additional hardware manufacturers.
Enough reasons to justify the use of an APU from an economical perspective.
What I don't get is the hate companies like Intel or AMD receive in this 'war'. I as a user choose whatever is best to complete the task in and for a set time frame, I see no reasons to be a loyal customer to any of those hardware companies, whether it is Intel, AMD or nVidia.
Bottom line: The worst thing about this is that Intel will use their IGP to justify higher prices of their products and dump them on everyone, no matter what tasks their product is going to perform, like high performance gaming where discrete GPUs are common. Currently they don't leave you a choice like AMD does.
I don't "hate" the APUs in any way, as I said I have an E350 APU netbook and for the tasks I perform on a service call, checking wired and wireless networks, downloading drivers, hell even watching videos on it is just fine.
I think the problem people have with the APUs is that they are being pushed, especially by Intel, into places where they just don't belong. For example if one is building a gamer PC then the GPU on that new Intel chip is not only pointless it is hamstringing the rest of the chip by adding heat and limiting how far you can OC, they have found the same to be true of AMD APUs where the CPU clocks are being hampered by how fast the GPU can go.
But the problem with both the X720 and PS4, and this is coming from somebody who owns and builds AMD exclusively and have for over 5 years is NOT that its an APU, its what KIND of APU they chose. if they would have chosen the A series which was based on Liano and then piledriver? Sure it would be great, those chips make great HTPCs and with some GDDR 5 would make sweet gaming consoles. The problem is they went with Jaguar which...its just not made to do that, its like trying to pull a boat with a Kia. Look up the specs on Jaguar yourself and prepare to go WTF as it is based on Bobcat which is a VERY limited APU designed to go up against Atom and nothing else, its cores are MUCH more primitive than even a K8 which means a first gen Athlon X2 is gonna best it when it comes to number crunching...and you are gonna put that in a system that requires 1080P and heavy physics?
Second of all its using the same mistake of a layout for their chips that the "now infamous" bulldozer used which is a "half core" design. All you have to do is read any review of the bulldozer to see that its a SERVER chip that AMD had to force out as a desktop because the previous CEO did a slash and burn and fired nearly all the engineers so he could get a stock bounce and cash out. but here we are talking about a console...can you think of ANYTHING that is more unlike a typical server load than playing video games? BD makes a great server chip because a good 90% of the work a server has to do is highly threaded integer heavy loads, most games hit one or two cores very hard and are heavy on floating point which is the weakest part of the half core design.
Finally you have the fact that because they went the bulldozer route of "half cores" what you have is NOT an octocore but a quad core with hardware assisted hyperthreading, which again would be curbstomped by that $65 Athlon quad and which makes no sense when it comes to video games as you are taking a lightly threaded FP heavy load and sticking it on a chip designed for heavily threaded integer loads. So the whole thing makes no damned sense!
But as far as Intel goes...don't buy 'em, ever since i heard about how Intel was bribing OEMs and rigging their compiler I've been avoiding them like an STD and have never been happier. I have found that MAYBE 5% of the population are doing jobs that require every cycle they can get, the rest are just as well served by that $45 Athlon triple (that just FYI I've been seeing better than 75% core unlocks with) so I not only take every chance to tell folks they don't need Intel's douchebaggery but i put my money where my mouth is, 5 desktops a laptop and a netbook in my family and they are ALL AMD. Hell Tigerdirect has been selling the 1045T hexacores for just $89, that is cheaper than the bottom of the line crippled Pentium Dual. The bang for the buck from AMD is just awesome ATM, better than it has ever been, and thanks to how long they stick with the AM socket you get plenty of upgrade options down the road.
But lets face it Intel should have been busted for antitrust over both AMD and how they locked Nvidia out of the chipset market so they could keep the whole thing for themselves, so Intel using this to force APUs where they don't belong and adding a price raise to boot really shouldn't be surprising as they are a pretty douchey company. I'm just glad we still have AMD to give us choice and at such cheap prices to boot.
ACs don't waste your time replying, your posts are never seen by me.
Yeah it's curious how AMD advertises their Vishera processors as high performance 8-core gaming processors. Most operations games do on the CPU are floating point based geometry calculations.
For my last hardware upgrade I've chosen an i5-3570k over an FX-8350. Because I often use my PC for gaming I didn't see that much advantages of AMD over Intel on this topic. I did see the higher power consumption of the FX-8350 under full load, which would have made the 20€ I would have saved by buying the AMD appear on my energy bill after about 8 months at today's energy prices in Germany (I pay 0.28€ per kW/h).
Before that I used a Phenom II x955 because it seemed to be the more sensible choice over the Core 2 CPUs back then. I'm more of an opportunist here than loyal to some companies philosophies, which are often circumstantial. So I picked the i5-3570k and ignored how useless its Intel HD 4000 graphics are in comparison to the Radeon HD 7870 that I also bought. I would have bought an i5-3570k equivalent without the IGP, but Intel offer those for a reasonable price.
So yeah, I totally agree that Intel is dumping their APUs where they don't belong simply to justify higher prices.
I went with a 1035T myself when those hit $100. Runs at 2.6 when all cores are in use and ramps up to 3.1 when I'm playing most games so i get the best of both worlds, a fast triple for gaming and a full hexacore for video transcoding or editing my multitrack recordings. of course the fact that I can (and have on several occasions) play a game AND transcode a video AND burn a DVD certainly helped make up my mind ;-)
But I see no point in going with the "half core" chips, i really don't, as the bang for the buck just isn't there and as you noted they are power pigs. in tests they had to get the half cores a full 1GHz higher than the Phenom II chips to beat the Phenom and of course adding that kind of OCing makes it just belch heat and go through power like a drunk hitting a free minibar. honestly i'm glad that they got the game console gigs because hopefully that will give them the needed capital to get rid of the half core design and get something better, maybe as that article I posted suggested and going back to the K8 the way Intel went back to the P3 to make the Core.
Luckily thanks to the long life of the AM socket neither me nor my customers HAVE to go with the half core, as there is plenty of AM3 and AM3+ Phenoms and Athlons for sale and frankly THAT is where the bang for the buck is right now not only in AMDLand but IntelLand as well, you can get an Athlon triple for around $45 that has a better than 3 in 4 chance of unlocking the fourth core. I mean a triple with a great chance at getting a quad, for less than $50? Not to mention the 1045T chips are selling for just $89, that is crazy cheap for 6 full cores.
BTW if you ever decide you'd like a faster chip check out StarMicro as I can't say enough good things about them. Been buying chips from them for a couple of years now, never a bad chip and fast shipping, in fact I have an Athlon X2 ULV coming the first of next week from them so I can retire that aging Sempron I use as a nettop at the shop. as you can see they sell both Intel and AMD and go back several sockets so its easy to take an older machine and give it a nice kick in the pants.
But I agree that while APUs have their place they just aren't suitable for every task and Intel is trying to stuff those things into places where they do NOT belong just so they can squeeze more $$$ out of the consumer. Considering the lead they have on chips trying to bleed more money out of the consumer seems extra dickish to me, but then again Intel has never been a nice company.
ACs don't waste your time replying, your posts are never seen by me.