SiSoftware put out the mother lode of information on Intel's upcoming Arc "Alchemist" gaming graphics card series, along with OpenCL compute performance of the entry-level Arc A380. The Arc series model numbering is "A" (Alchemist) followed by a number series. The A300 series makes up the entry-mainstream; the A500 series makes up the mid-performance segment; and the A700 series leads the pack with high-end SKUs. The "Alchemist" GPUs are built on the 7 nm silicon fabrication node at TSMC, the N7.

The A300 series is based on the smaller "Alchemist" series dies, with 128 EUs (execution units), which work out to 1,024 programmable shaders. The A500 series and A700 series appear to be carved out from the larger silicon. The A500 series has roughly 384 EU or 3,072 shaders. The top-dog A700 series has all 512 EU or 4,096 shaders enabled. Intel is tapping into industry-standard GDDR6 for dedicated graphics memory. The A300-series SKUs typically have 6 GB of 14 Gbps-rated memory across a 96-bit wide memory bus, for 192 GB/s of bandwidth. The A500 series parts have 12 GB of 16 Gbps-rated memory across a 192-bit bus, for 384 GB/s of bandwidth. The top A700 series maxes out the 256-bit memory bus with 16 GB of memory at 16 Gbps data-rate, for 512 GB/s bandwidth.

During the International Solid-State Circuits Conference (ISSCC) 2022, Intel gave us a more significant look at its upcoming Ponte Vecchio HPC accelerator and how it operates. So far, Intel convinced us that the company created Ponte Vecchio out of 47 tiles glued together in one package. However, the ISSCC presentation shows that the accelerator is structured rather interestingly. There are 63 tiles in total, where 16 are reserved for compute, eight are used for RAMBO cache, two are Foveros base tiles, two represent Xe-Link tiles, eight are HBM2E tiles, and EMIB connection takes up 11 tiles. This totals for about 47 tiles. However, an additional 16 thermal tiles used in Ponte Vecchio regulate the massive TDP output of this accelerator.

What is interesting is that Intel gave away details of the RAMBO cache. This novel SRAM technology uses four banks of 3.75 MB groups total of 15 MB per tile. They are connected to the fabric at 1.3 TB/s connection per chip. In contrast, compute tiles are connected at 2.6 TB/s speeds to the chip fabric. With eight RAMBO cache tiles, we get an additional 120 MB SRAM present. The base tile is a 646 mm² die manufactured in Intel 7 semiconductor process and contains 17 layers. It includes a memory controller, the Fully Integrated Voltage Regulators (FIVR), power management, 16-lane PCIe 5.0 connection, and CXL interface. The entire area of Ponte Vecchio is rather impressive, as 47 active tiles take up 2,330 mm², whereas when we include thermal dies, the total area jumps to 3,100 mm². And, of course, the entire package is much larger at 4,844 mm², connected to the system with 4,468 pins.

China is reacting to new outbreaks of the Omicron variant of the Coronavirus with partial lockdowns. This could further delay the availability of laptops with 12th Gen Intel Core processors and NVIDIA's Ti graphics cards, which debuted at the beginning of the year. The first factories have already been closed in Suzhou in the east of the country. Supply chain and logistics bottlenecks, a shortage of certain chip types and price increases are already on the horizon.

Back in December, we reported that Tower Semiconductor was one of several semiconductor manufacturers that was considering building a fab in India, largely due to government subsidies. Since then, Intel has stepped in and bought Tower Semiconductor and has taken over the negotiations with the Indian government. What has also come to light is that Tower Semiconductor has been in discussions with the Indian government for over a decade, but apparently the two parties have been unable to come up with a suitable agreement. Tower Semiconductor was apparently ready to cancel any plans on building in India as late as September 2021, but the more recent government initiative renewed their interest.

As to exactly what kind of fab Intel would build, is unclear at this point in time, but it might still be a MEMS fab or it could simply be a testing and packaging plant. Regardless of what kind of facility it'll be, it's interesting that Intel decided to keep the ongoing plans from Tower Semiconductor going. Tower Semiconductor mostly manufactured for fabless companies and were producing some two million wafers a year. It's likely that Intel will carry on producing for the same companies at the same terms for now, although as Tower Semiconductor gets integrated closer with the Intel foundry, things could change.

Intel plans to ship no less than 4 million discrete GPUs in 2022, the company stated in its Investor Meeting 2022 presentation. The Accelerated Computing Systems and Graphics Group (AXG), headed by Raja Koduri, announced this bold target. The company announced a Q1-2022 debut of its ambitious new Arc "Alchemist" discrete GPU for notebooks (before April). This is to be followed by a desktop debut in Q2-2022 (before July), before a professional-visualization (workstation-class) debut in Q3 (before October). All put together, the company plans to ship over 4 million discrete GPUs over the year.

Intel announced over 50 design wins for OEMs and "AICs." This is big, as it denotes that Arc "Alchemist" graphics cards won't just be sold in the OEM/SI channel, but also the DIY retail channel. Among the familiar brands in the DIY space from the Intel slide are ASUS, MSI, and GIGABYTE. The company is working with over 100 software-ecosystem partners or ISVs, to optimize their current and upcoming applications and games, for the Xe HPG graphics architecture. This includes support for the XeSS performance enhancement (analogous to AMD FSR and NVIDIA DLSS), and DeepLink, a graphics processing resource virtualization tech. Intel plans to launch a new generation of Arc almost every year for the next 3 years, starting with "Alchemist" in 2022, "Battlemage" somewhere around 2023-2024, and "Celestial" after 2024.

Intel is allegedly advancing the launch of its 13th Gen Core "Raptor Lake-S" desktop processors to some time in Q3-2022, according to a report by Moore's Law is Dead. It was earlier believed to be a Q4 launch, much like "Alder Lake" was, in 2021. The report predicts the debut of "Raptor Lake" in the desktop segment in Q3-2022 (between July and September), with certain mobile SKUs expected toward the end of the year, in Q4. The Core "Raptor Lake-S" processor is built in the existing Socket LGA1700 package, and is being designed for compatibility with existing Intel 600-series chipset motherboards with a firmware update.

The "Raptor Lake-S" silicon is built on the existing Intel 7 (10 nm Enhanced SuperFin) node, and physically features eight "Raptor Cove" P-cores, along with sixteen "Gracemont" E-cores that are spread across four clusters. The chip has additional cache memory, too. Moore's Law is Dead predicts that the "Raptor Cove" P-core could introduce an IPC uplift in the region of 8 to 15 percent over the "Golden Cove" core, while the chip's overall multi-threaded performance could be anywhere between 30 to 40 percent over "Alder Lake-S," on account of not just increased IPC of the P-cores, but also eight additional E-cores.

Intel has recently unveiled its plans for their 3rd generation Celestial Arc graphics cards to compete with NVIDIA and AMD in the "Ultra Enthusiast" GPU market. The Arc Celestial GPU series is now scheduled to launch in 2024 with the architecture currently under active development. These cards will target future flagship cards from NVIDIA however in 2023/2024 we should see the launch of 2nd generation Arc Battlemage products that may narrow the gap. The timeline Intel shared indicates a launch date of 2024+ for Celestial GPUs so the launch date may slip into 2025. This was previously the year which Intel was rumored to launch 4th generation Arc Druid graphics cards so it remains to be seen if this official timeline will hold.

Intel Xeon Scalable "Sapphire Rapids" is an upcoming enterprise processor with a CPU core count of up to 60. This core-count is achieved using four dies inter-connected using EMIB. Locuza, who leads social media with logic die annotation, posted one for "Sapphire Rapids," based on a high-resolution die-shot revealed by Intel in its ISSCC 2022 presentation.

Each of the four dies in "Sapphire Rapids" is a fully-fledged multi-core processor in its own right, complete with CPU cores, integrated northbridge, memory and PCIe interfaces, and other platform I/O. What brings four of these together is the use of five EMIB bridges per die. This allows CPU cores of a die to transparantly access the I/O and memory controlled any of the other dies transparently. Logically, "Sapphire Rapids" isn't unlike AMD "Naples," which uses IFOP (Infinity Fabric over package) to inter-connect four 8-core "Zeppelin" dies, but the effort here appears to be to minimize the latency arising from an on-package interconnect, toward a high-bandwidth, low-latency one that uses silicon bridges with high-density microscopic wiring between them (akin to an interposer).

Intel Corporation today announced that Christoph Schell has been appointed executive vice president and chief commercial officer to lead the Sales, Marketing and Communications Group (SMG), starting March 14. Schell will succeed Michelle Johnston Holthaus, who will take on a new role as general manager of Intel's Client Computing Group (CCG).

"Christoph has an exceptional track record of driving innovative and disruptive go-to-market strategies around the globe. He brings expertise in understanding business segments, verticals and the solutions and services customers want," said Pat Gelsinger, Intel CEO. "We are harnessing our core strengths as an advantage to grow in our traditional markets and accelerate our entry into new ones. I'm confident Christoph is the right leader to take on this critical role and guide the talented SMG organization to achieve our growing ambitions."

Schell joins Intel from HP Inc., where he was most recently chief commercial officer. With his go-to-market team, he led customer and partner success, category management and customer support globally. During his 25 years with the company, Schell held various senior management roles across the globe, including president of 3D Printing & Digital Manufacturing. Prior to rejoining HP in 2014, Schell served as executive vice president of Growth Markets for Philips, where he led the lighting business across Asia Pacific, Japan, Africa, Russia, India, Central Asia and the Middle East. He started his career in his family's distribution and industrial solutions company and worked in brand management at Procter & Gamble.

The NUC Extreme might not share much in terms of design with either the original NUC or its earlier Extreme siblings these days, as it's grown into a rather hefty SFF system. Now the 12th gen NUC Extreme has leaked and it comes with a few unexpected surprises, in both a good and a bad sense. Initially it looks like there will be two main barebones SKU's, the NUC12EDBi9 and the NUC12EDBi7, with a 65 W Core i9-12900 and a Core i7-12700 CPU respectively. In other words, it appears we're not looking at any dedicated CPU SKU's this time around.

The first thing that sticks out in the spec is the fact that Intel has gone for a pair of DDR4 SO-DIMM slots, rather than DDR5. In all fairness, this could be due to a lack of DDR5 SO-DIMMs in the market, but feels odd in a product with Extreme in the product name. Memory speeds of up to 3200 MHz are supported and up to 64 GB can be fitted. On the storage side, there's support for no less than three PCIe 4.0 M.2 NVMe drives using the 2280 form factor. Two of the slots can also accept 2242 drives and SATA drives. A full PCIe 5.0 x16 slot is also present for an optional graphics card, but more on that a little bit later.

Intel's upcoming "Meteor Lake" and "Arrow Lake" client mobile processors introduce an interesting twist to the chiplet concept. Earlier represented in vague-looking IP blocks, new artistic impressions of the chip put out by Intel shed light on a 3-die approach not unlike the Ryzen "Vermeer" MCM that has up to two CPU core dies (CCDs) talking to a cIOD (client IO die), which handles all the SoC connectivity; Intel's design has one major difference, and that's integrated graphics. Apparently, Intel's MCM uses a GPU die sitting next to the CPU core die, and the I/O (SoC) die. Intel likes to call its chiplets "tiles," and so we'll go with that.

The Graphics tile, CPU tile, and the SoC or I/O tile, are built on three different silicon fabrication process nodes based on the degree of need for the newer process node. The nodes used are Intel 4 (optically 7 nm EUV, but with characteristics of a 5 nm-class node); Intel 20A (characteristics of 2 nm), and external TSMC N3 (3 nm) node. At this point we don't know which tile gets what. From the looks of it, the CPU tile has a hybrid CPU core architecture made up of "Redwood Cove" P-cores, and "Crestmont" E-core clusters.

When Intel announced the company's first hybrid design, codenamed Alder Lake, we expected to see more of such design philosophies in future products. During Intel's 2022 investor meeting day, the company provided insights into future developments, and a successor to Alder Lake is no different. Codenamed "Raptor Lake," it features a novel Raptor Cove P-core design that is supposed to bring significant IPC uplift from the previous generation of processors. Using Intel 7 processor node, Raptor Lake brings a similar ecosystem of features to Alder Lake, however, with improved performance across the board.

Perhaps one of the most exciting things to note about Raptor Lake is the advancement in core count, specifically the increase in E-cores. Instead of eight P-cores and eight E-cores like Alder Lake, the Raptor Lake design will retain eight P-cores and double the E-core count to 16. It was a weird decision on Intel's end; however, it surely isn't anything terrible. The total number of cores now jumps to 24, and the total number of threads reaches 32. Additionally, Raptor Lake will bring some additional overclocking improvement features and retain socket compatibility with Alder Lake motherboards. That means that, at worst, you would need to perform a BIOS update to get your previous system ready for new hardware. We assume that Intel has been working with software vendors and its engineering team to optimize core utilization for this next-generation processor, even though they have more E-cores present. Below, we can see Intel's demonstration of Raptor Lake running Blender and Adobe Premiere and the CPU core utilization.

At Intel's 2022 investor meeting, the company has presented a technology roadmap update to give its clients an insight into what is to come. Today, team blue announced one of the first discrete data-centric graphics cards in the lineup, codenamed Arctic Sound-M GPU. Based on the DG2 Xe-HPG variation of Intel Xe GPUs, Arctic Sound-M is the company's first design to enter the data center space. The DG2 GPU features 512 Execution Units (EUs), which get passive cooling from the single-slot design of Arctic Sound's heatsink, envisioned for data center enclosures with external airflow.

One of the most significant selling points that Intel advertises is support for hardware-based AV1 encoding standard. This feature allows the card to achieve a 30% greater bandwidth, and it is the main differentiator between consumer-oriented Arc Alchemist GPUs and itself. The card is powered by PCIe power and an 8-pin EPS power connector. Arctic Sound-M is already sampling to select customers and it will become available in the middle of 2022.Below is Intel's teaser video.

The "tick tock" product development cycle, which enabled Intel to develop a new silicon fabrication node every alternating year, a new microarchitecture every alternating year, and interleaving the two in such a way that each new microarchitecture is built on two successive nodes, and each node is used for building two succeeding microarchitectures, is back. The company has, for the first time in over 6 years, mentioned the tick-tock development cadence in its Investor Day presentation.

When laying out its upcoming foundry nodes following the current Intel 7 (10 nm enhanced SuperFin), the company mentioned its successors, starting with Intel 4 (7 nm EUV-based), which offers electrical properties and transistor densities in the league of 5 nm-class nodes by TSMC. Intel 4 debuts with "Meteor Lake" mobile architecture slated for the first half of 2023, with mass-production of wafers commencing in 2H-2022. The Intel 3 node is targeted for a year later in late-2023, with the server processor that succeeds "Sapphire Rapids" being developed for this node. Following this, Intel, along with several other foundry companies, enter the tricky sub-2 nm class.

Introducing the EVGA Z690 DARK K|NGP|N - The Motherboard Designed by and Used by Professional Overclockers. EVGA DARK motherboards blaze the trail for other boards to follow, and the Z690 DARK K|NGP|N is no exception. The ability to destroy world records is insignificant next to the power of a 21-phase VRM and a 10-layer PCB - capable of driving the most powerful 12th Gen Intel Core processors. With support for 64 GB of DDR5 memory at up to 6600 MHz+(OC), PCIe Gen5, and PCIe Gen4 M.2 NVMe SSDs, a new DARK age of overclocking will rise as quickly as new hardware becomes available. The Z690 DARK K|NGP|N is today's choice for the future of overclocking and gaming.

Intel on Thursday (17/02/2022), hosted its 2022 Investor Meeting and outlined key elements of the company's strategy and path to long-term growth during an era of unprecedented demand for semiconductors. The event included a series of announcements at both a corporate and individual business unit level, including more details of the company's Smart Capital strategy, product roadmaps across its new reporting segments and key execution milestones.

"The continued proliferation of technology is driving sustained, long-term demand for semiconductors, creating a $1 trillion market opportunity by 2030," said Pat Gelsinger, Intel chief executive officer. "With that opportunity in mind, today we outlined our strategy and roadmap for accelerating to 10%-12% year-over-year revenue growth by 2026 by doubling down on innovation, driving even deeper collaboration with our customers and partners, and leveraging our core strengths to successfully grow traditional markets and disrupt new ones. Our goals are ambitious, but I'm confident we have the right strategy and right team to achieve them and to deliver long-term value for our shareholders."

At Intel's 2022 Investor Meeting, Chief Executive Officer Pat Gelsinger and Intel's business leaders outlined key elements of the company's strategy and path for long-term growth. Intel's long-term plans will capitalize on transformative growth during an era of unprecedented demand for semiconductors. Among the presentations, Intel announced product roadmaps across its major business units and key execution milestones, including: Accelerated Computing Systems and Graphics, Intel Foundry Services, Software and Advanced Technology, Network and Edge, Technology Development, More: For more from Intel's Investor Meeting 2022, including the presentations and news, please visit the Intel Newsroom and Intel.com's Investor Meeting site.

Things are apparently anything but smooth for TSMC when it comes to its US expansion in Arizona, as reports claim that the construction of its new fab in Arizona is going to be late. This is largely due to labour shortages caused by the pandemic, which in turn is set to delay the entire project. As such, it's being suggested that the installation of manufacturing equipment will be delayed from late Q3 this year until Q1 next year. The knock on effect of this is that production is unlikely to start in Q1 2024 and will most likely be delayed to sometime in the second half of 2024. As a comparison, TSMC normally spends two years to build and configure their fabs in Asia, whereas their first expansion outside of Asia is set to take at least two and a half years.

Another issue is said to be related to finding the right staff, since not only TSMC, but also Intel is looking for competent staff in Arizona. Intel might be the winner here, as TSMC is said to already have complaints from some of its employees, especially from western countries. The main complaint is about excessively long meetings that can add several hours to their workdays. Other complaints revolve around long working hours, as the company employs 12 hour shifts for its engineers and they are often on call over weekends. The company has apparently become increasingly demanding when it comes to its workforce, although TSMC has apparently improved in some ways, based on changes to the Taiwanese labour laws.

Following its acquisition of FPGA and network hardware giant Xilinx, AMD is a larger company in terms of market capitalization. At closing bell on Tuesday (15/02), this figure stands at $199.58 billion, which for the very first time in AMD's history, beats rival Intel, which closed at $197.20 billion. Chiakokhua, aka Retired Engineer, provided the calculation that arrives at the $199.58 billion market cap. Before close, AMD had a share-count of 1.216 billion. 427 million shares were issued to Xilinx shareholders, resulting in a share-count (after close) of 1.643 billion, which at a share price of $121.47 works out to $199.58 billion. At $121.47, AMD is still trading around 26% lower than its all-time high price of $165.46.

Update: The Intel acquisition of Tower Semiconductor has gone through for a value of $5.4 billion, at a price of $53 per share. Through the deal, Intel adds Tower Semiconductor's infrastructure, IP, technicians, logistics and clients to its portfolio. Intel CEO Pat Gelsinger said that "Tower's specialty technology portfolio, geographic reach, deep customer relationships and services-first operations will help scale Intel's foundry services and advance our goal of becoming a major provider of foundry capacity globally." He then added that "This deal will enable Intel to offer a compelling breadth of leading-edge nodes and differentiated specialty technologies on mature nodes - unlocking new opportunities for existing and future customers in an era of unprecedented demand for semiconductors." The original story follows.

Intel is reportedly looking to increase its manufacturing capability - and its cadre of wafer-purchasing clients - by acquiring Israeli semiconductor manufacturer Tower Semiconductor. If true, the deal will bring seven additional foundries to Intel's existing infrastructure, capable of 2 million wafer starts per year. The foundries are located across three continents: Tower Semiconductor owns and operates a 150 mm and a 200 mm fab in Migdal Haemek, Israel; two 200 mm fabs in the United States (Newport Beach, California and San Antonio, Texas); two 200 mm fabs in Japan; and one additional 300 mm fab in Japan. The deal could be finalized as soon as this week.

Intel's Alder Lake CPUs started the wave of hybrid designs spanning the consumer sector with high-performance P-cores and high-efficiency E-cores combined to make a mixed design work. And it seems like the replacement for it is already in progress, as the next-generation Intel "Raptor Lake" processors are continuing enablement in the Linux kernel. This next-generation Raptor Lake design will arrive towards the end of this year, and the software ecosystem is already preparing for its arrival. According to the report from Phoronix, audio support for Intel Raptor Lake processors has been added to the Linux kernel 5.18.

As the report points out, the enablement work is no different since days of Skylake, where adding new IDs to the driver gets the job done. However, what is interesting is that Raptor Lake is slowly getting the entire software ecosystem support functional. This shows with Linux kernel 5.17, where Raptor Lake-S Gen 12-based graphics card received initial software support. As the software matures, full support for Raptor Lake will come, especially as we enter the later months of 2022, when the next generation is supposed to arrive.

Intel recently announced the Core i9-12900KS, its new flagship desktop processor that comes as a deterrent to the AMD Ryzen 7 5800X3D, which the red-team claimed to be matching the current i9-12900K in gaming performance. The new i9-12900KS is built from the highest bins of the "Alder Lake-S" C0 silicon, which are needed to support the chip's 5.50 GHz maximum Turbo Boost frequency on the P-cores, and 3.90 GHz max Turbo on the E-cores. While the E-core max Turbo isn't any different from the i9-12900K, the P-core sees it go up from 5.20 GHz on the older model.

The Core i9-12900KS processor is now beginning to show up on retailers, with Shop BLT listing it at USD $791 for the boxed retail processor, and $780 for the chip-only OEM part. Even at these prices, the premium over the i9-12900K is barely $150. The listing also sheds light on increased power limits. The processor base power value for the i9-12900KS is set at 150 W, compared to 125 W on the i9-12900K. This isn't the same as PL1, as Intel changed the definition of its power definitions with the 12th Gen. The maximum turbo power value (PL2) remains unknown. For the i9-12900K, this is set at 241 W. This isn't the first "KS" SKU by Intel, with the last one, the i9-9900KS, shipping as the first processor with a 5.00 GHz all-core Turbo frequency. It remains to be seen if all Socket LGA1700 motherboards support the i9-12900KS with a firmware update, because not all 300-series chipset motherboards supported the i9-9900KS due to its steep electrical requirements.

Intel's Alder Lake family is apparently still growing and the latest leaks suggest that a new addition is on its way in the shape of the Alder Lake-N. This should be the most basic SKU of Alder Lake CPUs, as it'll only have "small" Gracemont cores and no Golden Cove cores at all, unlike all of its other siblings. The oddities don't stop here though, as these new CPUs won't even have any PCIe lanes from the CPU itself, beyond the chipset interconnect.

It's possible that these will be some kind of embedded parts, as Alder Lake-N is said to come with up to eight cores. The limitation of PCIe lines, of which apparently only a total of nine will be offered, is something that might make it less appealing for embedded systems, especially if it requires a separate chipset. It's possible that Intel has designed these new SKUs for Chromebooks or other budget notebooks, but they'd have to be priced extremely affordably to be appealing, considering how cheap Chromebooks already are. The chips are also said to feature a full GT1 Gen 12.2 GPU with up to 32 EUs, so graphics performance should at least be comparable to Alder Lake-S desktop parts. We'd hazard a guess that the GPU clocks will be a lot lower though.

Intel's next-generation Xeon processors code-named Sapphire Rapids are on track to hit the market this year. These new processors are supposed to bring a wide array of new and improved features and a chance for Intel to show off its 10 nm SuperFin manufacturing process in the server market. Thanks to the Twitter user YuuKi_AnS, we have some of the first tests run in AIDA64 and Cinebench R15 benchmark suites. Yuuki managed to get ahold of DDR5-enabled Sapphire Rapids Xeon with 48 cores and 96 threads, equipped with a base frequency of 2.3 GHz and boost speeds of 3.3 GHz. The processor tested was an engineering sample with a Q-SPEC designation of "QYFQ" and made for Intel Socket E (LGA-4677). This CPU sample was locked at 270 Watt TDP.

Below, you can see the performance results of this processor, tested in the AIDA64 cache and memory benchmark and Cinebench R15 bench test. There is a comparison between AMD's Milan-X and Xeon Platinum 8380, so the numbers are more in check of what you can expect from the final product.

Digital computing continues to enrich our lives in more ways than we can imagine. We acquire, consume, and create content and services with a few clicks or taps of our fingertips. Exponential increases in compute performance, enabled by Moore's Law, play a significant role in making these experiences seamless. Moore's Law is also enabling us to democratize access to this enormous pool of processing power. Amazing things happen when a lot of compute is available to a lot of people without much friction.

Blockchain is a technology that has the potential to enable everyone to own much of the digital content and services they create. Some even call it an inflection point in computing, fundamentally disrupting the way we store, process and transact our digital assets as we usher in the era of metaverse and Web 3.0. No matter how the future evolves, it is certain the availability of a lot more compute to everyone will play a central role.