AMD today held its "New Horizon" event for investors, offering guidance and "color" on what the company's near-future could look like. At the event, the company formally launched its Radeon Instinct MI60 GPU-based compute accelerator; and disclosed a few interesting tidbits on its next-generation "Zen 2" mircroarchitecture. The Instinct MI60 is the world's first GPU built on the 7 nanometer silicon fabrication process, and among the first commercially available products built on 7 nm. "Rome" is on track to becoming the first 7 nm processor, and is based on the Zen 2 architecture.

The Radeon Instinct MI60 is based on a 7 nm rendition of the "Vega" architecture. It is not an optical shrink of "Vega 10," and could have more number-crunching machinery, and an HBM2 memory interface that's twice as wide that can hold double the memory. It also features on-die logic that gives it hardware virtualization, which could be a boon for cloud-computing providers.

TSMC has become the de facto leader when it comes to manufacturing technology. The company is on the forefront of new process technologies, and provides solutions for some of the biggest players in the industry, like Apple, NVIDIA, Qualcomm, and AMD, just to name a few. This process leadership means that TSMC is being courted by numerous fabless silicon designers so as to produce their silicon chips with the latest process technologies - part of the reason why TSMC has seen increasing revenues and profits forecasts.

By the end of 2018, TSMC will have taped out 50 7 nm designs, and plans to double that number in 2019. And these design wins don't stand solely on the shoulders of TSMC's first 7 nm technology (which should account for 20% of the company's revenue by 2019); the company will also tape-out chips built upon their 7 nm + EUV process, which will begin production in 2019.

Samsung Electronics, a world leader in advanced semiconductor technology, today announced that it has completed all process technology development and has started wafer production of its revolutionary process node, 7LPP, the 7-nanometer (nm) LPP (Low Power Plus) with extreme ultraviolet (EUV) lithography technology. The introduction of 7LPP is a clear demonstration of Samsung Foundry's technology roadmap evolution and provides customers with a definite path to 3nm. The commercialization of its newest process node, 7LPP gives customers the ability to build a full range of exciting new products that will push the boundaries of applications such as 5G, Artificial Intelligence, Enterprise and Hyperscale Datacenter, IoT, Automotive, and Networking.

"With the introduction of its EUV process node, Samsung has led a quiet revolution in the semiconductor industry," said Charlie Bae, executive vice president of foundry sales and marketing team at Samsung Electronics. "This fundamental shift in how wafers are manufactured gives our customers the opportunity to significantly improve their products' time to market with superior throughput, reduced layers, and better yields. We're confident that 7LPP will be an optimal choice not only for mobile and HPC, but also for a wide range of cutting-edge applications."

AMD "Zen" CPU architecture brought the company back to competitive relevance in the processor market. It got an incremental update in the form of "Zen+" which saw the implementation of an improved 12 nm process, and improved multi-core boosting algorithm, along with improvements to the cache subsystem. AMD is banking on Zen 2 to not only add IPC (instructions per clock) improvements; but also a new round of core-count increases. Bits n Chips has information that Zen 2 is making significant IPC gains.

According to the Italian tech publication, we could expect Zen 2 IPC gains of 13 percent over Zen+, which in turn posted 2-5% IPC gains over the original Zen. Bits n Chips notes that these IPC gains were tested in scientific tasks, and not in gaming. There is no gaming performance data at the moment. AMD is expected to debut Zen 2 with its 2nd generation EPYC enterprise processors by the end of the year, built on the 7 nm silicon fabrication process. This roughly 16 percent IPC gain versus the original Zen, coupled with higher clocks, and possibly more cores, could complete the value proposition of 2nd gen EPYC. Zen 2-based client-segment products can be expected only in 2019.

Even as AMD plans to dedicate 7 nm CPU and GPU manufacturing entirely to TSMC, reports are emerging that Apple could make the Taiwanese silicon fabrication giant the sole supplier of its 7 nm A13 SoC, which powers the next generation iPhone and iPad devices. Manufacturing of the A13 could commence in 2019 to keep pace with Apple's roadmaps. TSMC is currently the most strongly placed semiconductor foundry for 7 nm EUV manufacturing, after GlobalFoundries crashed out, and Samsung is trailing behind with a contract to manufacture only a portion of Qualcomm's next-generation Snapdragon SoCs.

TSMC has quickly (over a span of years, but still) become the de-facto silicon manufacturing giant in the industry. They produce silicon-based solutions for almost all the significant tech companies (NVIDIA, AMD, Apple, Qualcomm, including the silicon manufacturing leader of yonder, Intel), and are on the forefront of new fabrication technologies. Just today we've covered how they are already well on their way to their second-gen 7 nm (N7+) fabrication technology with usage of EUV, and carving their path forward for 5 nm (N5).

Intel's in-house sub-10 nanometer silicon fabrication dreams seem more distant by the day. Raymond James analyst Chris Caso, in an interview with CNBC stated that Intel's 10 nm process development could set the company back by at least 5 years behind TSMC. In its most recent financial results call, Intel revised its 10 nm outlook to reflect that the first 10 nm processors could only come out by the end of 2019. "Intel's biggest strategic problem is their delay on 10nm production - we don't expect a 10nm server chip from Intel for two years," analyst Chris Caso said in a note to clients Tuesday. "10nm delays create a window for competitors, and the window may never again close."

By that time, Intel will have missed several competitive milestones behind TSMC, which is in final stages of quantitatively rolling out its 7 nm process. Caso predicts that by the time Intel goes sub-10 nm (7 nm or something in that nanoscopic ballpark), TSMC and Samsung could each be readying their 5 nm or 3 nm process roll-outs. A Rosenblatt Securities report that came out late-August was even more gloomy about the situation at Intel foundry. It predicted that foundry delays could set the company back "5, 6, or even 7" years behind rivals. Intel is already beginning offload some of its 14 nm manufacturing to TSMC. Meanwhile, AMD is reportedly planning to entirely rely on TSMC to make its future generations of "Zen" processors.

Arcturus is the fourth brightest star in the night sky, and could be the a new GPU architecture by AMD succeeding "Navi," according to a Phoronix report. The codename of Navi-successor has long eluded AMD's roadmap slides. The name "Arcturis" surfaced on Phoronix community forums, from a post by an AMD Linux liaison who is a member there. The codename is also supported by the fact that AMD is naming its GPU architectures after the brightest stars in the sky (albeit in a descending order of their brightness). Polaris is the brightest, followed by Vega, Navi, and Arcturus.

AMD last referenced the Navi-successor on a roadmap slide during its 2017 Financial Analyst Day presentation by Mark Papermaster. That slide mentioned "Vega" to be built on two silicon fabrication processes, 14 nm and "14 nm+." We know now that AMD intends to build a better-endowed "Vega" chip on 7 nm, which could be the world's first 7 nm GPU. "Navi" is slated to be built on 7 nm as the process becomes more prevalent in the industry. The same slide mentions Navi-successor as being built on "7 nm+," which going by convention, could refer to an even more advanced process than 7 nm. Unfortunately, even in 2017, when the industry was a touch more optimistic about 7 nm, AMD expected the Navi-successor to only come out by 2020. We're not holding our breath.

To sustain its meteoric rise at the stock markets, AMD needs to keep investors convinced it has a competitive edge over Intel, even if it means investing heavily on short-term roadmap changes. According to an Elchapuzas Informatico article, AMD could be working on a new 10-core/20-thread processor for the AM4 platform, to compete with the upcoming Core i9-9900K 8-core/16-thread processor from Intel. The said processor is being labeled "Ryzen 7 2800X" and plastered over CineBench nT screenshots, where due to the sheer weight of its 10 cores, it tops the nT test in comparison to Intel's mainstream-desktop processors, including the 2P Xeon X5650 12-core/24-thread.

The Forbes article that cites the Elchapuzas Informatico, however, is skeptical that AMD could make such a short-sighted product investment. It believes that development of a 10-core die on existing "Zen+" architecture could warrant a massive redesign of the CCX (Zen Compute Complex), and AMD would only get an opportunity to do so when working on "Zen 2," which AMD still expects to debut by late-2018 on its EPYC product line. We, however, don't discount the possibility of a 10-core "Zen+" silicon just yet. GlobalFoundries, AMD's principal foundry partner for CPUs, has given up on 7 nm, making the company fall back to TSMC to meet its 7 nm roadmap commitments. TSMC already has a long list of clientele for 7 nm, including high-volume contracts from Apple, Qualcomm, and NVIDIA. This could force AMD to bolster its existing lineup as a contingency for delays in 7 nm volume production.

Intel was once the shining star in the semiconductor manufacturing industry, with a perfectly integrated, vertical product design and manufacturing scheme. Intel was one of the few companies in the world to be able to both develop its architectures and gear their manufacturing facilities to their design characteristics, ensuring a perfect marriage of design and manufacturing. However, not all is rosy on that field, as we've seen; AMD itself also was a fully integrated company, but decided to spin-off its manufacturing arm so as to survive - thus creating GLOBALFOUNDRIES.But Intel was seen as many as the leader in semiconductor manufacturing, always at the cutting edge of - well - Moore's Law, named after Intel's founding father Gordon Moore. Now, Mehdi Hosseini, an analyst with Susquehanna, has gone on to say that the blue giant has effectively lost its semiconductor leadership. And it has, in a way, even if its 10 nm (which is in development hell, so to speak) is technically more advanced than some 7 nm implementations waiting to be delivered to market by its competitors. However, there's one area where Intel will stop being able to claim leadership: manufacturing techniques involving EUV (Extreme UltraViolet).

GLOBALFOUNDRIES today announced an important step in its transformation, continuing the trajectory launched with the appointment of Tom Caulfield as CEO earlier this year. In line with the strategic direction Caulfield has articulated, GF is reshaping its technology portfolio to intensify its focus on delivering truly differentiated offerings for clients in high-growth markets.

GF is realigning its leading-edge FinFET roadmap to serve the next wave of clients that will adopt the technology in the coming years. The company will shift development resources to make its 14/12nm FinFET platform more relevant to these clients, delivering a range of innovative IP and features including RF, embedded memory, low power and more. To support this transition, GF is putting its 7nm FinFET program on hold indefinitely and restructuring its research and development teams to support its enhanced portfolio initiatives. This will require a workforce reduction, however a significant number of top technologists will be redeployed on 14/12nm FinFET derivatives and other differentiated offerings.

It has been a rollercoaster Monday for AMD as it bled yet another bright executive. Jim Anderson, who led Computing and Graphics Group after the departure of Raja Koduri, and who is rumored to have conceived the idea of Threadripper and the client-segment monetization of the "Zen" architecture, left AMD to become CEO of Lattice Semiconductor, a company that designs FPGAs. Anderson will be paid an inducement award of company shares valued up to $2.9 million.

On the same day, AMD stock crossed $25 to close at $25.26 up 5.34 percent, a historic high since way back in 2006 as Intel was beginning to regain its footing with its Core processor family. This raises the company's market cap to $22.9 billion. AMD is better funded than ever (in over 12 years), to start a new GPU project, for example. CTO Mark Papermaster, in a company blog post assured customers that AMD is going all-in with 7 nanometer, and it could bank more heavily on TSMC to achieve its roadmap goals of first-to-market 7 nm CPU and GPU by end of the year.

Intel is one of the few semiconductor companies that manufactures a majority of its products on its own silicon fabrication foundries. The breadwinner for the company continues to be CPUs, and a majority of its revenues continue to come from its client-computing group (CCG). CPUs, like GPUs, are required to be built on the latest silicon fabrication process to keep up (or catch up) with Moore's Law. Intel is plagued with severe technological roadblocks toward advancing its foundry process from 14 nanometer (nm) to its next step, 10 nm. In its latest Q2-2018 earnings call, the company confirmed that the 10 nm node won't put out before Q4-2019, even as rival AMD's CEO announced that its first 7 nm processors will be up for purchase by the end of 2018 (a year ahead with a more advanced process, on paper). Analysts are beginning to paint a very grim future for Intel's foundry business.

The prospects for Intel going fabless, at least for its cutting-edge products, is higher than ever. Analysts, speaking with Taiwan-based industry observer DigiTimes, mentioned that there is speculation of Intel scaling down its foundry business. Something like this, if true, could hint at the company looking for foundry partners with newer silicon-fabrication nodes at a more advanced stage of development (eg: GlobalFoundries 7 nm) to manufacture its processors, while relegating its own foundries to manufacture less complex products such as chipset, NAND flash, 3D XPoint memory, 5G PHYs, etc. Fancy a Core processor made by GloFo in the great state of New York?

Wrap your head around this: at some point in 2019, AMD will be selling 7 nm processors while Intel sells 14 nm processors. That how grim Intel's 10 nanometer silicon fabrication process development is looking. In the Q&A session of its Q2-2018 Earnings Call, Intel stated that the first products based on its 10 nm process will arrive only by Holiday 2019, making 14 nm micro-architectures hold the fort for not just the rest of 2018, but also most of 2019. In the client-segment, Intel is on the verge of launching its 9th generation Core "Whiskey Lake" processor family, its 5th micro-architecture on the 14 nm node after "Broadwell," "Skylake," "Kaby Lake," and "Coffee Lake."

It's likely that "Whiskey Lake" will take Intel into 2019 after the company establishes performance leadership over 12 nm AMD "Pinnacle Ridge" with a new round of core-count increases. Intel is also squeezing out competitiveness in its HEDT segment by launching new 20-core and 22-core LGA2066 processors; and a new platform with up to 28 cores and broader memory interface. AMD, meanwhile, hopes to have the first 7 nm EPYC processors out by late-2018. Client-segment products based on its architecture, however, will follow the roll-out of these enterprise parts. We could see a point in 2019 when AMD launches its 7 nm 3rd generation Ryzen processors in the absence of competing 10 nm Core processors from Intel. Posted below is an Intel slide from 2013, when the company was expecting 10 nm rollout by 2015. That's how much its plans have derailed.

AMD in its Q2-2018 investors conference call dropped more hints at when it plans to launch its 3rd generation Ryzen processors, based on its "Zen2" architecture. CEO Lisa Su stated in the Q&A session that rollout of 7 nm Ryzen processors will only follow that of 7 nm EPYC (unlike 1st generation Ryzen preceding 1st generation EPYC). What this effectively means is that the fabled 16-core die with 8 cores per CCX won't make it to the desktop platform any time soon (at least not in the next three quarters, certainly not within 2018).

AMD CEO touched upon the development of the company's 7 nm "Rome" silicon, which will be at the heart of the company's 2nd generation EPYC processor family. 2nd generation EPYC, as you'd recall from our older article, is based on 7 nm "Zen2" architecture, and not 12 nm "Zen+." 3rd generation Ryzen is expected to be based on "Zen2." As of now, the company is said to have completed tape-out of "Rome," and is sending samples out to its industry partners for further testing and validation. The first EPYC products based on this will begin rolling out in 2019. The 7 nm process is also being used for a new "Vega" based GPU, which has taped out, and will see its first enterprise-segment product launch within 2018.

A post via Chiphell makes some substantial claims on AMD's upcoming Zen 2 microarchitecture, built on the 7 nm process. AMD has definitely won the core-count war once again (albeit with a much more decisive blow to Intel's dominance than with Bulldozer), but the IPC battle has been an uphill one against Intel's slow, but sure, improvement in that area over the years. AMD did say, at the time they introduced the Zen architecture, that they had a solid understanding on Zen's choke points and its improveable bits and pieces - and took it to heart to deliver just that.

At their technology symposium in Taipei, TSMC CEO CC Wei has made remarks, dismissing speculation that their 7 nanometer yield rate was not as good as expected. Rather the company is ramping up production capacity for 7 nm quickly, up 9% from 10.5 million wafers in 2017, to 12 million wafers in 2018. They plan to tape out more than 50 chip designs in 2018, with the majority of the tape outs for AI, GPU and crypto applications, followed by 5G and application processors.

Most of their orders for the 7 nanometer node come from big players like AMD, Bitmain, NVIDIA and Qualcomm. Apple's A12 processor for upcoming iPhones is also a major driver for TSMC's 7 nanometer growth. These orders will be fulfilled in early 2019, so it'll be a bit longer before we have 7 nm processors for the masses.

Next-gen 5 nanometer production will kick off next year, followed by mass production in late 2019 or early 2020. The company will invest as much as USD 25 billion in their new production facilities for this process node.

AMD in its Computex 2018 address earlier today, mention that its second-generation EPYC enterprise processors will be based on its 7 nanometer "Zen 2" architecture, and not 12 nm "Zen+." The company has the 7 nm silicon ready in its labs, and will begin sampling within the second half of 2018. The first products could launch in 2019, after validations. Besides improved energy-efficiency, the 12 nm "Zen+" architecture features a minor 3-5 percent IPC uplift thanks to improved multi-core clock-speed boosting, and faster caches. "Zen 2," on the other hand, presents AMD with the opportunity to make major design changes to its silicon to achieve higher IPC uplifts. The 7 nm process introduces significant transistor density uplifts over the current process. AMD is in the process of building 4-die multi-chip modules using the 12 nm "Pinnacle Ridge" silicon for its 2nd generation Ryzen Threadripper HEDT client processor family.

AMD demonstrated the world's first GPU built on the 7 nanometer silicon fabrication process, a Radeon Vega Instinct HPC/AI accelerator, with a 7 nm GPU based on the "Vega" architecture, at its heart. This chip is an MCM of a 7 nm GPU die, and 32 GB HBM2 memory stacks over four stacks (4096-bit memory bus width). It's also the first product to feature a removable InfinityFabric interface (competition to NVIDIA's NVLink interface). There will also be variants based on the common PCI-Express 3.0 x16. The card supports hardware virtualization and new deep-learning ops.

ARM has announced their next, high-performance computing solution with their A76 design, which brings another large performance increase to the fledgling architecture. having been touted for some time as a true contender to the aging x86 architecture, ARM has had a way of extracting impressive performance increases with each iteration of its computing designs, in the order of 20% do 40% performance increases in an almost annual basis. Compare that to the poster-child of x86 computing, Intel, and its passivity-fueled 5 to 10% yearly performance increases, and the projections aren't that hard to grasp: at some point in time, ARM cores will surpass x86 in performance - at least on the mobility space.

The new ARM A76 design, to be manufactured on the 7 nm process, brings about a 35% increase in performance compared to last years' A75. This comes with an added 40% power efficiency (partly from the 10 nm to 7 nm transition, the rest from architecture efficiency and performance improvements), despite the increase to maximum 3.0 GHz clocks. With the added performance, ARM is saying the new A76 will deliver 4x the Machine Learning performance of its previous A75 design.

Cadence and Micron have joined forces to build the world's first working DDR5-4400 memory module. Cadence provided their DDR5 memory controller and PHY for the prototype while Micron produced the 8 Gb chips, which were manufactured under TSMC's 7 nm process. They were able to achieve 4400 megatransfers per second, which is roughly 37.5% faster than the fastest DDR4 memory that is currently on the market. Nevertheless, Marc Greenberg from Cadence emphasized that DDR5 aims to provide increased capacity solutions, more than actual performance.

The DDR5 standard should facilitate the production of 16 Gb dies and make vertical stacking easier. Restricted by laws of physics, dies eventually get slower as they increased in size. Once you start putting 16Gb die in 1X memory technology, the distances between them starts to get longer. As a result, core timing parameters become worse. Cadence's prototype had a CAS latency of 42 (No, not a typo). Although, the test module does run at 1.1 volts, which makes it quite impressive when compared to DDR4.

It looks like AMD's processor product launch cycle is on steroids, and keeping up (or even ahead) of Intel. After launching the first 12 nm processor architecture with "Zen+," the company is giving final touches to what it hopes to be the world's first 7 nanometer processor architecture, with "Zen 2." The company will reportedly begin sampling the chip within 2018, to enable volume production and market launch in 2019. Speaking at an investors conference call following the company's Q1-2018 Results release, AMD CEO Dr. Lisa Su confirmed the 7 nm roll-out strategy of her company.

"We have a 7nm GPU based on Vega that we'll sample later this year. We have a 7nm server CPU that we'll sample later this year. And then, obviously, we have a number of products that are planned for 2019 as well. So it's a very, very busy product season for us. But we're pleased with the sort of the execution on the product roadmap," Dr. Su said. Unlike Zen+, Zen 2 is a major update to the company's processor micro-architecture, and presents the company with opportunities to improve several silicon-level specifications, such as the number of cores per CCX, the IPC of each core, the core-count of the die, the cache hierarchy, and the overall energy-efficiency.

With the latest Radeon Vega Instinct reveal, it's becoming increasingly clear that "Vega 20" is an optical shrink of the "Vega 10" GPU die to the new 7 nm silicon fabrication process, which could significantly lower power-draw, enabling AMD to increase clock-speeds. A prototype graphics card based on "Vega 20," armed with a whopping 32 GB of HBM2 memory, was put through 3DMark 11, on a machine powered by a Ryzen 7 1700 processor, and compared with a Radeon Vega Frontier Edition.

The prototype had lower GPU clock-speeds than the Vega Frontier Edition, at 1.00 GHz, vs. up to 1.60 GHz of the Vega Frontier Edition. Its memory, however, was clocked higher, at 1250 MHz (640 GB/s) vs. 945 MHz (483 GB/s). Despite significantly lower GPU clocks, the supposed "Vega 20" prototype appears to score higher performance clock-for-clock, but loses out on overall performance, in all tests. This could mean "Vega 20" is not just an optical-shrink of "Vega 10," but also benefits from newer architecture features, besides faster memory.

AMD has announced via its Twitter feed that the Vega die shrink from current 14 nm down to 7 nm has actually coalesced into a hardware product that can be tested and vetted at their labs. Via a teaser image, the company said that "7nm @RadeonInstinct product for machine learning is running in our labs."

Of course, working silicon is only half the battle - considerations such as yields, leakage, and others are all demons that must be worked out for actual production silicon, which may thus be some months off. Only AMD and TSMC themselves themselves know how the actual production run went - and the performance and power efficiency that can be expected from this design (remember that AMD's CEO Lisa SU herself said they'd partner with both TSMC and Globalfoundries for the 7 nm push, though it seems TSMC may be pulling ahead in that field). Considering AMD's timeline for the die-shrunk Vega to 7 nm - with predicted product launch for 2H 2018 - the fact that there is working silicon being sampled right now is definitely good news.

Semiconductor manufacturers have been historically bullish when it comes to the introduction of new manufacturing technologies. Intel, AMD (and then Globalfoundries), TSMC, all are companies who thrive in investors' confidence: they want to paint the prettiest picture they can in terms of advancements and research leadership, because that's what attracts investment, and increased share value, and thus, increased funds to actually reach those optimistic goals.

However, we've seen in recent years how mighty Intel itself has fallen prey to unforeseen complications when it comes to advancements of its manufacturing processes, which saw us go from a "tick-tock" cadence of new architecture - new manufacturing process, to the introduction of 14 nm ++ processes. And as Intel, Globalfoundries and TSMC race towards sub 7-nm manufacturing processes with 250 mm wafers and EUV usage, things aren't getting as rosy as the ultraviolet moniker would make us believe.