All | Editorial | General Tech | Graphics Cards | Networking | Motherboards | Cases and Cooling | Processors | Chipsets | Memory | Displays | Systems | Storage | Mobile | Shows and Expos
Subject: General Tech, Processors | September 6, 2018 - 01:22 PM | Jeremy Hellstrom
Tagged: amd, athlon, Zen, Vega, 200GE, PRO 200GE, ryzen, Ryzen 7 PRO 2700X, Ryzen 7 PRO 2700, Ryzen 5 PRO 2600
AMD is returning the Athlon name to active service with the arrival of the Athlon 200GE, combining their current Zen core with three Radeon Vega 3 GCUs and a GPU core of 1GHz. The dual core, multithreaded processor will run at 3.2GHz with a TDP of 35W, which should give you an idea of where you will find this new chip.
Along with the new Athlon comes four new Pro chips, the AMD Athlon PRO 200GE, Ryzen 7 PRO 2700X, Ryzen 7 PRO 2700 and Ryzen 5 PRO 2600. These will be more traditional desktop processors with enterprise level features to ensure the security of your systems as well as offering flexibility; with a cost somewhat lower than the competitions.
Subject: Processors, Mobile | September 2, 2018 - 11:45 AM | Sebastian Peak
Tagged: SoC, octa-core, mobile, Mali-G76, Kirin, Huawei, HiSilicon, gpu, cpu, Cortex-A76, arm, 8-core
Huawei has introduced their subsidiary HiSilicon’s newest mobile processor in the Kirin 980, which, along with Huawei's claim of the world's first commercial 7nm SoC, is the first SoC to use Arm Cortex A76 CPU cores and Arm’s Mali G76 GPU.
Huawei is aiming squarely at Qualcomm with this announcement, claiming better performance than a Snapdragon 845 during the presentation. One of its primary differences to the current Snapdragon is the composition of the Kirin 980’s eight CPU cores, notable as the usual 'big.LITTLE' Arm CPU core configuration for an octa-core design gives way to a revised organization with three groups, as illustrated by AnandTech here:
Of the four Cortex A76 cores just two are clocked up to maximize performance with certain applications such as gaming (and, likely, benchmarks) at 2.60 GHz, and the other two are used more generally as more efficient performance cores at 1.92 GHz. The remaining four A55 cores operate at 1.80 GHz, and are used for lower-performance tasks. A full breakdown of the CPU core configuration as well as slides from the event are available at AnandTech.
Huawei claims that the improved CPU in the Kirin 980 results in "75 percent more powerful and 58 percent more efficient compared to their previous generation" (the Kirin 970). This claim translates into what Huawei claims to be 37% better performance and 32% greater efficiency than Qualcomm’s Snapdragon 845.
The GPU also gets a much-needed lift this year from Arm's latest GPU, the Mali-G76, which features "new, wider execution engines with double the number of lanes" and "provides dramatic uplifts in both performance and efficiency for complex graphics and Machine Learning (ML) workloads", according to Arm.
Real-world testing with shipping handsets is needed to verify Huawei's performance claims, of course. In fact, the results shown by Huawei at the presentation carry a this disclaimer, sourced from today’s press release:
"The specifications of Kirin 980 does not represent the specifications of the phone using this chip. All data and benchmark results are based on internal testing. Results may vary in different environments."
The upcoming Mate 20 from Huawei will be powered by this new Kirin 980 - and could very well provide results consistent with the full potential of the new chip - and that is set for an official launch on October 16.
The full press release is available after the break.
Subject: Processors | August 31, 2018 - 10:36 AM | Ken Addison
Tagged: Threadripper, ryzen, 2nd generation threadripper, 2990wx, 2950x
Today, AMD's 2nd generation Ryzen Threadripper 2950X has finally reached retail availability. As you might remember from the launch a few weeks ago, the 32-core Threadripper 2990WX has already been on store shelves, but the 2950X was set to arrive on August 31st.
For those that need a bit of a refresher on 2nd generation Threadripper, you check out our full review of both the 2950X and 2990WX. Ultimately, we found the Threadripper 2950X is a great CPU for people looking to bridge the gap between content creation and gaming, with near top-level performance in both areas.
The 12-core and 24-core variants of 2nd generation Threadripper processors are still set to be coming later in the year.
Subject: Processors, Mobile | August 28, 2018 - 04:00 PM | Ken Addison
Tagged: whiskey lake, mobile, Intel, ifa 2018, amber lake, 8th generation
Tonight at the consumer electronics trade show IFA in Berlin, Intel announced their latest processors aimed at thin-and-light notebooks and 2-in-1 devices. Continuing the ever elongated 8th generation processor family from Intel, these new mobile CPUs are comprised of both 5W (Amber Lake-Y) and 15W (Whiskey Lake-U) parts.
|Core i7-8565U||Core i7-8550U||Core i5-8265U||Core i5-8250U||Core i3-8145U|
|Architecture||Whiskey Lake||Kaby Lake Refresh||Whiskey Lake||Kaby Lake Refresh||Whiskey Lake|
|Base Clock||1.8 GHz||1.8 GHz||1.6 GHz||1.6 GHz||2.1 GHz|
|Max Turbo Clock||4.6 GHz||4.0 GHz||3.9 GHz||3.6 GHz||3.9 GHz|
Just as we saw with the Kaby Lake Refresh CPUs last year, these 15W parts maintain the same quad-core, eight-thread configurations.
On the highest end part, the i7-8565U, we see an increase of 600MHz on the max turbo clock, while the base clock remains the same. The i5-8265U sees a smaller uptick of 300MHz boost while also keeping the same base clock of 1.6GHz as the previous generation.
|Core i7-8500Y||Core i7-7Y75||Core i5-8200Y||Core i5-7Y75||Core m3-8100Y||Core m3-7Y32|
|Architecture||Amber Lake||Kaby Lake||Amber Lake||Kaby Lake||Amber Lake||Kaby Lake|
|Base Clock||1.5 GHz||1.3 GHz||1.4 GHz||1.2 GHz||2.1 GHz||1.1 GHz|
|Max Turbo Clock||4.2 GHz||3.6 GHz||3.9 GHz||3.3 GHz||3.9 GHz||3.0GHz|
As we can see, the Amber Lake CPUs provide a significant frequency advantage over the previous Kaby Lake-Y processors, especially with the turbo frequencies ranging from 600-900MHz improvements.
These higher frequencies give these low power processors a substantial performance uptick from the previous generation, as long as the thermal solutions in the end product notebooks are up to the task of actually achieving these high turbo boost frequencies.
Across the board, Intel is marketing these CPU platforms as having increased connectivity options, with built-in 802.11AC 160MHz dual-band Wi-Fi support (which Intel is referring to as Gigabit WiFi). Additionally, both the Amber Lake and Whiskey Lake families have options to be paired with Intel LTE modems for cellular connectivity.
Also on the connectivity side, we see support for native USB 3.1 Gen 2 (10 Gbps) ports through the chipset on Whiskey Lake-U.
Intel is also touting battery life improvements with "16 hours on a single charge with power-optimized systems targeted to achieve about 19 hours" on the Whiskey Lake-U platform. However, as always, take these specifications with a grain of salt until we see real products with these processors integrated into them and benchmarked.
Subject: Processors | August 21, 2018 - 03:51 PM | Jeremy Hellstrom
Tagged: 2990wx, threadripper 2, linux, windows 10, amd
Windows 10 is much better at dealing with multithreaded tasks but Linux has been optimized for both high core counts and NUMA for quite a while, so looking at the performance difference is quite interesting. Phoronix tested a variety of Linux flavours as well as Windows 10 Pro and the performance differences are striking, in some cases we see results twice as fast on Linux as Win10. That does not hold true for all tests as there are some benchmarks which Windows excels at. Take a look at this full review as well as those under the fold for a fuller picture.
"Complementing the extensive Linux benchmarks done earlier today of the AMD Threadripper 2990WX in our review (as well as on the Threadripper 2950X), in this article are our first Windows 10 vs. Linux benchmarks of this 32-core / 64-thread $1799 USD processor. Tests were done from Microsoft Windows 10 against Clear Linux, Ubuntu 18.04, the Arch-based Antergos 18.7-Rolling, and openSUSE Tumbleweed."
Here are some more Processor articles from around the web:
- AMD's Ryzen Threadripper 2950X @ The Tech Report
- Threadripper 2990WX - 2950X & Wraith Ripper DIY Install @ [H]ard|OCP
- Linux vs. Windows Benchmark: Threadripper 2990WX vs. Core i9-7980XE Tested
- A Look At The Windows vs. Linux Scaling Performance Up To 64 Threads With The AMD 2990WX @ Phoronix
- The Mega-Tasking Test: AMD Threadripper 2990WX Heavy Multitasking Benchmark @ Techspot
- Armari AMD Ryzen Threadripper 2990WX – 32-Core Threadripper 2 Workstation @ Kitguru
- A Quick Look At The Windows Server vs. Linux Performance On The Threadripper 2990WX @ Phoronix
Subject: Processors | August 13, 2018 - 02:18 PM | Jeremy Hellstrom
Tagged: Zen+, Threadripper, second generation threadripper, ryzen, Intel, Core i9, 7980xe, 7960x, 7900x, 2990wx, 2950x
The 2950X and 2990WX are both ThreadRipper 2 chips but are very different beasts under the hood. The 2950X has two active die similar to the original chips while the 2990WX has four active die, two of which utilize an Infinity Fabric link to the other two to communicate to the memory subsystem. The W in the naming convention indicates the 2990WX is designed for workstation tasks and benchmarks support that designation. You will have seen our results here, but there are many other sources to read through. [H]ard|OCP offers up a different set of benchmarks in their review, with a similar result; with ThreadRipper AMD has a winner. The 2990WX is especially important as it opens up the lucrative lower cost workstations market for AMD.
"AMD teased us a bit last week by showing off its new 2nd Generation Threadripper 2990WX and 2950X packaging and specifications. This week AMD lets us share all our Threadripper data we have been collecting. The 2990WX is likely a lot different part than many people were expecting, and it turns out that it might usher AMD into a newly created market."
Here are some more Processor articles from around the web:
- AMD's Ryzen Threadripper 2990WX @ The Tech Report
- AMD Ryzen Threadripper 2950X and 2990WX @ Guru of 3D
- AMD Ryzen Threadripper 2990WX & 2950X @ TechSpot
- AMD Ryzen Threadripper 2950X @ TechPowerUp
- AMD Threadripper 2950X Offers Great Linux Performance At $900 USD @ Phoronix
- AMD Threadripper 2990WX Linux Benchmarks: The 32-Core / 64-Thread Beast @ Phoronix
- AMD Threadripper 2990WX Cooling Performance - Testing Five Heatsinks & Two Water Coolers @ Phoronix
Subject: Processors | August 9, 2018 - 04:36 PM | Jeremy Hellstrom
Tagged: Ryzen 7 2700, amd, Zen+
There is a ~$30 difference between the Ryzen 7 2700 and the 2700X, which begs the question as to whom would chose the former over the latter. The Tech Report points out another major difference between the two processors, the 2700 has a 65W TDP while the 2700X is 105W; pointing to one possible reason for choosing the less expensive part. The question remains as to what you will be missing out on and if there is any reason not to go with the even less expensive and highly overclockable Ryzen 7 1700? Find out the results of their tests and get the answer right here.
"AMD's Ryzen 7 2700 takes all the benefits of AMD's Zen+ architecture and wraps eight of those cores up in a 65-W TDP. We tested the Ryzen 7 2700's performance out in stock and overclocked tune to see what it offers over the hugely popular Ryzen 7 1700."
Here are some more Processor articles from around the web:
- One year with Threadripper @ TechSpot
- Battle of the Workstations: AMD Ryzen Threadripper vs Intel Core X-Series @ Techgage
- We Test a $1,000 CPU From 2010 vs. Ryzen 3 @ TechSpot
- Intel's Spectre 'Variant 4' Performance Tested: Speculative Store Bypass @ TechSpot
- Qualcomm's Snapdragon 670 packs high-end features into a mid-range chip @ The Inquirer
Subject: Processors | August 8, 2018 - 07:39 PM | Ken Addison
Tagged: xeon, intel DL boost, Intel, ice lake, dcg, data centric, cooper lake, cascade lake
Today at Intel's Data Center Group's Data-Centric Innovation Summit, they provided a peek into the future of Xeon processors.
Coming later this year are the oft-rumored Cascade Lake Xeons. In addition to supporting Optane DC Persistent memory, Cascade Lake will offer hardware-based mitigations for Spectre/Meltdown vulnerabilities.
Intel Deep Learning Boost will also make its first appearance in the Cascade Lake products. In its first iteration, DL Boost will provide a vector neural network instruction set (VNNI) based on AVX-512 for faster inference acceleration. Intel is working to add VNNI to industry standard deep learning frameworks like TensorFlow and Caffe.
Next, in late 2019, we have the Cooper Lake architecture. Still based on 14nm technology, Cooper Lake will expand upon Intel DL Boost and add support for the BFloat16 data type, which provides the same level of precision as double precision (32-bit) floating points, but in a smaller (16-bit) data size.
In 2020, after Cooper Lake, comes Ice Lake – the first 10nm-based Xeon. While details are sparse about what improvements Ice Lake will bring architecturally, Intel has said that it will be compatible with Cooper Lake platforms, giving users an upgrade path.
Subject: Processors | August 6, 2018 - 09:00 AM | Ken Addison
Tagged: Zen+, XFR 2.0, Threadripper, StoreMI, ryzen, r7 2700x, Pinnacle Ridge, Intel, Core i9-780xe, amd, 2nd generation threadripper, 12nm
First teased at Computex earlier this summer, AMD has now released details and availability information for their 2nd Generation Threadripper CPUs.
Based upon the same 12nm Zen+ architecture we saw with the Pinnacle Ridge CPUs like the R7 2700X, Threadripper will now be split into two product families, the X, and the WX series.
The X-series is mostly a refresh of the Threaripper SKUs that we saw last year, with 12 and 16-core variants. The Threadripper 2920X and 2950X will retain the same two die, 4 CCX arrangement that we saw with the previous generation, with the ability to run in either unified or non-unified memory modes.
Notably, the 8-core variant found in the original Threadripper lineup seems to be absent in the 2nd generation.
This new generation of Threadripper comes in less expensive than the last, with a $50 price drop on the 12-core CPU, and a $100 price drop on the 16-core variant.
The newest aspect of the 2nd Generation Threadripper Lineup is the addition of the "WX" series processors. These higher core count processors are being marketed by AMD more towards "Creators and Innovators" rather than gamers.
Available in both 24 and 32-core variants, the Threadripper WX series represents the highest core count consumer CPUs ever launched. Since we know that Zen+ dies contain a maximum of 8 cores, we can assume that these processors are using a 4 die configuration, similar to the EPYC server parts, but likely with the same 64 lanes of PCIe and 4 channel memory controllers
This pricing is extremely aggressive compared to the highest core count competitor from Intel, the $2000 18-core i9-7980XE.
All 2nd Generation Threadripper CPUs will include the 2nd Generation Zen features that we saw in the R7 2600 and 2700 series, including XFR 2.0, StoreMI, and improved memory support and latency.
Additionally, these new Threadripper CPUs will use the existing X399 chipset, with UEFI updates being made available for existing X399 boards, as well as some new variants such as the MSI MEG X399 Creation launching alongside the new CPUs.
Availability of these processors is staggered, with the 32-core WX CPU shipping first on August 13th (and available now for preorder on Newegg and Amazon), followed shortly by the 16-core 2950X. However, we won't see the 12 and 24 variants until October.
Stay tuned for our review of these parts as they reach retail availability!
Subject: Graphics Cards, Processors | August 3, 2018 - 04:41 PM | Ryan Shrout
Tagged: Zen, Vega, SoC, ryzen, China, APU, amd
Continuing down the path with its semi-custom design division, AMD today announced a partnership with Chinese company Zhongshan Subor to design and build a new chip to be utilized for both a Chinese gaming PC and Chinese gaming console.
The chip itself will include a quad-core integration of the Zen processor supporting 8 threads at a clock speed of 3.0 GHz, no Turbo or XFR is included. The graphics portion is built around a Vega GPU with 24 Compute Units running at 1.3 GHz. Each CU has 64 stream processors giving the “Fenghuang” chip a total of 1536 SPs. That is the same size GPU used in the Kaby Lake-G Vega M GH part, but with a higher clock speed.
The memory system is also interesting as Zhongshan Subor has integrated 8GB of GDDR5 on a single package. (Update: AMD has clarified that this is a GDDR5 memory controller on package, and the memory itself is on the mainboard. Much more sensible.) This is different than how Intel integrated basically the same product from AMD as it utilized HBM2 memory. As far as I can see, this is the first time that an AMD-built SoC has utilized GDDR memory for both the GPU and CPU outside of the designs used for Microsoft and Sony.
This custom built product will still support AMD and Radeon-specific features like FreeSync, the Radeon Software suite, and next-gen architecture features like Rapid Packed Math. It is being built at GlobalFoundries.
Though there are differences in the apparent specs from the leaks that showed up online earlier in the year, they are pretty close. This story thought the custom SoC would include a 28 CU GPU and HBM2. Perhaps there is another chip design for a different customer pending or more likely there were competing integrations and the announced version won out due to cost efficiency.
Zhongshan Subor is a Chinese holding company that owns everything from retail stores to an education technology business. You might have heard its name in association with a gluttony of Super Famicom clones years back. I don’t expect this new console to have near the reach of an Xbox or PlayStation but with the size of the Chinese market, anything is possible if the content portfolio is there.
It is interesting that despite the aggressiveness of both Microsoft and Sony in the console space in regards to hardware upgrades this generation, this Chinese design will be the first to ship with a Zen-based APU, though it will lag behind the graphics performance of the Xbox One X (and probably PS4 Pro). Don’t be surprised if both major console players integrate a similar style of APU design with their next-generation products, pairing Zen with Vega.
Revenue for AMD from this arrangement is hard to predict but it does get an upfront fee from any semi-custom chip customer for the design and validation of the product. There is no commitment for a minimum chip purchase so AMD will see extended income only if the console and PC built around the APU succeeds.
Enthusiasts and PC builders have already started questioning whether this is the type of product that might make its way to the consumer. The truth is that the market for a high-performance, fully-integrated SoC like this is quite small, with DIY and SI (system integrator) markets preferring discrete components most of the time. If we remove the GDDR5 integration, which is one of the key specs that makes the “Fenghuang” chip so interesting and expensive, I’d bet the 24 CU GPU would be choked by standard DDR4/5 DRAM. For now, don’t hold out hope that AMD takes the engineering work of this Chinese gaming product and applies it to the general consumer market.
Subject: Processors | August 1, 2018 - 01:24 PM | Ken Addison
Tagged: msi, Z370, Intel, 9900k, 9700, 8700k
Hot on the heels on an Intel Roadmap leak yesterday that points to Intel's upcoming Coffee Lake refresh desktop processors launching as soon a Q3 2018, MSI today confirmed through a news post on their website that these new processors will retain compatibility with at least Z370 motherboards.
The table posted by MSI contains the specific BIOS versions that add compatibility for these new processors for each Z370 motherboard in their lineup. There's no information about other existing Coffee Lake chipsets such as H370 and B360, but previous leaks have pointed towards these motherboards having some level of compatibility with new Intel processors.
The 9000-series is rumored to contain Intel's first 8-core consumer-oriented CPUs, in both non-hyperthreaded (i7-9700K), and hyperthreaded (i9-9900K) forms.
Subject: Processors | July 6, 2018 - 03:16 PM | Jeremy Hellstrom
Tagged: IBM, power9, talos 2, EPYC, xeon
Phoronix were recently given access to three servers running three different POWER9 Talos II configurations and compared them to EPYC and Xeon. On paper these systems look amazing, thanks to the architecture supporting four threads per core; they tested a dual 4-core Talos II system, a Talos II Lite with a single 22-core CPU and a Talos II with dual 18-core processors with thread counts of 32, 88, and 144 respectively.
There were certainly usage scenarios where the dual 18 core system could outpace even the EPYC 7601 but could not surpass the dual Xeon Gold 6138 system. The review covers a fair amount of benchmarks and configurations but doesn't begin to scratch the surface of wide variety of server configurations you need to consider before abandoning POWER9 altogether but the key metric, performance per dollar, shows these architecture solidly in the middle of the pack.
"Back in April we were able to run some IBM POWER9 benchmarks with remote access to the open-source friendly Talos II systems by Raptor Computer Systems. We were recently allowed remote access again to a few different configurations of this libre hardware with three different POWER9 processor combinations. Here are those latest benchmarks compared to Intel Xeon and AMD EPYC server processors."
Here are some more Processor articles from around the web:
- AMD Ryzen 7 2700 and Ryzen 5 2600 @ Modders-Inc
- Intel Pentium Gold G5600 3.9 GHz @ TechPowerUp
- Intel Core i7-8086K @ TechARP
- Intel Core i7 8086K Linux Performance @ Phoronix
- Intel Kaby Lake G Core i7-8705G @ TechSpot
Subject: Processors | June 11, 2018 - 03:50 PM | Jeremy Hellstrom
Tagged: Intel, i7-8086k, coffee lake-s, 8086
Now, before you decided to comment on Ken's i7-8086K article, consider he is not the only one who has encountered issues with Intel's Anniversary silicon. The Tech Report offers succinct advice in their review as well "the i7-8086K isn't worth the $75 upcharge over the i7-8700K at stock speeds." They manually overclocked the chip and found the same 5.1GHz limit, as the processors are thermally identical regardless of the handpicked artisan silicon inside the i7-8086K. The 5GHz stock speed advertised does not seem to be available right out of the box but instead requires a bit of work.
On the other hand, if you like the idea of an Anniversary model CPU and would enjoy manually overclocking, the extra $75 might mean very little to you.
"Intel's Core i7-8086K is the company's first CPU with a 5-GHz Turbo speed out of the box. We dig deep to see whether this chip has the cachet to live up to its limited-edition billing."
Here are some more Processor articles from around the web:
- A Look At How The AMD EPYC Linux Performance Has Evolved Over The Past Year @ Phoronix
- AMD Ryzen 7 2700 Overclocking @ [H]ard|OCP
- AMD's Ryzen Master Overclocking Software @ [H]ard|OCP
- Intel Core i3-8300 3.7 GHz @ TechPowerUp
- AMD Ryzen 5 2600 / Ryzen 7 2700 Benchmarks On Linux, 9-Way Ubuntu CPU Comparison @ Phoronix
Subject: General Tech, Processors | June 8, 2018 - 01:39 PM | Jeremy Hellstrom
Tagged: overclocking, Intel, i7-8086k, der8auer
Der8auer is at it again, this time pushing Intel's Anniversary Edition i7-8086K quickly passing 7GHz in initial overclocking, showing just how well picked these Core i7-8700K's are. He pushed the core voltage up past 1.85V and used an impressive amount of LN to accomplish this feat but he feels there is more to this processor. Having had more time to work on overclocking 8700K's he has successfully pushed them to 7.3GHz, so in theory the 8086K should be able to beat that. Take a look at the video posted on the Inquirer to see this happen.
"The processor, announced this week at Computex, commemorates 40 years of x86 computing and out of the box can hit 5GHz on a single core without overclocking via the chip's boost frequency."
Here is some more Tech News from around the web:
- Blockchain's Once-Feared 51% Attack Is Now Becoming Regular @ Slashdot
- Stop us if you've heard this one: Adobe Flash gets emergency patch for zero-day exploit @ The Register
- GitHub's Nat Friedman confirms no ads, no Microsoft logins, no worries @ The Inquirer
- Talkin’ Treble: How Android engineers are winning the war on fragmentation @ Ars Technica
- WannaCry reverse-engineer Marcus Hutchins hit with fresh charges @ The Register
Subject: Processors | June 5, 2018 - 11:22 PM | Ryan Shrout
Tagged: Zen 2, Zen, rome, amd
The first whiffs of Zen 2 are finally reaching us. During the AMD press conference at Computex today CEO Dr. Lisa Su stood on stage and held up the first public showing of Rome, the codename for AMD’s next-generation EPYC enterprise processor family.
Rome is exciting because it will be the first 7nm high-performance processor in the market, and it makes the 10nm production problems that Intel is having all the more troublesome for the blue-chip giant. And because Rome will be socket compatible with the currently shipping EPYC systems, there is a huge potential for market penetration through 2019.
AMD stated that it would be sampling Rome-based Zen 2 processors to partners in the second half of 2018, with launch in 2019. AMD does have silicon back in the labs, up and running. No more timing detail was given than that.
The competitive statement of AMD putting timeframes on its 7nm server processors, rumored to be going up to 64-cores PER SOCKET, while Intel struggles with its move to 10nm, is significant. AMD still targets a 5% market share for server processors by the end of the year, but it might be 2019 that proves to be a more significant year for the company’s drive back into the server space.
Subject: Processors | June 5, 2018 - 11:03 PM | Ryan Shrout
Tagged: Threadripper, ryzen, amd, 32-core, 12nm
During the keynote address at Computex in Taipei, AMD SVP Jim Anderson was on stage to showcase a preview of the upcoming 2000-series of Threadripper processors for high-end consumer PCs. The Threadripper brand already made waves last year by bringing 16-core and 32-thread designs to the market for the very first time, improving performance for extreme productivity tasks, rendering, development, video, and more.
We knew that the 2000-series was coming this year, based on the 12nm process from GlobalFoundries, just as the Ryzen 2000-series uses, but we have narrowed the availability time frame to Q3 of 2018.
But the big story at the show was that this generation would see a doubling of the maximum core count on Threadripper. Yes, you will be able to buy 32-core and 64-thread AMD Threadripper CPUs later this year!!
Hot on the heels of the impressive, but dubiously cooled, Intel 28-core demo yesterday, AMD is clearly intent on continuing momentum that is has built throughout 2017. AMD didn’t show us any Cinebench numbers, but my understanding is that the demo provided was completely air cooled. Intel’s…not so much. While impressive to see 28-cores at 5 GHz yesterday, more impressive is a 32-core machine with a system design I would be willing to implement.
No more details on pricing, performance, or platform were made available during the keynote, but we’ll be asking those questions as the week progresses.
Get ready for 32-cores!!
Subject: Processors | June 5, 2018 - 11:40 AM | Ryan Shrout
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.
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!!
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.
Subject: Processors | June 5, 2018 - 11:20 AM | Ryan Shrout
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|
|Base Clock||3.7 GHz||4.0 GHz|
|Turbo Clock||4.7 GHz||5.0 GHz|
|TDP||95 watts||95 watts (probably)|
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.
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.
Subject: Processors | May 30, 2018 - 11:18 AM | Sebastian Peak
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.
(Screen captures above sourced 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.
Subject: Processors | May 22, 2018 - 07:51 PM | Scott Michaud
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.
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.