|
I wonder if they are trying to do a small on die FPGA for dynamic instruction set add ons or something. Like if there is some cool new encryption algorithm or something they could just sell the fpga program as an add on, instead of waiting for it to be added and tested in a brand new processor, which also lets them do hardware patches like that one thing that haswell hosed up or whatever.
|
|
#
?
Jun 2, 2015 16:55
|
|
|
|
| # ? Apr 27, 2024 21:11 |
|
|
Five years of these CPU releases that barely budge the performance needle. This is really getting tiresome.
|
|
#
?
Jun 2, 2015 17:09
|
|
|
HalloKitty posted:Holy poo poo snacks, those iGPU numbers are seriously impressive. Well, they out-AMD'd AMD in that market, and now it's looking reasonable to build an HTPC/entry level gaming machine with no GPU. That's one hell of a small, efficient box. Well for HTPC at least ARM based systems are much much smaller and more efficient and cheaper than anything you'll get from Intel or AMD. You can build a nice Pi2 HTPC for 1080p that never draws more than 4W for $50, good luck doing that with x86.
|
|
#
?
Jun 2, 2015 17:13
|
|
|
Pryor on Fire posted:Five years of these CPU releases that barely budge the performance needle. This is really getting tiresome. so is this
|
|
#
?
Jun 2, 2015 17:13
|
|
|
go3 posted:so is this Great post, thanks for contributing! Really if we had anything even resembling a worthwhile anti trust body in this country Intel would be broken up and forced to compete again. At this point I wouldn't even be surprised if they started decreasing performance while increasing prices, nobody could stop them.
|
|
#
?
Jun 2, 2015 17:18
|
|
|
If desktop users were a big enough market they would probably focus more on products for us but it makes more sense economically for them to focus on servers and mobile. Extracting more single-threaded performance at this point is difficult and expensive, so combined with the shrinking desktop market they don't have the financial incentive to really put a lot of effort into it.
|
|
#
?
Jun 2, 2015 17:23
|
|
|
Intel has been focusing on cutting power and increasing GPU performance with great gains but because CPU performance isn't going up like it used to they just aren't trying
|
|
#
?
Jun 2, 2015 17:24
|
|
|
We are literally going to run out of atoms to shave off the transistors in the next 5 years because Intel is being a complacent, anti-competitive monopoly.
|
|
#
?
Jun 2, 2015 17:36
|
|
|
Pryor on Fire posted:Five years of these CPU releases that barely budge the performance needle. This is really getting tiresome. From a power users perspective yes but when it comes to mobile, efficiency and datacenter things have drastically improved but we don't see much of that. Looking at the current roadmap I'm not even sure if Cannonlake will be much of a upgrade.
|
|
#
?
Jun 2, 2015 17:49
|
|
|
The iGPU numbers blew me away. There is hope now that even if AMD dies I can have a tiny form factor gaming PC. I wonder if nvidia will play nice with intel iGPUs when DX12 launches.
|
|
#
?
Jun 2, 2015 17:50
|
|
|
Pryor on Fire posted:Five years of these CPU releases that barely budge the performance needle. This is really getting tiresome. Pryor on Fire posted:Really if we had anything even resembling a worthwhile anti trust body in this country Intel would be broken up and forced to compete again. At this point I wouldn't even be surprised if they started decreasing performance while increasing prices, nobody could stop them. How would you even break Intel up? Split design teams? Split design from silicon/process? I don't see how any of these actually improve CPU performance since those gains take a lot of careful research. You can't really will them into existence, free market worship or not.
|
|
#
?
Jun 2, 2015 18:06
|
|
|
How are you getting that ARM is beating Intel?
|
|
#
?
Jun 2, 2015 18:09
|
|
|
Tab8715 posted:How are you getting that ARM is beating Intel? Well, unit sales of smartphones + tablets vs laptops paints a pretty dire picture. Then you look at CPU sales in USD and realize its a false comparison.
|
|
#
?
Jun 2, 2015 18:10
|
|
|
Shipping 1000:1 is a nice start. If we're comparing dollars for some reason I'd prefer it be market cap, why exactly would per-unit cost merit any discussion? I posted the mechanism by which higher volumes train competitors to come up the stack towards premium products. Did you have some metric where you thought Intel was ahead?
|
|
#
?
Jun 2, 2015 18:14
|
|
|
Let's take one step back, what is and why are we measuring by market cap?
|
|
#
?
Jun 2, 2015 18:15
|
|
|
JawnV6 posted:Shipping 1000:1 is a nice start. If we're comparing dollars for some reason I'd prefer it be market cap, why exactly would per-unit cost merit any discussion? I posted the mechanism by which higher volumes train competitors to come up the stack towards premium products. Did you have some metric where you thought Intel was ahead? Profitability, market cap, and a lower price/earnings, especially vs the major ARM manufacturers like Qualcomm. Intel's margins are enormous compared to them. Growth could be a problem, I'll give you that. Right now Intel is making money hand over fist. Because anybody can make ARM chips, they are doomed to become a commodity.
|
|
#
?
Jun 2, 2015 18:18
|
|
|
There's no question Intel is coming from behind in the markets ARM rules, but they are coming. First they were getting design wins in tablets, then smartphones, soon smartwatches and other devices. They are losing a billion dollars a quarter on muscling into mobile and yet they are operating at a tidy profit so I imagine they're prepared to continue that spending for as long as it takes.
|
|
#
?
Jun 2, 2015 18:21
|
|
|
It was probably pretty stupid of Intel to let go of Xscale and then not to jump on the iphone CPU but a couple of years ago people still laughed at the idea of an x86 Intel CPU in a phone, and yet now they're shipping competitive phones and small tables. Yeah I'm annoyed by the lack of progress in desktop performance but sadly there just hasn't been any reason for masses to demand that. Most people just need to run Office/Chrome poo poo that even my ancient Core 2 Quad does perfectly fine. Even games don't need a top-end CPU, so really you're only looking at a small subset that needs to run calculations or rendering on their desktops, which is a tiny minority of users. It's not the lack of competition, it's the lack of demand, mostly.
|
|
#
?
Jun 2, 2015 19:08
|
|
|
Rastor posted:There's no question Intel is coming from behind in the markets ARM rules, but they are coming. First they were getting design wins in tablets, then smartphones, soon smartwatches and other devices. They are losing a billion dollars a quarter on muscling into mobile and yet they are operating at a tidy profit so I imagine they're prepared to continue that spending for as long as it takes. I doubt the mobile market wants to pay $380 for a CPU in a $600 phone. They'll gladly accept intel's bribes, go thru the motions and release some android device. Windows phones and tablets are another story, not a relevant one for now.
|
|
#
?
Jun 2, 2015 19:09
|
|
|
mobby_6kl posted:Even games don't need a top-end CPU, so really you're only looking at a small subset that needs to run calculations or rendering on their desktops, which is a tiny minority of users. It's not the lack of competition, it's the lack of demand, mostly. And for any kind of professional rendering or hardcore scientific calculations, you end up with a dual socket Xeon workstation from a real OEM, and then stuff it full of 64+ GB of ECC RAM. And most/all scientific calcs and render jobs are stupidly multithreaded, so they scale really well to 8/12/24 cores of Xeon goodness @ 3ghz. And that market is a shitload bigger and higher margin than gamers will ever be. For everyone that seems to think that processors should keep getting faster and faster, keep in mind that at 5 Ghz, light travels about 6 cm per clock cycle in vacuum. On a decent sized processor core, that's not exactly a huge margin of error for total signal propagation.
|
|
#
?
Jun 2, 2015 20:59
|
|
|
Pryor on Fire posted:Five years of these CPU releases that barely budge the performance needle. This is really getting tiresome. lol ok. (Games are not the performance needle, sorry  )
|
|
#
?
Jun 2, 2015 21:09
|
|
|
theres like, haswell-e for you dudes that need faster anime encodes
|
|
#
?
Jun 2, 2015 21:13
|
|
|
karoshi posted:I doubt the mobile market wants to pay $380 for a CPU in a $600 phone. They'll gladly accept intel's bribes, go thru the motions and release some android device. Windows phones and tablets are another story, not a relevant one for now. Maybe I'm misunderstanding you, but nearly all the x86 phones are Android. Why do you think x86 requires Windows?
|
|
#
?
Jun 2, 2015 22:04
|
|
|
Gwaihir posted:(Games are not the performance needle, sorry Which is why a big jump in integrated graphics is meaningful in the market, because 75%+ of users don't use a discrete GPU.
|
|
#
?
Jun 2, 2015 22:34
|
|
|
Most certainly, it's hugely nice if you can get stuff like these new chips a Dell XPS13 ish form factor, and then you have a really pretty decently capable machine that can game on the road without the usual discrete GPU laptop drawbacks.
|
|
#
?
Jun 3, 2015 00:13
|
|
|
I can't seem to find any ARM systems in the processor generation statistics here: http://top500.org/statistics/list/ Not gonna be holding my breath!
|
|
#
?
Jun 3, 2015 00:24
|
|
|
Funny, I don't see any Alpha and only one SPARC.
|
|
#
?
Jun 3, 2015 00:58
|
|
|
JawnV6 posted:Funny, I don't see any Alpha and only one SPARC. So your pro-ARM argument is that ARM is the next Intel. Okay, call me when they crack the top 500. Still not holding my breath!
|
|
#
?
Jun 3, 2015 01:21
|
|
|
Does single threaded performance need to get much better than the 5~10% we are getting? I figured it was us that needed to get better with utilising cores. I'm a naive, 4/10 (maybe?) programmer still at Uni though.
|
|
#
?
Jun 3, 2015 01:23
|
|
|
pmchem posted:I can't seem to find any ARM systems in the processor generation statistics here: You'll see ARM on that list sooner than you may think.
|
|
#
?
Jun 3, 2015 01:29
|
|
|
Lord Windy posted:Does single threaded performance need to get much better than the 5~10% we are getting? I figured it was us that needed to get better with utilising cores. You know what would be way better than us getting better at using multiple cores? Really fast single cores. I would love to have a single core 17.6GHz Haswell instead of a quad core 4.4 GHz one. We were supposed to be around 20 GHz by now! http://www.geek.com/chips/intel-predicts-10ghz-chips-by-2011-564808/
|
|
#
?
Jun 3, 2015 01:34
|
|
|
Lord Windy posted:Does single threaded performance need to get much better than the 5~10% we are getting? I figured it was us that needed to get better with utilising cores. It's not that we don't need more it's that we're not likely to get more than that at this point, clock speeds can't be pushed much higher and the various methods we have used to exploit more IPC over the years are starting to hit diminishing returns. It's much easier to just increase core counts rather than try to further increase single-threaded performance after a certain point, and as people pointed out before most server or HPC applications can take advantage of the more cores approach.
|
|
#
?
Jun 3, 2015 01:55
|
|
|
pmchem posted:So your pro-ARM argument is that ARM is the next Intel. Okay, call me when they crack the top 500. Still not holding my breath! I also made an appeal to the notion that ARM is an ecosystem. Intel debuggers are written by Intel. Arm debuggers are written by ~5 different teams who are all competing for market share. Other facets of design are also subject to competitive forces. This was in the middle of an argument about anti-trust sanctions. I like that you're able to drop by halfway through all this context and act like I'm on a single point based on a metric you brought up without any justification or even a nod towards relevance.
|
|
#
?
Jun 3, 2015 02:20
|
|
|
Twerk from Home posted:We were supposed to be around 20 GHz by now! http://www.geek.com/chips/intel-predicts-10ghz-chips-by-2011-564808/ quote:f 10 GHz is the best that Intel can do by 2011, AMD or somebody else is going to eat their lunch. Intel better pick up the pace if they want to remain dominant. Besides, I want it NOW. What will I do with it. Well, I also want the applications now. I guess I've been spoiled by the industry and expect incredible improvements every year. - by Allen quote:Back in grad school I worked on computing with light and transistors that had ten states (0-9 or base 10) rather than 2 (0 and 1 or binary). Anybody who doesn't think that these types of technology won't be commercially available by 2011 is kidding themselves. In addition, new OS capability to scale up and out will radically change how we compute. Maybe clock speeds will only be 10 GHz by then but dozens and dozens of processors may coexist on a single chip that process data in base 10 (or hex) instead of base 2, effectively performing hugely more complex computations with fewer transistors and (relatively) lower clock speeds than would currently be needed. I have seen the future and it ROCKS!!…. (Oh, Windows 2010 is still a slug…. ;-) Goddamn those comments are hilarious. Like for every person that goes "I don't think that is how it will work" there is 8 dreaming about their dream computer or arguing over DNA computers. Everyone is also talking about Tertis and Windows 2000, did it come built in? Because 9 year old me would have played the poo poo out of that if he knew about it. EDIT: Also OS wars
|
|
#
?
Jun 3, 2015 02:25
|
|
|
This hellish future left me with not one single 5+Ghz processor (on air, no turbo) and levitating gently caress bot. The gall incoherent fucked around with this message at 04:42 on Jun 3, 2015 |
|
#
?
Jun 3, 2015 02:30
|
|
|
pmchem posted:So your pro-ARM argument is that ARM is the next Intel. Okay, call me when they crack the top 500. Still not holding my breath!
|
|
#
?
Jun 3, 2015 02:51
|
|
|
JawnV6 posted:I also made an appeal to the notion that ARM is an ecosystem. Intel debuggers are written by Intel. Arm debuggers are written by ~5 different teams who are all competing for market share. Other facets of design are also subject to competitive forces. This was in the middle of an argument about anti-trust sanctions. I like that you're able to drop by halfway through all this context and act like I'm on a single point based on a metric you brought up without any justification or even a nod towards relevance. There are compilers and debuggers being written for Intel chips by a heck of lot more companies, universities, and worldwide open source teams than "just Intel". No idea how you're even making that statement. Making some general argument of "new hotness gonna replace old fogeys" is a strawman too. You asked for a metric where Intel was ahead; I provided one relevant to my work. ARM is not even attempting to compete on floating point throughput yet. While they might, one day, the light is not even visible at the end of that tunnel yet. Intel has an incredible manufacturing/process advantage and huge resources for chip R&D, beyond something like "Cray" which was never really a CPU company so is a terrible example. It's far beyond what DEC was to Intel in the 90s. Cray still exists by the way: I used three of them today! They're not ignoring the competition from ARM; check out the recent realworldtech article about Atom improvements. Indeed, even for Intel facets of design are subject to competitive forces. I look forward to the day where there is a credible Intel competitor once again in scientific work, but the sense of "ARM inevitability" being championed here is way premature.
|
|
#
?
Jun 3, 2015 03:12
|
|
|
Twerk from Home posted:You know what would be way better than us getting better at using multiple cores? Really fast single cores. I would love to have a single core 17.6GHz Haswell instead of a quad core 4.4 GHz one. Your link gives me hope, but...
|
|
#
?
Jun 3, 2015 03:44
|
|
|
Theoretically ARM has the advantage of the decoder logic taking up a smaller portion of the CPU die but there's also been a trend over time of the decoder logic taking up a smaller portion of the CPU die across all microarchitectures so this might not end up mattering that much. From what I have seen so far Intel still has a big advantage in performance/watt due to their superior fab when compared to a theoretical ARM competitor, especially with their low power Xeons. It would be interesting to see how the performance/watt would compare if Intel made some ARM cores, which it looks like might happen before too long. EDIT: But fundamentally saying "Intel's going to be eaten alive by ARM" doesn't really make any sense. ARM is an ISA and Intel is a chip manufacturer, if Intel eventually sees an advantage in dumping x86 for ARM they will do so and go along designing and manufacturing chips just as they did before. http://seekingalpha.com/article/3229806-intel-becomes-an-arm-chip-maker MaxxBot fucked around with this message at 04:39 on Jun 3, 2015 |
|
#
?
Jun 3, 2015 04:22
|
|
|
|
| # ? Apr 27, 2024 21:11 |
|
|
Lord Windy posted:Goddamn those comments are hilarious. Like for every person that goes "I don't think that is how it will work" there is 8 dreaming about their dream computer or arguing over DNA computers. It reminds me of kids 10-15 years back saying GPU changes were so big between generations, that in no time we'll be getting graphics so good, they'll look even better than real life. I mean, there's no  big enough to possibly respond to that line of thinking.
|
|
#
?
Jun 3, 2015 05:10
|
|
