Computex 2018: Intel demos 28-core processor at 5 GHz

Subject: Processors | June 5, 2018 - 11:40 AM |
Tagged: X399, X-Series, Intel, HEDT, 28 core

If you thought running at 5 GHz was neat with a 6-core part, Intel had another surprise for you last night. As part of its Computex keynote, the company demonstrated a 28-core processor running at 5 GHz on all cores, planned for the HEDT segment sometime before the end of 2018.

We don't have a lot of detail on this demo, including what socket this is using, whether this is a single monolithic die design or a multi-chip package using EMIB, or if this is will cost you more than your current domicile to purchase.

intel28core.jpg

Image courtesy The Verge

It showed a score of 7334 on Cinebench R15. Think about that - the 18-core Core i9-7980XE is our current stock leader in this test with a result of 3346. That means this 28-core processor demo was 2.19x faster than the current fastest part on the market!! 

intel28corecb.jpg

Image courtesy Tom's Hardware

All of the unknown factors make it slightly less exciting, to be honest. What power draw was it running at? Is this viable for a consumer platform, in reality? Is 5 GHz a possibility for us mere mortals? Clearly if you are in need of extreme multi-threading capability and performance for rendering, encoding, or mega-tasking, it appears Intel may have the best solution available come this holiday season.

UPDATE 6/6/18: It has now been confirmed by people on the ground in Taipei that the Intel 28-core demo was a complex feat. The motherboards were built by ASUS and Gigabyte, modifications of a server-class LGA3647 socket board that required a 32-phase power system, and a 1HP (horsepower) water chiller and refrigerant to drop the liquid to a cool 4 degrees Celsius. The processor is a single-die part, basically a Xeon Scalable Platinum 8180, that has a list price of $10,000.

Obviously this is not a configuration that any reasonable consumer, even the crazy ones really, would be willing to employ. It means motherboards with the X299 chipset will not be compatible with this part as it requires a new socket. It also means that clock speeds for real-world designs will be much lower, likely a Gigahertz or more. 

There are a lot of questions to poke around about before the end of the year if we are truly going to understand Intel's plans for the enthusiast platform at the end of 2018.

Source: Intel

Computex 2018: Intel announces Core i7-8086K officially, 6 cores at 5 GHz

Subject: Processors | June 5, 2018 - 11:20 AM |
Tagged: kaby lake, Intel, core i7, 8086K

It should come as no real surprise to those of you that read PC Perspective, but Intel officially unveiled the new Core i7-8086K processor during its keynote last night in Taipei at Computex. The specs are right in line with expectations, offering a 6-core / 12-thread chip with a peak Turbo clock speed of 5.0 GHz.

  Core i7-8700K Core i7-8086K
Architecture Coffee Lake Coffee Lake
Process Tech 14nm++ 14nm++
Cores/Threads 6/12 6/12
Base Clock 3.7 GHz 4.0 GHz
Turbo Clock 4.7 GHz 5.0 GHz
Cache 12MB 12MB
Memory Support DDR4-2666 DDR4-2666
PCIe Lanes 16 16
TDP 95 watts 95 watts (probably)
Socket LGA115x LGA115x
Price $349 $??

Full Intel Ark Listing

The Core i7-8086K is a limited edition part with just 50,000 expected to be built, in celebration of the company's 50th anniversary and the 40th anniversary of the original Intel 8086 x86 processor. Pricing hasn't been released, but Intel is running a sweepstakes to give away 8,086 of the CPUs and it lists $425 as the value in the fine print, so that seems like a good guess.

8080k.png

The 300 MHz increases in base and Turbo clock speeds is impressive while sitting inside the same 95 watt TDP. We are eager to get one in for testing ourselves and see how that works in practice, though the limited edition nature of the part makes it a bit less interesting in the long run. (We were considering moving our GPU testbed to this for example, but using a part that may not be available for replication of our data in the future seems like a bad idea.)

I am sure many were hoping this limited edition part would be, or would be in addition to, an 8-core processor launch at Computex, but it doesn't appear that is in the cards.

Source: Intel

Report: Intel i7-8086K Anniversary Edition CPU Listed by Retailers

Subject: Processors | May 30, 2018 - 11:18 AM |
Tagged: VideoCardz, rumor, report, processor, Intel, history, cpu, anniversary edition, 8086K, 8086

The 40th anniversary of the original Intel 8086 microprocessor launch is just days away (June 8), and ahead of this VideoCardz.com has posted screen captures of online listings for the rumored 8086 anniversary CPU - the Core i7-8086K.

VideoCardz_8080K_Screens.png

(Screen captures above sourced from VideoCardz.com)

From VideoCardz.com:

"Some retailers have already started listing the new SKU on their websites, indicating 70 USD/EUR premium over i7-8700K (~480/470 EUR). Not much is known at this point, but the CPU is rumored to be 5.0 GHz chip out of the box. It is, however, still expected to be a 6-core SKU."

Beyond the online retailer listings accidentally posted early, presumably, not much is known; though it seems fair to conclude that this may indeed be a higher-clocked version of the current i7-8700K and would therefore remain a 6-core/12-thread product. Intel is going to be at Computex beginning June 5 where they "will showcase how the company is powering the future of computing" so might we hear an announcement of a new product on the eve of the 8086 anniversary? The possibility is too logical to ignore.

Source: VideoCardz

Spectre 3a and Spectre 4 Unfortunately Announced...

Subject: Processors | May 22, 2018 - 07:51 PM |
Tagged: x86, arm, Intel, amd, spectre

Security researchers at Microsoft and Google have found two new vulnerabilities along the lines of the Spectre and Meltdown bugs from early January. These are being called Spectre 3a (Rogue System Register Read) and Spectre 4 (Speculative Store Bypass). Like last time, hardware and software vendors have addressed the issues, which will be coming down via OS updates.

bond-2018-spectre-joke.jpg

Naturally, James Bond will steal information when there's Intel Inside.

On the AMD side of things, they claim that the Spectre 4 vulnerability will be patched as far back as Bulldozer (2011). They also claim that no action will be necessary, at least to their knowledge, for Spectre 3a on their x86 parts. They have also released a short, five-page whitepaper discussing the issue.

On the Intel side of things… a security bulletin has been posted for CPUs as far back as Nehalem. They don’t exactly clarify which processors are susceptible to which vulnerabilities, but they acknowledge that both Spectre 3a and Spectre 4 touch something on their product stack to some extent. They have submitted a beta microcode update to OS vendors, which they expect to be production ready “in the coming weeks”.

ARM is also affected to some extent. They have published a table that lists which architectures are vulnerable to what exploit. Interestingly, there are some processors that are vulnerable to 3a, but not 4, and others that are vulnerable to 4, but not 3a (and, of course, some that are vulnerable to both and neither). Since these exploits are based on optimizations gone awry, you would think that it would have built up over time, but that doesn’t seem to be the case. The only pattern I could notice is that Variant 4 only affects newish 64-bit ARM processors. I don’t know if that’s a red herring, or a well-known corollary of the bug that I just don’t know enough about, but it’s about all that I can see.

Regardless, expect patches soon, which might, again, lower performance by some amount.

AMD Releases Updated Raven Ridge Desktop APU Graphics Drivers

Subject: Graphics Cards, Processors | May 18, 2018 - 04:33 PM |
Tagged: Vega, ryzen, raven ridge, Radeon Software Adrenalin Edition, r5 2400g, r3 2200g, amd

Today, AMD released the first driver update for the desktop Raven Ridge APUs since their launch in February of this year.

The new Q2 2018 drivers are based on AMD's current Radeon Software Adrenalin Edition release and bring features such as ReLive and the Radeon overlay to the Vega-powered desktop platform.

adrenalin-74.jpg

We haven't had a lot of time to look for potential performance enhancements this driver brings yet, but we did do a quick 3DMark run on our Ryzen 5 2400G with memory running at DDR4-3200.

3dmark-fs.png

Here, we see healthy gains of around 5% in 3DMark Firestrike for the new driver. While I wouldn't expect big gains for older titles, newer titles that have come out since the initial Raven Ridge drive release in February will see the biggest gains.

We are still eager to see the mobile iterations of AMD's Raven Ridge processors get updated drivers, as notebooks such as the HP Envy X360 have not been updated since they launched in November of last year.

It's good to see progress from AMD on this front, but they must work harder to unify the graphics drivers of their APU products into the mainstream graphics driver releases if they want those products to be taken seriously as gaming options.

Source: AMD

While we await Ryzen 5 Pro 2500U benchmarks, here's some Ryzen 5 2600 performance for you

Subject: Processors | May 16, 2018 - 02:46 PM |
Tagged: amd, ryzen 2, Ryzen 5 2600, Core i5-8400

There are no benchmarks of the new Ryzen Pro series to offer as of yet, so why not check out a few hundred benchmarks pitting the $190 Ryzen 5 2600 against the $180 Core i5-8400?  Techspot takes you on a tour of games, from ARK Survival Evolved through PUBG to Warhammer Total War to see what effect your choice of processor has when gaming on a GTX 1080 Ti.  When the dust settled there were two obvious choices for prospective buyers.  For those who want a simple solution, the i5-8400 makes sense as it will offer decent performance right out of the box, no fiddling required.  On the other hand, for those who are not completely boring, the Ryzen 5 2600, overclocked to 4.2GHz paired with DDR4-3400 is clearly better overall. 

Check out the performance of your favourite games in the full review and then scream about the unfairness of it all below.

2018-05-16-image-4.jpg

"For the past few weeks we've been busy benchmarking AMD's Ryzen 5 2600 and Intel's Core i5-8400. For testing we have 36 games on the menu, each tested at 720p, 1080p and 1440p using the GeForce GTX 1080 Ti. That is, 324 individual tests, three times each... almost 1,000 benchmark runs, so grab a drink, some snacks and get comfortable."

Here are some more Processor articles from around the web:

Processors

 

Source: TechSpot

Two scoops of Ryzen, eat on the go or at your desk

Subject: General Tech, Processors | May 15, 2018 - 01:49 PM |
Tagged: ryzen pro, amd, APU, ryzen 7 pro 2700u, Ryzen 5 Pro 2500U, Ryzen 3 Pro 2300U, Ryzen 5 Pro 2400G, Ryzen 5 Pro 2400GE, Ryzen 3 Pro 2200G

AMD have extended both their processor lineup as well as their names, by sticking Pro into the already verbose Ryzen 2 series, and added another letter to pay attention to as well.   The 2xxxU series are mobile APUs which you won't see running around in the wild, the 2xxxG desktop series you certainly will, however there is also an E you need to pay attention to. 

The Ryzen 5 Pro 2400G is a 65W part which will offer four multi-threaded cores topping out at 3.9GHz, with 11 Vega CUs and ships with the Wraith Stealth cooler. The Ryzen 5 Pro 2400GE is almost as similar as the name but tops out at 3.8GHz, also has 11 Vega CUs and sports an impressive TDP of 35W, which may be part of the reason why it doesn't ship with a cooler. 

The series looks to offer a great choice for someone building a machine without a GPU installed, whether they intend to add one at a later time or not.  The naming conventions being used by Intel and AMD are getting far too easy to confuse already, without adding possible confusion within single product lines.  Let's hope this does not continue for too long.  The Inquirer lists all the models, mobile and desktop, on this page.

82446-raven-am4-ryzen-5-vega-pib-left-facing-1260x709.png

"Alongside the usual specs, the chips all have the built-in security and onboard encryption features of the Ryzen Pro CPUs, designed to make them appeal for commercial and enterprise use."

Here is some more Tech News from around the web:

Tech Talk

Source: The Inquirer

Precisely what are AMD's XFR 2 and Overdrive?

Subject: Processors | May 11, 2018 - 02:43 PM |
Tagged: amd, ryzen, xfr2, precision boost 2, Precision Boost Overdrive

Whether you have had a chance to play around with a new Ryzen processor or not, you might benefit from more information on what XFR2 and Precision Boost 2 are and what they are not.  [H]ard|OCP spent some time to write an article that dispels the rumours which have been spread, especially the fact that these are both unreleased at the moment.  Together they will provide support for Precision Boost Overdrive, which could be supported by Ryzen Zen+ CPUs on an X470 motherboard, at least in theory.  When enabled it will utilize the ability of the new Ryzen Master software to monitor your motherboards VRM usage and if it sees it is below it capacity it will relax the vCore limiter on your CPU allowing more juice to flow in which can be used to increase the frequency of your Zen + chip.  It will be interesting to see how effective this is, but for now all we can do is read about it.

master.PNG

"We wanted to put together a quick overview about what Precision Boost 2 and XFR2 are NOT about. It seems that slides leaked, and faked, earlier in the 2nd generation Ryzen's development have clouded some people's understanding on what features are included, but more important which features are not."

Here are some more Processor articles from around the web:

Processors

 

Source: [H]ard|OCP

Microsoft releases 64-bit SDK for Windows on Arm platforms

Subject: Processors, Mobile | May 8, 2018 - 07:30 PM |
Tagged: windows on snapdragon, windows on arm, microsoft, 64-bit

During the Microsoft BUILD developer conference, the Windows initiative for Qualcomm and Arm processors got a much needed shot in the arm (heh) with announced support for a 64-bit SDK.

Visual Studio 15.8 Preview 1 contains the early version of these tools that will give developers the ability to build native 64-bit Arm apps. Microsoft claims that this “represents the next step in the evolution of the Always Connected PC running Windows 10 on ARM” and I couldn’t agree more.

qcwindows.jpg

This gives software developers the ability to target Arm-based processors like the Snapdragon 835 from Qualcomm natively without forcing users to depend on emulation layers provided by Microsoft. While the emulation layer is critical for compatibility, it does slow performance quite a bit compared to native-running code.

While the Windows Store already supports ARM32 packages, ARM64 packages will be supported “soon” based on what Microsoft is telling us. Even more interesting, Microsoft is promoting the ability for developers to post the Win32 (non-Store) ARM64 version of software online, rather than waiting for the Store apps to be approved.

The Microsoft website has details on how developers can start this integration. Qualcomm has its own documentation as well.

From my own view, this a necessary step for Microsoft to take, even if it does seem later than many would have liked. The benefits of Windows 10 running on Snapdragon and Arm are real and substantial, but being hindered by performance due to emulation was always known to be a speedbump. Getting developers access to better, and easier to use, Arm compilation is the next step.

I would also like to see Microsoft take a more proactive role in pushing developers to offer both versions of software. MS simply cannot take a passive, backseat approach to the Always On, Always Connected PC initiative and have it be a success.

Source: Microsoft

Intel Kicks Kaby Lake-X CPUs to the Curb

Subject: Processors | May 1, 2018 - 10:25 AM |
Tagged: kaby lake-x, Intel, 7740x, 7640x

So, do you remember the Kaby Lake-X processors that launched along side the Skylake-X parts back on June 19, 2017. These are (were) 14nm+ processors built into the LGA2066 socket as a part of the X299 chipset launch. They shipped as the Core i7-7740X (4-core, 8-thread) and Core i5-7640X (4-core, 4-thread) and at the time I had this to say about them:

These are very…interesting CPUs. They do not offer new features compared to the Core i7-7700K or Core i5-7600K, but run at barely higher clocks (100 MHz on the base on the 7740X for example). They don’t see more PCIe integration, they don’t have larger caches. They are basically the same Kaby Lake design we have come to know previously but in a new package and prepped for a new set of motherboards. Is that an advantage? It’s hard to know yet, but in general, the X299 motherboard market is going to be more expensive than the Z270 motherboard market, meaning you are going to pay more in total to own this CPU. Does the added TDP give us more thermal headroom for overclocking? Maybe the new heat spreader? I’m not sure and Intel hasn’t said yet. But what they have stated is that they wanted to offer the option to consumers that wanted the “absolute fastest gaming processor” with the best clock speeds at a reasonable price.

7740x.jpg

Even in June, the value and positioning of the Kaby Lake-X processor was a mystery. Well Intel has fixed all of that today by announced end-of-life for both of those processors.

7740x-eol.png

Intel's language in the release is kind of interesting: "Market demand for the products listed in the "Products Affected/Intel Ordering Codes" tables below have shifted to other Intel products." Yeah, I bet it has. 

These were parts without a real audience, and their creation was a consistent mystery to the enthusiast market Intel targeted. For many, it was a honest sign that Intel has lost track of what the PC market was asking for. At least the short lifespan of the pair indicates that Intel got the message loud and clear.

If you are so inclined, you can still pick up the 7740X and 7640X for a while longer. Here is the table of Kaby Lake-X's remaining life.

7740x-eol2.png

You can read the entire Intel document here if you'd like. 

Source: Intel