AMD CPU speculation... and expert conjecture

[hcl123]

^^ what about software compatibility and high end developes such as adobe (photoshop) autocad, maxxon, ect. running on ARM?

In order for ARM to just break into the desktop market, they need something to convince people that their current software will work instead of trying to get people to upgrade to ARM them go buy all new software.

Cost of upgrading a pc: cost of the pc

Cost of migrating from pc to ARM DT: cost of the pc +cost of the NEW software.

Until we can directly compare ARM to x86, its all just marketing hype. For some reason, a few people here are overjoyed by the hype and expect ARM to walk away with the market next month.

The current x86 android OS is still buggy and ARM doesn't run well on Windows RT. There is no direct comparison just like there is no direct transition.

Am I dissing ARM? not really. Im hoping my next phone won't crash all the time and that TOMS will quit screwing with the forums making it "mobile friendly".

I can't even post on my phone anymore, constant "server timeout", yet this is the cpu thats supposedly going to take over. The more I use my phone, the less I want to see it on the DT.

Would I try a DT ARM computer? maybe if it was cheap, but im not going to just rush out and buy the newest thing just because its ARM based.

All kind of the same issues when x86 started to break away from the "toy" PC, to professional workstations and servers... IT WILL TAKE TIME... BUTS ITS HAPPENING EVERYDAY...

Matter of fact the most used OS (operanting system) on earth is Linux not Windows (not anymore), more specifically the Linux kernel... even Android is Linux kernel... every Linux/Open Source software is prone for either x86 or ARM, and IBM Power is not that behind, ARM is big on Khronos standards, ARM is on the steering board of HSA which is an Open Standard.

hcl123 yet intel are ahead of everyone by miles yet supposedly don't improve much. AMD have barely improved at all for desktop cpus in last 4 years apart from going from 45nm to 32nm and adding another 2 cores but adding more power consumption.

Don't talk nonsense... matter of fact AMD suffers the same disease of Intel, we can say its a x86 disease, by inaction... from SNB to Broadfail ... err well... its not even 20% improvement and no way this kind of uarch can give anything more, hardly any motive for upgrade unless there is a need for some specific new instructions (which for the common DT is nill now). I just miss the days when was common 20 to 30% increase for a single uarch upgrade, now its needed 4 or 5 for the same.

OTOH i see the BD uarch with way much more possibilities of scaling, just lets hope AMD is not dead.

Yes the BD design has great scalability potential, but from potential to reality is a matter of *money* (like my mechanic used to say about car speed lol), which lacks alot for the sides of AMD... but lets hope they see the light and make the effort, its not the DT that is dead, its that there is no incentive to change computers as the paradigma is... i can't feel much difference from a 5 years old computer to now, current windows software is also dead in the water, we need "compute" we need good multithreading software, we need "realistic" ray-traced games, we need much more performant CPU and heterogenous. Then the DT can boom again.

You seem content with what you have!!??... then why change yes ? ... then you are not from my club, and that is not because you prefer Intel, is because you are too narrow sited, too biased, too childish, too ignorant.

 

[8350rocks]

OTOH i see the BD uarch with way much more possibilities of scaling, just lets hope AMD is not dead.

Yes the BD design has great scalability potential, but from potential to reality is a matter of *money* (like my mechanic used to say about car speed lol), which lacks alot for the sides of AMD... but lets hope they see the light and make the effort, its not the DT that is dead, its that there is no incentive to change computers as the paradigma is... i can't feel much difference from a 5 years old computer to now, current windows software is also dead in the water, we need "compute" we need good multithreading software, we need "realistic" ray-traced games, we need much more performant CPU and heterogenous. Then the DT can boom again.

+1 that is almost 100% the way I see it. If they can scale the BD arch to where it has the potential...it will bury everything else in x86.

You seem content with what you have!!??... then why change yes ? ... then you are not from my club, and that is not because you prefer Intel, is because you are too narrow sited, too biased, too childish, too ignorant.

+111111111111111111111111111111111111111111

 

[de5_Roy]

Actually Ubuntu is about as close to a flagship OS as ARM will get for a while...(at least in DT end)

how many performance arm-based pcs use ubuntu's arm version and how widespread is ubuntu itself? it's negligible. closed-source softwares and their developers can incentivize their effort unlike in free, open source. especially in consumer sector. i dunno if it came out right.. i mean that there's a tangible reward/punishment for people who work with closed source, paid software and provide customer service for it. i use linux distros myself (ubuntu included), yet my primary o.s.-of-use is windows. that's why i left out ubuntu and only mentioned android. volunteers cannot match paid workers.

amusingly, arm and linux make perfect couple, almost perfect. arm pretty much operate like a charity and linux is free. although arm will wait till they have full market penetration e.g. high revenue markets like hpc and servers before they start to raise their fees in the name of 'advancing high performance' and so on.

@hafijur: haswell-E won't use less than 130-150w tdp. performance won't be 2x of fx8350. "performance will be 2x" is a loaded claim anyway (what kind? what program? efficient? what system? what price? etc.). it might actually need to use more for cooling purposes. and amd will only gouge if they have a strong product, or if they think they have a strong product.

 

[8350rocks]

The 8 core haswell should take slightly less electricity then the fx8350 have 8 core 16 threads and double the performance of the fx8350. Intel have a 2.1x ipc advantage in pure single threaded stuff. gimp fotosizer superpi all show this. Why else do i5's sell well at £150 compared to lets say a cheaper fx8320 its because you get similar multithreaded performance but everything is new from moherboard memory controller and massive cuts in electricity costs and its own igpu. Do you really think steamroller with its own gpus going to cost £90 with 6 cores like they are now. A 6 core steamroller with ok integrated gpu will cost probably around £200 and yet intel are already ahead of that at £150.

I only have a movie quote in response to this post:

"Which brings me to my next point kids...don't smoke crack!"



5 points if you can name the movie and who said it...

 

[hcl123]

Certain problems require exascale level compute. The problem is that current petascale supercomputers cannot be scaled up 1000x due to the immense power consumption. Therefore research groups concluded that ARM was the kind of efficient architecture needed to build supercomputers at that scale.

The research group has shown that ancient Tegra chips are more efficient than the i7 in single core perf. and had the same efficiency that the i7 in multicore at the same freq.

Ivy Bridge is about a 10-15% better than Sandy and Haswell is (being generous here) about a 10% better than Ivy. I don't know how Broadwell and Skylake will perform, but I doubt that will introduce more than a 20%.

However, the current Tegra 4 is 10x/5x better than Tegra 2/3 they tested. And Parker will be about 100x better and comes in 2015, probably in 14nm. Intel Broadwell also comes in 14nm but it is not more for desktops

http://www.fudzilla.com/home/item/32524-broadwell-won%E2%80%99t-make-it-to-desktop

For the sake of comparison 100x is a 9900% >>> 20%

ummm... i think the key to exascale is in heterogeneous, a kind of APU, not necessarily one that has a full GPU for the heterogeneous part. Perhaps that is why ARM is in HSA, HSA is not about iGPUs as many seem to reason... its all everything heterogenous... yes HSA in exascale supercomputer (OpenMPI is already foreseen).

All this ARM vs i7 is awkward. Even biased blinds can see that an A57 as much more perf/watt... its not only 28nm vs 22nm finfet (double the theoretically price), its also power management and turbo, so its not 1.3Ghz vs 1.49Ghz, ARM as kind of rudimentary power management and no turbo, while Intel has the best power management of them all (this should please hafijur)...

A57 on 22nm finfet and Intel like power management (turbo) will be a severe beating not only at perf/watt, but also in pure performance (where it can win already in most of benches).

If x86 is caught with their pants down, we can thank hafijur and the like... a multitude like him makes no real incentive to develop anything superior... annoying tireless sturborn fanboys, perhaps reason to suspect many are payed, a campaign to cut cost with x86 high performance development to concentrate on low power, and like those kind of brainless posters, intel is even more brainless if it thinks it can beat on low power perf/watt an uarch that was developed since the very debut for it, matured long years thinking what best to be there, by a uach (x86 ISA) that was "rapidly" developed first by IBM thinking on "toy" PC (personal computers), when power was nit even on a side consideration (edt)...

baahh! intel must think too much of its own propaganda spin power (an insult to engineers if you ask me).

 

[hcl123]

The 8 core haswell should take slightly less electricity then the fx8350 have 8 core 16 threads and double the performance of the fx8350. Intel have a 2.1x ipc advantage in pure single threaded stuff. gimp fotosizer superpi all show this. Why else do i5's sell well at £150 compared to lets say a cheaper fx8320 its because you get similar multithreaded performance but everything is new from moherboard memory controller and massive cuts in electricity costs and its own igpu. Do you really think steamroller with its own gpus going to cost £90 with 6 cores like they are now. A 6 core steamroller with ok integrated gpu will cost probably around £200 and yet intel are already ahead of that at £150.

I only have a movie quote in response to this post:

"Which brings me to my next point kids...don't smoke crack!"



5 points if you can name the movie and who said it...

Too late, he already OD lol

(a 6 core Intel can even lose in some benchmarks to their own 4 cores (which is a testament that "clock" counts a lot, even if its turbo... and a testament Windows soft doesn't scale, low multi-threading if any, and no incentive for more cores... revert all this 200%, seems more than a miracle with the same kind of uarch, and the same clock flat fab processes thinking on low power (edt))

 

[Cazalan]

Therefore you decided to ignore again the quote that says that Intel is less efficient. Funny.

Certain problems require exascale level compute. The problem is that current petascale supercomputers cannot be scaled up 1000x due to the immense power consumption. Therefore research groups concluded that ARM was the kind of efficient architecture needed to build supercomputers at that scale.

The research group has shown that ancient Tegra chips are more efficient than the i7 in single core perf. and had the same efficiency that the i7 in multicore at the same freq.

Ivy Bridge is about a 10-15% better than Sandy and Haswell is (being generous here) about a 10% better than Ivy. I don't know how Broadwell and Skylake will perform, but I doubt that will introduce more than a 20%.

However, the current Tegra 4 is 10x/5x better than Tegra 2/3 they tested. And Parker will be about 100x better and comes in 2015, probably in 14nm. Intel Broadwell also comes in 14nm but it is not more for desktops

http://www.fudzilla.com/home/item/32524-broadwell-won%E2%80%99t-make-it-to-desktop

For the sake of comparison 100x is a 9900% >>> 20%

I didn't ignore it. Less efficient at single core performance at the lower clock speeds. But when you use it as it's designed with 4 cores and higher clock speeds Intel became more efficient. Chop 2 legs off a horse and yes a human will outrun that horse. In one of the same slides they overclocked an ARM chip and saw the performance/energy actually go down.

You're taking Nvidia marketing terms at face value compared to CPU only Intel advancements. Those NVidia numbers are HEAVILY weighted towards the GPU capability they're adding to the device, not the CPU capability. It's apples and oranges.

Now if you take Sandy GPU benchmarks compared to Haswell GPU benchmarks what do you see?

http://www.sisoftware.net/?d=qa&f=cpu_intel_sb
http://www.sisoftware.co.uk/?d=qa&f=gpu_hsw

Sisoftware Float Vectorized compute shader - Sandy 19.44MPix/s
Sisoftware Float Vectorized compute shader - Haswell 537MPix/s

A 27x improvement in 2 generations. Yes that was cherry picked but the point is NVidia just needs 1 benchmark that shows 100x improvement for that marketing slide to be true. That's not very hard to do with benchmark magic.

You can't take ANY marketing slide at face value. That goes for EVERY company.

PS: MIPS is considered more energy efficient than ARM, it just hasn't had a champion until Imagination bought it last year. Now they have their own energy efficient 64 bit core to bundle with their PowerVR Rogue (Used in iPhone 5S).

 

[Cazalan]

you don't follow pcs news much, do you? intel already has 6,8 and 10 core cpus. 8c and 10c ones are xeons - big cpus unlike mainstream desktop ones.
according to older cpu roadmaps, we're supposed to have mainstream 6c core i5 and 8c core i7 a while ago, but that didn't happen. instead we got overpriced ivb and haswell cpus. in case you don't know, current intel cpus are overpriced a lot.
broadwell not being on desktop is not a good news for customers.
there's no muscle flexing or anything, intel can't get people to buy their stuff, so they're extorting more than usual.

There will be Broadwell desktops just not the socketed kind you're expecting to see. Just like there are already Jaguar desktops out there. BGA chips don't exclude a part from going in a desktop or AIO. They're just not upgradeable, which for 95% of the public doesn't matter anyway.

 

[de5_Roy]

There will be Broadwell desktops just not the socketed kind you're expecting to see. Just like there are already Jaguar desktops out there. BGA chips don't exclude a part from going in a desktop or AIO. They're just not upgradeable, which for 95% of the public doesn't matter anyway.

ugh, forgot about those. aio boards and smaller cases like nuc use so many mobile cpus that i keep forgetting that intel's S and T series and now R series cpus go into those. i really dislike the unupgradability (well, with intel it's like that most of the time) part and really high price intel charges for those types of cpus.

 

[hcl123]

Stop wasting time with those A9 vs i7 comparatives... A9 is not going anywhere, just to start is 32bit can only address 4GB, a surprise option for micro-micro servers ... (yet perhaps much less power and more speed have hundreds thousands on VM (virtual machines) and run all those numerous tiny jobs from a big IBM machine on a centralize location... its not by chance and IBM does next to nil publicity, that IBM does rivers of money to, in a time when power wasting in server jobs is on top of list, but IBM Chips are >200W... there is much more to the all power bill than the low power of a couple of CPU chips).

Also A9 was never intended to have any relevant performance, neither the ARM v7 uarch... A15 of Tegra4 is almost double of A9 yet is not any kind of high performance... but what has clearly the intention of having good performance and maintain or gain low power without fancy expensive to develop power management features... is A57 and ARM v8.

[ an no that Apple A57 based A7 chip is not about *high performance either*... a big surprise to see it do so terribly well against tablet similar, even low end DT ones... just drooling to see what an IDM experienced with high performance designs (like AMD ) can do!.. ]

 

[Cazalan]

ugh, forgot about those. aio boards and smaller cases like nuc use so many mobile cpus that i keep forgetting that intel's S and T series and now R series cpus go into those. i really dislike the unupgradability (well, with intel it's like that most of the time) part and really high price intel charges for those types of cpus.

Well soon you'll be considered a dinosaur in the industry if you even mention a PC being upgradeable. Your kids or grand kids will look at you funny for even mentioning it. Consider the throw away youth of today that have only experienced a non-upgradable phone or tablet their whole life.

 

[de5_Roy]

Well soon you'll be considered a dinosaur in the industry if you even mention a PC being upgradeable. Your kids or grand kids will look at you funny for even mentioning it. Consider the throw away youth of today that have only experienced a non-upgradable phone or tablet their whole life.

ah.. those were the days...
right now, arm is the biggest proponent of unupgradable, disposable devices. i honestly thought it would be intel who closes down devices first, when pcs were dominant and laptops were gaining in sales and marketshare. it could still be intel in x86 pcs. but overall, arm has leapfrogged intel and x86 in that regard. i think it'll soon cause customer fatigue and backlash(hopefully!). i hope amd still lets people customize their pcs(arm/x86) even though they seem to be going the tablet way with kabini....
i'm okay with being a dinosaur.. mmm veggies...

 

[hcl123]

There will be Broadwell desktops just not the socketed kind you're expecting to see. Just like there are already Jaguar desktops out there. BGA chips don't exclude a part from going in a desktop or AIO. They're just not upgradeable, which for 95% of the public doesn't matter anyway.

ugh, forgot about those. aio boards and smaller cases like nuc use so many mobile cpus that i keep forgetting that intel's S and T series and now R series cpus go into those. i really dislike the unupgradability (well, with intel it's like that most of the time) part and really high price intel charges for those types of cpus.

Perhaps Intel feels it cannot compete on smarthphone factors and is inventing a new market sector where their low power chips have more room to breath... the same happened when their first Atoms couldn't get anywhere near phones and they invented the netbooks (a low end laptop was way better anyway, but it sold well).

*If* Steamroller is SOI, and is at least ~20% better overall (not to mention the 30% talked about)... Broadwell is going to be terribly squeezed from above with by performant high clock offerings of AMD, and from below by all those ARM v8 offerings that will follow, and that almost certain will spill out of the phone/tablet formats.

I think is a good strategy for intel... not upgradeable is a consequence of the strategy (more money, all in house). A better strategy will be to get on ARM v8, and to discard all this #well crap uarches ( which many inside probably will say "over my dead body" -> well! if they insist!), open the IP book that is extensive, and gets a real scalable high performance chip with high performance exotic features (will resemble AMD BD ? .. so what ?).

 

[de5_Roy]

Perhaps Intel feels it cannot compete on smarthphone factors and is inventing a new market sector where their low power chips have more room to breath... the same happened when their first Atoms couldn't get anywhere near phones and they invented the netbooks (a low end laptop was way better anyway, but it sold well).

intel has so much money that they did just that, with ultrabooks and it's derivative hybrids. first, they locked the ultrabook formfactor to keep amd away, then [strike]bribed everyone (i mean everyone)[/strike] err... funded their advertisement campaigns and stuff... although amd and glofo didn't help much, their apus couldn't scale down to low power and that includes richland. bobcat was too slow. kabini is amd's best bet right now since kaveri is suspect to some degree. it's not like ultrabooks sold... they flopped. then they came up with (B)SDP to scam people into buying underclocked sb, ivb and hsw cpus. we know those are 11-15w cpus darnit!
iirc they made netbooks to sell celerons first, then atoms. never liked them.

*If* Steamroller is SOI, and is at least ~20% better overall (not to mention the 30% talked about)... Broadwell is going to be terribly squeezed from above with by performant high clock offerings of AMD, and from below by all those ARM v8 offerings that will follow, and that almost certain will spill out of the phone/tablet formats.

I think is a good strategy for intel... not upgradeable is a consequence of the strategy (more money, all in house). A better strategy will be to get on ARM v8, and to discard all this #well crap uarches ( which many inside probably will say "over my dead body" -> well! if they insist!), open the IP book that is extensive, and gets a real scalable high performance chip with high performance exotic features (will resemble AMD BD ? .. so what ?).

if BRW is focused on certain formfactors, it might not feel pressured that much. intel is lengthening their refresh cycle to 2 years from every year (wonder why...) meaning users will have to suffer longer. kinda like amd users had to endure suffer(they still are, disregarding the fanboys) with phenom to bd(zambezi). like i said before, intel's not getting new customers, so their current stragegies are to take share from amd (good for them, drives them to arm, kabini and semicustom ), devour more of the b.o.m., develop own o.s.(and fail) and suck up to google and apple.
apple got them to make crystalwell! just one company! that's like intel's cherry-popping for custom chips!
i think intel's uarches are provenly scalable (from server to mobile), might not be as modular as jaguar(proven - consoles, kabini, temash etc). bulldozer and derivative's scalability and modularity are both suspect imo. bd(zambezi) pretty much failed all around but it was a first attempt. but pd and it's branches didn't fare better. for example, trinity and richland perform better than llano but failed to capitalize (market situation is to blame as well) on llano's success.
i am looking forward to skymont and skylake. skylake looked like a beefed up atom. not interested, just wanna see what intel does with them.

 

[8350rocks]

Perhaps Intel feels it cannot compete on smarthphone factors and is inventing a new market sector where their low power chips have more room to breath... the same happened when their first Atoms couldn't get anywhere near phones and they invented the netbooks (a low end laptop was way better anyway, but it sold well).

intel has so much money that they did just that, with ultrabooks and it's derivative hybrids. first, they locked the ultrabook formfactor to keep amd away, then [strike]bribed everyone (i mean everyone)[/strike] err... funded their advertisement campaigns and stuff... although amd and glofo didn't help much, their apus couldn't scale down to low power and that includes richland. bobcat was too slow. kabini is amd's best bet right now since kaveri is suspect to some degree. it's not like ultrabooks sold... they flopped. then they came up with (B)SDP to scam people into buying underclocked sb, ivb and hsw cpus. we know those are 11-15w cpus darnit!
iirc they made netbooks to sell celerons first, then atoms. never liked them.

*If* Steamroller is SOI, and is at least ~20% better overall (not to mention the 30% talked about)... Broadwell is going to be terribly squeezed from above with by performant high clock offerings of AMD, and from below by all those ARM v8 offerings that will follow, and that almost certain will spill out of the phone/tablet formats.

I think is a good strategy for intel... not upgradeable is a consequence of the strategy (more money, all in house). A better strategy will be to get on ARM v8, and to discard all this #well crap uarches ( which many inside probably will say "over my dead body" -> well! if they insist!), open the IP book that is extensive, and gets a real scalable high performance chip with high performance exotic features (will resemble AMD BD ? .. so what ?).

if BRW is focused on certain formfactors, it might not feel pressured that much. intel is lengthening their refresh cycle to 2 years from every year (wonder why...) meaning users will have to suffer longer. kinda like amd users had to endure suffer(they still are, disregarding the fanboys) with phenom to bd(zambezi). like i said before, intel's not getting new customers, so their current stragegies are to take share from amd (good for them, drives them to arm, kabini and semicustom ), devour more of the b.o.m., develop own o.s.(and fail) and suck up to google and apple.
apple got them to make crystalwell! just one company! that's like intel's cherry-popping for custom chips!
i think intel's uarches are provenly scalable (from server to mobile), might not be as modular as jaguar(proven - consoles, kabini, temash etc). bulldozer and derivative's scalability and modularity are both suspect imo. bd(zambezi) pretty much failed all around but it was a first attempt. but pd and it's branches didn't fare better. for example, trinity and richland perform better than llano but failed to capitalize (market situation is to blame as well) on llano's success.
i am looking forward to skymont and skylake. skylake looked like a beefed up atom. not interested, just wanna see what intel does with them.

Trinity is/was very successful in OEMs. Which is why AMD are pushing APUs forward.

I just hope that AMD zigs while everyone else zags to mobile.

If AMD made a strong push with a renewed FX line into gaming desktops and HEDT in general...I think they could easily catch Intel sleeping with a price/performance competitive new product and regain some market share.

 

[The Q6660 Inside]

Well soon you'll be considered a dinosaur in the industry if you even mention a PC being upgradeable. Your kids or grand kids will look at you funny for even mentioning it. Consider the throw away youth of today that have only experienced a non-upgradable phone or tablet their whole life.

ah.. those were the days...
right now, arm is the biggest proponent of unupgradable, disposable devices. i honestly thought it would be intel who closes down devices first, when pcs were dominant and laptops were gaining in sales and marketshare. it could still be intel in x86 pcs. but overall, arm has leapfrogged intel and x86 in that regard. i think it'll soon cause customer fatigue and backlash(hopefully!). i hope amd still lets people customize their pcs(arm/x86) even though they seem to be going the tablet way with kabini....
i'm okay with being a dinosaur.. mmm veggies...

*Inserts tomato joke *

 

[GOM3RPLY3R]

come next year, all non-nvidia sponsored games might look like this. AMD probably doesn't even need a new card in that case.

Go home hafijur, you're drunk!

Annnndddd loook!!!! Turns out us so called "AMD fanbois" were right!

http://www.tomshardware.com/news/xbox-one-ps4-amd-apu-pc-gaming,24295.html

"When consoles are first launched, games are first developed on console and then ported to PC," he added. "Because it's our architecture there, it's easier to port the games. And because they're first developed on our hardware, there should be a performance advantage. They should run better on our hardware. So if we can create that performance advantage on the PC, from a graphics point of view, then we can give our customers a better gaming experience and grow our market share."

They need to realize:
1. It's a custom OS made for AMD
2. There's no other hardware competition for Consoles right now
3. PC does not = Console
4. Yes the hardware is better than last generation, however, the architecture with no doubt will be lowered. My Core 2 Quad Q8300 and Radeon 5570 are about the same performance of these consoles. (ex: BF4. Really no performance difference from BF3, and to get 60 FPS on a console? Yeah that needs some serious tuning, especially considering that the console version on lowest possible settings on my pc runs on multiplayer at ~20-30 FPS).


They are leaving out major facts. Also I saw a post earlier about how Intel isn't really leaving Desktop and they are implementing more into the Extreme series.

Unless they dropped the price of the Extreme series, there's absolutely no point. Take a 3930k and OC it to 3.5, you'll be getting similar performance as a 3960X except with less Power Consumption and less heat.

I even think the 4930k will be amazing, on that IB-E. I'm hearing mixed feelings from gamers, but other than that, its great.

As a side note, I think you all may know this website: anandtech.com

Super fast and easy way to get your point across, as well as efficiently and correctly. They can do GPU and CPU comparisons across a surprisingly wide variety of tests. Also, there's this place: postimage.org

You can upload your own image and host it for free. I could make a comparison off of anandtech and then post it up in less than a minute. You're welcome. ^_^

5570, seems legit, you realize a PS4 is packing a 7850+ CPU and 8-cores right?

Just because it says, "OH BOY THIS HAS A 7850 AND A 8 CORE CPU IN IT!!" A 7850 will totally fit in a tiny Console case. These "7850's" will definitely be less than a low profile 7850. Also take into consideration Power Consumption and Heat. The performance will literally drop, okay not a 5570, but something like a 6650 or 6750 should do the trick, which is no where close to "A average gaming PC."

Nope. It is not "this" CPU and "that" GPU. The PS4 has a custom HSA APU with hUMA. Custom means that it is improved hardware available only for it. E.g. the iGPU has about 4x the compute queues of a 7990 (if my memory doesn't fail), there is an extra bus for accessing data...

Even if a PC had exactly that custom hardware, the PS4 would be still faster:

http://www.eurogamer.net/articles/digitalfoundry-inside-metro-last-light

Oles Shishkovstov: No, you just cannot compare consoles to PC directly. Consoles could do at least 2x what a comparable PC can due to the fixed platform and low-level access to hardware.

This is not very different from car vs motorbike comparison. A 100HP motorbike is much faster than a 100HP car.

4. Yes the hardware is better than last generation, however, the architecture with no doubt will be lowered. My Core 2 Quad Q8300 and Radeon 5570 are about the same performance of these consoles.

Not even close. It is more like

PS4 ~ i7 + GTX 680/780 Windows PC

Nope an i3 3220 is faster and its like an inbetween 7850 7870 gpu performance level but supposedly on 8000 series architecture. The only good thing about the consoles is hyperthreaded dual cores are here to stay for hardcore gaming.

You have no idea of what you are talking, but well... I am not saying anything new.

I don't know what fancy land you are in, but if your logic is correct, then almost every PC gamer would have a PS4 right now. -_-

In a comparison, realistically, its basically a Core 2 Quad and ~ a 6570-6670. Comparing that hardware to last generation, it's a huge jump. Realistically, if the Consoles had THAT much power, first of all, AMD would set a price MUCH higher than anything, and the console itself in turn would cost more than almost any High End PC out there.

This logic is just bad. For consoles, which are premade, and almost non-customize-able, to overpower Rigs that cost $2000 or more, and for such a low price, just does not make sense.

No, you're wrong...the HD 6670 is on VLIW4 architecture, and the HD 7XXX series is on GCN 1.0, and the consoles are on GCN 1.1 (HD 9XXX series coming soon).

Additionally, the count of the number of processors in the PS4 exceeds the count in a HD 7850 by a small margin, but is also more advanced technology. So, it really is essentially a HD ~9790/9830 (if such a thing were to exist in the next batch of cards)

As far as the cores go, you're not talking about a FX 8350 downclocked to ~2.2 GHz. You're talking about 8 core CPU with 8 FPUs and 3 ALUs per core (this, is more ALUs per core than FX series).

I think you don't understand this entirely...

A better comparison would be to take 2x i5-3350p and downclock to 2.2 GHz and allow developers to code to bare metal.

That should give you some idea of what you're looking at in the consoles...

So in other words, very cheap $3000 level PC? Excuse my Czech, but I call BS. If that's the case, on the scale of the hardware, the console should be ~$4000 if not more.

Okay maybe yeah, the SPECS say that it's "That Good," but will it be "That Good?" No. By any means, there's no way that consoles are THAT GOOD. Please understand this.

Even though it uses "New Hardware," It's all custom, so it wont be true hardware. Kinda like a GTX 680M is not a 680, at all, in any way shape or form, and it take on the power of ~ a GTX 650 Ti - GTX 660, however for this scale (from these "fantastic specs"), the ratio will by MUCH larger.

EDIT NOTE: By the way, I was in no way saying it was that verbatim. "It has the performance of a 6670," is much different than, "it is a 6670."

 

[hcl123]

i think intel's uarches are provenly scalable (from server to mobile), might not be as modular as jaguar(proven - consoles, kabini, temash etc). bulldozer and derivative's scalability and modularity are both suspect imo. bd(zambezi) pretty much failed all around but it was a first attempt. but pd and it's branches didn't fare better. for example, trinity and richland perform better than llano but failed to capitalize (market situation is to blame as well) on llano's success.
i am looking forward to skymont and skylake. skylake looked like a beefed up atom. not interested, just wanna see what intel does with them.

Every design nowadays is scalable in that sense... even GPUs, watch how many bins there is only by fusing shaders. In that sense the the notion of modularity and scalability i quite blurred in the definitions.

I meant scalability in terms of performance and easy to upgrade features. Intel needs to get the FPU out of the integer way, specially when they are thinking of 512 bit vectors... that means probably (don't see other way) a co-processor orientation for FP, it will resemble FlexFPU. Also hyperthreading(SMT) when a good single core is going to the 10mm² size just doesn't make any sense anymore (was good when a single core was more than 50mm², a huge chip couldn't get more than 4 or 8, now they can get easily 16 or more )... at best resort only to single cores, at worst CMT (cluster multithreading) is way much better.

Because the first iteration of the BD design was mediocre, doesn't mean the uarch philosophy is. It has lots of potential (see how easy they got ~10% better for PD and more clock), it needs real exotic high performance features (speculation, data flow, multithreading etc), and the faster they realize x86 can't compete with low power and for smaller systems, the faster we can have those features and the DT booming again.

What is doomed in medium long term are the kabinis and Silvermonts and the like on x86... specially intel if it wants to save x86, it better start to think real high performance..

For AMD this is kind of agnostic, i'm sure they thought of x86_64 execution pipes for "binary translation" *help* (like the chinese of Godson is doing with MIPS), on other uarchs. At least by the time of Ruiz, that launched the famous law suit against intel, he also bought all the relevant IP of Transmeta, falling short of buying Transmeta itself...

So since a lot of time i don't see that much pressure on AMD, Intel may think its eating AMD, but what they may eat is nothing, a virtual bite, cause what was there is not anymore, and AMD itself escaped away.(edt)

 

[GOM3RPLY3R]

http://www.amazon.co.uk/review/RQJ2AQTSH86WV/ref=cm_cr_pr_cmt?ie=UTF8&ASIN=B009O7YUF6&linkCode=&nodeID=&tag=#wasThisHelpful


"After testing I've found I can run the 8350 at stock speed but under-volted by 0.050v and it remains solid on Prime95 (small SSTs). What's odd is the power usage: it's a really hungry beast. At stock voltage and 100% load the draw at the wall is 290W. Somewhere around 180W must be going through the CPU socket! So the quoted TDP of 125W is highly questionable. Under-volting it saves 30W. It's not hard to cool though; with both the case fan and CPU fan cruising quietly at 1/2 speed and under-volted it runs Prime95 at 46C which is very comfortable.

The 8350 supports the GTX 660s very well in running games.

BUT, now I've created an Excel benchmark test macro. The FX-8350's performance is hopeless. It's even slower than my 5 year old Intel QX6700 which runs at 2.7Ghz. It's slower than my daughter's Lenovo E320 laptop (i3-2330M @2.2GHz). And it's about half the speed of an i5-3570K @3.8Ghz. Since this is the most important use for me I'm going to replace it. Be warned! "
...............................................................................
This proves my point intels ipc is much better. According to superpi the fx8350 is on par with a cpu at 2.4ghz from the core 2 era. Now intel currently are twice as fast ar superpi or image editing with gimp or fotosizer. The i5 at 3.8ghz should be 95% faster then the fx8350 at this task.

+1. I would like to add one fact. SuperPI is not Bias, it's pure fact. Intel's Per Core Performance is much higher (as you may know). Take into consideration that more and more people are getting 3930k's, and Intel is getting more into 6 core mainstream, and will soon be providing 8 core CPU's for the 3930k like price. On the other hand, AMD isn't even done using their 8 cores yet, and have yet to produce a 'consumer value' 10 core or even 12 core CPU.

By math, basically a 4 core Intel and 8 core AMD are ~ the same performance (3570k, and FX8350 for example). So right there, With half the cores, Intel is the same performance. If you were to do this Intel 6 core, AMD 8 core (3930k vs 8350, or even 9590), the performance gain of Intel to AMD is ~ 40% or more.

So when 8 core Intel's are as common as the sixes are today, whilst AMD is cruising with their newly released 12 core CPU, do the math, Intel will always be ahead, if not gain more ground at this rate.

Here's today's market share:

There's no doubt in my mind that this very slow trend will continue, if not accelerate if AMD keeps their plans up. ^_^

 

[8350rocks]

http://www.amazon.co.uk/review/RQJ2AQTSH86WV/ref=cm_cr_pr_cmt?ie=UTF8&ASIN=B009O7YUF6&linkCode=&nodeID=&tag=#wasThisHelpful


"After testing I've found I can run the 8350 at stock speed but under-volted by 0.050v and it remains solid on Prime95 (small SSTs). What's odd is the power usage: it's a really hungry beast. At stock voltage and 100% load the draw at the wall is 290W. Somewhere around 180W must be going through the CPU socket! So the quoted TDP of 125W is highly questionable. Under-volting it saves 30W. It's not hard to cool though; with both the case fan and CPU fan cruising quietly at 1/2 speed and under-volted it runs Prime95 at 46C which is very comfortable.

The 8350 supports the GTX 660s very well in running games.

BUT, now I've created an Excel benchmark test macro. The FX-8350's performance is hopeless. It's even slower than my 5 year old Intel QX6700 which runs at 2.7Ghz. It's slower than my daughter's Lenovo E320 laptop (i3-2330M @2.2GHz). And it's about half the speed of an i5-3570K @3.8Ghz. Since this is the most important use for me I'm going to replace it. Be warned! "
...............................................................................
This proves my point intels ipc is much better. According to superpi the fx8350 is on par with a cpu at 2.4ghz from the core 2 era. Now intel currently are twice as fast ar superpi or image editing with gimp or fotosizer. The i5 at 3.8ghz should be 95% faster then the fx8350 at this task.

Time for another quote response:

"If you're going to be crazy, you have to get paid for it or else you're going to be locked up."

 

[8350rocks]

http://www.amazon.co.uk/review/RQJ2AQTSH86WV/ref=cm_cr_pr_cmt?ie=UTF8&ASIN=B009O7YUF6&linkCode=&nodeID=&tag=#wasThisHelpful


"After testing I've found I can run the 8350 at stock speed but under-volted by 0.050v and it remains solid on Prime95 (small SSTs). What's odd is the power usage: it's a really hungry beast. At stock voltage and 100% load the draw at the wall is 290W. Somewhere around 180W must be going through the CPU socket! So the quoted TDP of 125W is highly questionable. Under-volting it saves 30W. It's not hard to cool though; with both the case fan and CPU fan cruising quietly at 1/2 speed and under-volted it runs Prime95 at 46C which is very comfortable.

The 8350 supports the GTX 660s very well in running games.

BUT, now I've created an Excel benchmark test macro. The FX-8350's performance is hopeless. It's even slower than my 5 year old Intel QX6700 which runs at 2.7Ghz. It's slower than my daughter's Lenovo E320 laptop (i3-2330M @2.2GHz). And it's about half the speed of an i5-3570K @3.8Ghz. Since this is the most important use for me I'm going to replace it. Be warned! "
...............................................................................
This proves my point intels ipc is much better. According to superpi the fx8350 is on par with a cpu at 2.4ghz from the core 2 era. Now intel currently are twice as fast ar superpi or image editing with gimp or fotosizer. The i5 at 3.8ghz should be 95% faster then the fx8350 at this task.

+1. I would like to add one fact. SuperPI is not Bias, it's pure fact. Intel's Per Core Performance is much higher (as you may know). Take into consideration that more and more people are getting 3930k's, and Intel is getting more into 6 core mainstream, and will soon be providing 8 core CPU's for the 3930k like price. On the other hand, AMD isn't even done using their 8 cores yet, and have yet to produce a 'consumer value' 10 core or even 12 core CPU.

By math, basically a 4 core Intel and 8 core AMD are ~ the same performance (3570k, and FX8350 for example). So right there, With half the cores, Intel is the same performance. If you were to do this Intel 6 core, AMD 8 core (3930k vs 8350, or even 9590), the performance gain of Intel to AMD is ~ 40% or more.

So when 8 core Intel's are as common as the sixes are today, whilst AMD is cruising with their newly released 12 core CPU, do the math, Intel will always be ahead, if not gain more ground at this rate.

Here's today's market share:

There's no doubt in my mind that this very slow trend will continue, if not accelerate if AMD keeps their plans up. ^_^

SuperPi = archaic x87 benchmark from 15 years ago.

It has nothing to do with per core performance actually, only the legacy support of x87 instructions.

Additionally, there is a BIOS modification for the FX series that allows a 20% increase in performance for SuperPi benchmarks discovered by Finnish overclocker "the Stilt", which drastically closes the gap.

Also, SuperPi isn't even the fastest program for calculating Pi anymore.

 

[hcl123]

Trinity is/was very successful in OEMs. Which is why AMD are pushing APUs forward.

I just hope that AMD zigs while everyone else zags to mobile.

If AMD made a strong push with a renewed FX line into gaming desktops and HEDT in general...I think they could easily catch Intel sleeping with a price/performance competitive new product and regain some market share.

Its agnostic really. HSA is not about iGPU, its about a *SOFTWARE MODEL*, and nowadays is clear we can't separate high performance from software (benchmarks even un-representative, and compiler developments show this)(edt)... what good is a 8 core / 16 thread CPU, like hafijur was spinning, when windows software is not even average 4 threads, and when good heterogeneous can beat a CPU many times over for certain jobs ?

So in a sense we can say HSA is about high performance, multi kernels = threads, in a MIMT (multi instriction multi thread) paradigma, coupled with a relax memory model prone to very high memory parallelism orders.

Is a slight of hand... AMD would be laughing, because this serves any uarch and not only CPU, if they weren't in dire straits.

But the vision of Intel consuming AMD can be the contrary now... If AMD wants to eat Intel... or better said, get Intel eaten... release x86_64 (license their IP including the Transmeta bought) for *binary translation* for other uarchs (they may, but not yet, it will eat away their x86 to).

 

[hcl123]

http://www.amazon.co.uk/review/RQJ2AQTSH86WV/ref=cm_cr_pr_cmt?ie=UTF8&ASIN=B009O7YUF6&linkCode=&nodeID=&tag=#wasThisHelpful


"After testing I've found I can run the 8350 at stock speed but under-volted by 0.050v and it remains solid on Prime95 (small SSTs). What's odd is the power usage: it's a really hungry beast. At stock voltage and 100% load the draw at the wall is 290W. Somewhere around 180W must be going through the CPU socket! So the quoted TDP of 125W is highly questionable. Under-volting it saves 30W. It's not hard to cool though; with both the case fan and CPU fan cruising quietly at 1/2 speed and under-volted it runs Prime95 at 46C which is very comfortable.

The 8350 supports the GTX 660s very well in running games.

BUT, now I've created an Excel benchmark test macro. The FX-8350's performance is hopeless. It's even slower than my 5 year old Intel QX6700 which runs at 2.7Ghz. It's slower than my daughter's Lenovo E320 laptop (i3-2330M @2.2GHz). And it's about half the speed of an i5-3570K @3.8Ghz. Since this is the most important use for me I'm going to replace it. Be warned! "
...............................................................................
This proves my point intels ipc is much better. According to superpi the fx8350 is on par with a cpu at 2.4ghz from the core 2 era. Now intel currently are twice as fast ar superpi or image editing with gimp or fotosizer. The i5 at 3.8ghz should be 95% faster then the fx8350 at this task.

Time for another quote response:

"If you're going to be crazy, you have to get paid for it or else you're going to be locked up."

LOL

THAT PROVES NOTHING

Besides you could run that Excel twist even on a 486 that you won't *feel* much difference (even if you pick the code and twist it optimizing for AMD, and make an FX 600% better than a i7 3960x lol).. at least i think a *REAL* spreadsheet needs an user input RIGTH ? ... well , this user is orders of magnitude slower than even an ooold 486 lol ( well a 486 is a bit of an exaggeration, but not much if you don't include graphics on your stupid excel trick )

[ You ppl never get tired of so many breaks for *commercials* ? ... i hate it in movies, i even hate it in sports ... and all from the same marketing boy hafijur ? ( so tireless, i think there is more than 1 real person using that name and login) (edt) ]

 

[hcl123]

Hafijur real micro-benchmarks looks like this

IMAGE
http://www.amdzone.com/phpbb3/download/file.php?id=838&mode=view/rokbox.jpg

No CPU can *win* all the tests all the time... in there even a Richland (4 cores) wins many times (loses more than wins) for a IvyBridge(8threads)... there is plenty of room for all kind of optimizations, unless you narrow it and make a synthetic of synthetic thing. But the more you narrow it the less representative it gets... and that is all about it, you are talking baloney... all those benchmarks are usually optimized for intel, they are not representative of real applications or current software, and even when they are derivate from real things, they are "NARROWED" to the kind of tests that makes intel look good.

So when you pick a couple of those "useless" pieces of software and make peremptory comments, you can only be laugh at.

[ JUST MIND YOU, THAT CHART HAS **44** TESTS (compared with your couple), I COULD HAD PICKED A DOZEN WHERE RICHLAND IS BETTER AND SAY AMD IS BETTER THIS MUCH THAN INTEL... but then it would make me an hafijur, and i couldn't in any way live with that, suicide would be the probable sad outcome (not kidding)]

[ and NO.. its not my software or my tests... i just stumbled on it ]

 

[juanrga]

The 8 core haswell should take slightly less electricity then the fx8350 have 8 core 16 threads and double the performance of the fx8350.

You know that Intel is inferior to what you pretend and that is why you need to compare a future ~$1500 chip to an older $200 chip.

how many performance arm-based pcs use ubuntu's arm version and how widespread is ubuntu itself? it's negligible. closed-source softwares and their developers can incentivize their effort unlike in free, open source. especially in consumer sector. i dunno if it came out right.. i mean that there's a tangible reward/punishment for people who work with closed source, paid software and provide customer service for it. i use linux distros myself (ubuntu included), yet my primary o.s.-of-use is windows. that's why i left out ubuntu and only mentioned android. volunteers cannot match paid workers.

Let us see market share data:

Phones? Linux is ~90%
Tablets? Linux is ~95%
Servers? Linux is ~70%
Supercomputers? Linux is ~99%

Now some concrete examples:

PS4? Uses FreeBSD (similar to linux)
Apple OSX? Is derived from FreeBSD (similar to linux)
SteamBox? Uses Linux

Windows is only majority in the desktop/laptop *. Anything requiring __serious__ work uses linux.

* Only Windows XP and Windows 7 are, because Windows 8 has about a 15% of desktop/laptop share.