Intel's Future Chips: News, Rumours & Reviews

[Turb0Yoda]

New nm process would require a new socket, and v3 is pretty new, so I doubt they'd do that.. I just want to add on to Cazalan's answer

 

[Alpha3031]

New nm process would require a new socket, and v3 is pretty new, so I doubt they'd do that.. I just want to add on to Cazalan's answer

Now I'm confused. Broadwell and Haswell are different processes and same socket.

 

[Turb0Yoda]

New nm process would require a new socket, and v3 is pretty new, so I doubt they'd do that.. I just want to add on to Cazalan's answer

Now I'm confused. Broadwell and Haswell are different processes and same socket.

Well then, I derped and am stupid

 

[fudgecakes99]

Considering

http://www.kitguru.net/components/cpu/anton-shilov/intel-7nm-process-technology-will-require-new-materials/


this article which may or may not be factual. From what i've heard from others it would seem when intel inevitably goes to look for a new material to make processors from wouldn't that material exponentially increase the performance of processors by a huge factor?

 

[Turb0Yoda]

Considering

http://www.kitguru.net/components/cpu/anton-shilov/intel-7nm-process-technology-will-require-new-materials/


this article which may or may not be factual. From what i've heard from others it would seem when intel inevitably goes to look for a new material to make processors from wouldn't that material exponentially increase the performance of processors by a huge factor?

Theoretically. Should be above a 25% increase or something like that imho

 

[fudgecakes99]

@XxD34THxX I thought intel was looking into graphite chips which were supposedly 1tb performance of unicorn farts and leprechaun sweat.

 

[Turb0Yoda]

@XxD34THxX I thought intel was looking into graphite chips which were supposedly 1tb performance of unicorn farts and leprechaun sweat.

hmmm, wheres the unicorn vomit... Honestly, I've been bombed with work and don't have much free time anymore and I haven't looked at the nerd news yet :/

 

[juanrga]

Intel shows Broadwell-K processors finally. They come with Iris Pro graphics, which means AMD only advantage over Intel is vanishing

http://wccftech.com/intel-demonstrates-65w-broadwell-k-socketed-processors-gdc-2015-features-iris-pro-igpu-launching-mid2015/

 

[truegenius]

Intel shows Broadwell-K processors finally. They come with Iris Pro graphics, which means AMD only advantage over Intel is vanishing

http://wccftech.com/intel-demonstrates-65w-broadwell-k-socketed-processors-gdc-2015-features-iris-pro-igpu-launching-mid2015/

wow, great, instead of buying amd's 100-150$ chip i will buy intel's 200-250$ chip to play game[strike]'s and movie's videos[/strike] at 4k

 

[de5_Roy]

Skylake headed for second half of year
http://www.fudzilla.com/news/processors/37193-skylake-headed-for-second-half-of-year
Intel, Raptr join forces to give modest PCs a headache-free boost in gaming performance
http://www.pcworld.com/article/2892446/intel-raptr-join-forces-to-give-modest-pcs-a-headache-free-boost-in-gaming-performance.html

Raptr is adding support for the QuickSync video transcoding hardware built into Intel processors, so that the CPU overhead of video recording and streaming should be minimal.

 

[Isaiah4110]

Intel shows Broadwell-K processors finally. They come with Iris Pro graphics, which means AMD only advantage over Intel is vanishing

http://wccftech.com/intel-demonstrates-65w-broadwell-k-socketed-processors-gdc-2015-features-iris-pro-igpu-launching-mid2015/

wow, great, instead of buying amd's 100-150$ chip i will buy intel's 200-250$ chip to play game[strike]'s and movie's videos[/strike] at 4k

From the wccftech.com link:

In a new disclosure at GDC, Intel showed the first 5th Generation Core LGA-socketed CPU with Intel® Iris™ Pro graphics. This 65 watt unlocked desktop processor, available mid-2015, will bring new levels of performance and power efficiency to Mini PCs and desktop All-In-Ones.

It looks pretty clear to me that Intel is not trying to tout spectacular performance, but rather improved performance with much better power efficiency. Essentially the performance improvement will not knock your socks off any will likely look very unimpressive on its own, but Intel doesn't really care about that. The bigger improvement is in the power efficiency, and the fact that they are improving power efficiency that much (TDP is dropping 23%) while still bringing (likely) a 5-10% performance improvement is pretty impressive.

 

[jdwii]

Intel shows Broadwell-K processors finally. They come with Iris Pro graphics, which means AMD only advantage over Intel is vanishing

http://wccftech.com/intel-demonstrates-65w-broadwell-k-socketed-processors-gdc-2015-features-iris-pro-igpu-launching-mid2015/

Wonder what the temps will be might just get that and sell this new CPU to my friend who wants it .

I really thought they would just skip this series or delay skylake to help sell these parts

 

[jdwii]

Skylake headed for second half of year
http://www.fudzilla.com/news/processors/37193-skylake-headed-for-second-half-of-year
Intel, Raptr join forces to give modest PCs a headache-free boost in gaming performance
http://www.pcworld.com/article/2892446/intel-raptr-join-forces-to-give-modest-pcs-a-headache-free-boost-in-gaming-performance.html

Raptr is adding support for the QuickSync video transcoding hardware built into Intel processors, so that the CPU overhead of video recording and streaming should be minimal.

De5 i see this being good for Amd and Intel about raptr, also like the idea of recording games with little performance hit since i use shadowplay.

 

[de5_Roy]

De5 i see this being good for Amd and Intel about raptr, also like the idea of recording games with little performance hit since i use shadowplay.

quicksync powered recording/streaming is promising indeed. this is one of the situations where having fixed function block on the host processor pays off. unfortunately amd's fx and intel's -E cpus can't have quick sync. they'd have to depend on amd and nvidia (v.c.e. and nvenc).
it'd be interesting how processors like core i3, pentium -K and amd's apus handle streaming this way e.g. while using discreet gfx card.

 

[de5_Roy]

Valve develops its own Intel graphics driver for Linux
http://www.fudzilla.com/news/graphics/37203-valve-develops-its-own-intel-graphics-driver-for-linux
intel gfx driver so bad that even valve think it can do better! very nice!

Zotac details upcoming SN970 Steam Machine box
http://www.fudzilla.com/news/37198-zotac-details-upcoming-sn970-steam-machine-box
"unnamed skylake cpu and geforce gtx 970M". 'guessing the skylake cpu belongs to core M models with 25-28w tdp.

 

[Isaiah4110]

Valve develops its own Intel graphics driver for Linux
http://www.fudzilla.com/news/graphics/37203-valve-develops-its-own-intel-graphics-driver-for-linux
intel gfx driver so bad that even valve think it can do better! very nice!

Interesting. So that would be drivers for a SteamBox right?

 

[de5_Roy]

Interesting. So that would be drivers for a SteamBox right?

yeah.

 

[juanrga]

Valve develops its own Intel graphics driver for Linux
http://www.fudzilla.com/news/graphics/37203-valve-develops-its-own-intel-graphics-driver-for-linux
intel gfx driver so bad that even valve think it can do better! very nice!

No. Intel open drivers are well appreciated within linux community by their quality and documentation, unlike AMD/Nvidia. Fudzilla forgot to quote this part from the source:

While Intel graphics hardware isn't the fastest, it's very common and also most easy to target for an open-source driver given Intel's extensive hardware specifications / programming documentation that they routinely release for new generations. The Intel DRM kernel driver is also in great shape. On the NVIDIA side, the Nouveau community is largely left for reverse-engineering. For open-source Radeon graphics, AMD mostly has just been putting out code these days with not as much key documentation as in recent years, and when docs do come it is after the fact.

However, this news is about Vulkan drivers and Valve goal is not what you pretend. Intel prefer to wait to final API, whereas Valve developed a preliminary driver to help first game developers:

The Vulkan API is still being argued about and will not be finalised until later this year, but Valve has been developing their own Intel GPU reference driver for Vulkan to help early adopters boot-strap their code.

 

[de5_Roy]

No. Intel open drivers are well appreciated within linux community by their quality and documentation, unlike AMD/Nvidia. Fudzilla forgot to quote this part from the source:

However, this news is about Vulkan drivers and Valve goal is not what you pretend. Intel prefer to wait to final API, whereas Valve developed a preliminary driver to help first game developers:

before parroting others, please state your personal experience, in details, with intel's gfx drivers. i want to see how your experience is different from mine.

 

[-Fran-]

No. Intel open drivers are well appreciated within linux community by their quality and documentation, unlike AMD/Nvidia. Fudzilla forgot to quote this part from the source:

However, this news is about Vulkan drivers and Valve goal is not what you pretend. Intel prefer to wait to final API, whereas Valve developed a preliminary driver to help first game developers:

before parroting others, please state your personal experience, in details, with intel's gfx drivers. i want to see how your experience is different from mine.

I'll just leave this here: http://richg42.blogspot.com/2014/05/the-truth-on-opengl-driver-quality.html

Cheers! 😛

 

[de5_Roy]

I'll just leave this here: http://richg42.blogspot.com/2014/05/the-truth-on-opengl-driver-quality.html

Cheers! 😛

the comments... 😆
but that's from the independent developer p.o.v. while mine is end-user p.o.v.
driver developers deserve credit for continuously contributing to linux ecosystem.

edit2: thanks for the link. i figured out which vendor is which before the comments. i think i know the other lettered vendors are as well. i don't usually get devs' p.o.v. on working with vendors. it was a nice read.

edit3: i guess vulkan will alleviate a lot of these problems. in time. after the developers get to know it well and get over the initial barrier of entry.

 

[jdwii]

Yes everyone knows it was a pain to work on linux that is now going to end for API's hate to say it but something tells me 12 is really going to smack those steam machines from being real competition to windows for gaming now(unless its truly easy to write the game for both API's).

Sad to i really wanted to see Microsoft compete with Linux in gaming i mean like a 50/50 split competition. Not what linux is today with only 1% of PC games being on it. Dying light on linux was very bad offered half the performance that it did on windows just proving how much they truly cared outside of PR.

 

[juanrga]

Intel shows Broadwell-K processors finally. They come with Iris Pro graphics, which means AMD only advantage over Intel is vanishing

http://wccftech.com/intel-demonstrates-65w-broadwell-k-socketed-processors-gdc-2015-features-iris-pro-igpu-launching-mid2015/

Wonder what the temps will be might just get that and sell this new CPU to my friend who wants it .

I really thought they would just skip this series or delay skylake to help sell these parts

http://www.theregister.co.uk/2015/03/05/intel_core_i7_iris_pro/

The 65W Core i7 chip will run relatively cool, Baker promised, and so will be aimed at all-in-one PCs and small form-factor systems. In April, Intel will ship the processor in one of its fanless Next Unit of Computing (NUC) PCs, and showed off a palm-sized example using a 28W Core i7 running Iris 6100 in a 0.67 litre case.

 

[juanrga]

I'll just leave this here: http://richg42.blogspot.com/2014/05/the-truth-on-opengl-driver-quality.html

Cheers! 😛

the comments... 😆
but that's from the independent developer p.o.v. while mine is end-user p.o.v.
driver developers deserve credit for continuously contributing to linux ecosystem.

edit2: thanks for the link. i figured out which vendor is which before the comments. i think i know the other lettered vendors are as well. i don't usually get devs' p.o.v. on working with vendors. it was a nice read.

edit3: i guess vulkan will alleviate a lot of these problems. in time. after the developers get to know it well and get over the initial barrier of entry.

That link was given by gamerk before in the AMD thread and discussed in deep, but well my question is why do you think a new API will change drivers situations and strategies of the companies?

 

[de5_Roy]

That link was given by gamerk before in the AMD thread and discussed in deep, but well my question is why do you think a new API will change drivers situations and strategies of the companies?

strategies often depend with management decisions. so the outcome may not be favorable despite all the good things the new api would be bringing to the table.

the new api may be able to improve the driver situation (as described by independent developers) by drawing them to the new api's improvements. but that's only my opinion. like in the article says, hardware vendors are very different from each other, their tech support, cooperation, time taken to patch etc. everything is different. the worst outcome may be nothing changes in the end.